)]}' { "log": [ { "commit": "8e303f20f4b3611615118a22a737fd2dc7c4ef81", "tree": "15fd6d83c5bd196bc28f0cb07d714dda5b7a80e1", "parents": [ "2b022a82a01737012155b5ba462db74232ff1f2e" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Thu Sep 29 17:05:08 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Sep 29 16:29:53 2011 -0300" }, "message": "perf tools: Fix raw sample reading\n\nWrong pointer is being passed for raw data sanity checking, when parsing\nsample event.\n\nThis ends up with invalid event and perf record being stuck in\n__perf_session__process_events function during processing build IDs\n(process_buildids function).\n\nFollowing command hangs up in my setup:\n\t./perf record -e raw_syscalls:sys_enter ls\n\nThe fix is to use proper pointer to the raw data instead of the \u0027u\u0027\nunion.\n\nReviewed-by: David Ahern \u003cdsahern@gmail.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Neil Horman \u003cnhorman@tuxdriver.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLink: http://lkml.kernel.org/r/1317308709-9474-2-git-send-email-jolsa@redhat.com\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "2b022a82a01737012155b5ba462db74232ff1f2e", "tree": "18cabe19d2884ae5d5bf07e605d75c96fb5406e6", "parents": [ "9e59e0995a57048c53773f1de99c6637ad12dd25" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 15:38:53 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 15:38:53 2011 -0300" }, "message": "perf python: Add missing perf_event__parse_sample \u0027swapped\u0027 parm\n\nProblem introduced in 936be50, that missed one perf_event__parse_sample\nuser, the python binding.\n\nReported-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-ja4phms9618ggi657plyuch2@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "9e59e0995a57048c53773f1de99c6637ad12dd25", "tree": "f50f29fa9797e0be4e5a3a79e3ef2b190b7279dd", "parents": [ "af52aafad26fe83edc3ff95d6f630c2fc98a0c4c" ], "author": { "name": "Darren Hart", "email": "dvhart@linux.intel.com", "time": "Thu Sep 08 13:42:39 2011 -0700" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:38:07 2011 -0300" }, "message": "perf tools: Add support for disabling -Werror via WERROR\u003d0\n\nGCC often introduces new warnings with lots of false positives -\nbreaking -Werror builds. WERROR\u003d0 allows one to build perf without much\nfuss - while still encouraging people to send patches to avoid the fuss\nof having to type WERROR\u003d0.\n\nBisecting back to commits that produce a (mostly harmless) warning on\nsome compilers is more difficult. With WERROR\u003d0 one could bisect without\nworrying about harmless warnings.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLink: http://lkml.kernel.org/r/eac06c7cc4920e5d4830417d466161fb26c7359c.1315514559.git.dvhart@linux.intel.com\nSigned-off-by: Darren Hart \u003cdvhart@linux.intel.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "af52aafad26fe83edc3ff95d6f630c2fc98a0c4c", "tree": "ad71a13f3fa386c50fc1b0f3b50b20a0b3ce4b0e", "parents": [ "be96ea8ffa788dccb1ba895cced29db6687c4911" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Sep 14 15:54:30 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:37:54 2011 -0300" }, "message": "perf top: Fix userspace sample addr map offset\n\nThe \u0027perf top\u0027 tool came from the kernel where we had each DSO (vmlinux,\nmodules) loaded just once at a time.\n\nBut userspace may have DSOs loaded in multiple addresses (shared\nlibraries), requiring that we use the just resolved map instead of the\nfirst one found.\n\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-ag53wz0yllpgers0n2w7hchp@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "be96ea8ffa788dccb1ba895cced29db6687c4911", "tree": "17b805c4d27f2b06d8a11fdc0b33845321f8765e", "parents": [ "936be50306a92356367f330ef9d44f1f62478d22" ], "author": { "name": "Stephane Eranian", "email": "eranian@google.com", "time": "Fri Oct 22 17:25:01 2010 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:37:41 2011 -0300" }, "message": "perf symbols: Fix issue with binaries using 16-bytes buildids (v2)\n\nBuildid can vary in size. According to the man page of ld, buildid can\nbe 160 bits (sha1) or 128 bits (md5, uuid). Perf assumes buildid size of\n20 bytes (160 bits) regardless. When dealing with md5 buildids, it would\nthus read more than needed and that would cause mismatches and samples\nwithout symbols.\n\nThis patch fixes this by taking into account the actual buildid size as\nencoded int he section header. The leftover bytes are also cleared.\n\nThis second version fixes a minor issue with the memset() base position.\n\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Robert Richter \u003crobert.richter@amd.com\u003e\nCc: Stephane Eranian \u003ceranian@gmail.com\u003e\nLink: http://lkml.kernel.org/r/4cc1af3c.8ee7d80a.5a28.ffff868e@mx.google.com\nSigned-off-by: Stephane Eranian \u003ceranian@google.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "936be50306a92356367f330ef9d44f1f62478d22", "tree": "5a69dbe1ee295fb7b09fd2605a37032d0a6b59b5", "parents": [ "6bb8f311a870d6042e0310309eb3d607ae52fe3e" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Tue Sep 06 09:12:26 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:37:27 2011 -0300" }, "message": "perf tool: Fix endianness handling of u32 data in samples\n\nCurrently, analyzing PPC data files on x86 the cpu field is always 0 and\nthe tid and pid are backwards. For example, analyzing a PPC file on PPC\nthe pid/tid fields show:\n\n rsyslogd 1210/1212\n\nand analyzing the same PPC file using an x86 perf binary shows:\n\n rsyslogd 1212/1210\n\nThe problem is that the swap_op method for samples is\nperf_event__all64_swap which assumes all elements in the sample_data\nstruct are u64s. cpu, tid and pid are u32s and need to be handled\nindividually. Given that the swap is done before the sample is parsed,\nthe simplest solution is to undo the 64-bit swap of those elements when\nthe sample is parsed and do the proper swap.\n\nThe RAW data field is generic and perf cannot have programmatic knowledge\nof how to treat that data. Instead a warning is given to the user.\n\nThanks to Anton Blanchard for providing a data file for a mult-CPU\nPPC system so I could verify the fix for the CPU fields.\n\nv3 -\u003e v4:\n- fixed use of WARN_ONCE\n\nv2 -\u003e v3:\n- used WARN_ONCE for message regarding raw data\n- removed struct wrapper around union\n- fixed whitespace issues\n\nv1 -\u003e v2:\n- added a union for undoing the byte-swap on u64 and redoing swap on\n u32\u0027s to address compiler errors (see git commit 65014ab3)\n\nCc: Anton Blanchard \u003canton@samba.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "6bb8f311a870d6042e0310309eb3d607ae52fe3e", "tree": "18fae0525c4abf2a13bec13d38f7d77b96ad3b0d", "parents": [ "6a0e55d85babfccfd976703852ec8bab388b3a10" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Aug 31 11:51:45 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:37:17 2011 -0300" }, "message": "perf sort: Fix symbol sort output by separating unresolved samples by type\n\nI took a profile that suggested 60% of total CPU time was in the\nhypervisor:\n\n...\n 60.20% [H] 0x33d43c\n 4.43% [k] ._spin_lock_irqsave\n 1.07% [k] ._spin_lock\n\nUsing perf stat to get the user/kernel/hypervisor breakdown contradicted\nthis.\n\nThe problem is we merge all unresolved samples into the one unknown\nbucket. If add a comparison by sample type to sort__sym_cmp we get the\nreal picture:\n\n...\n 57.11% [.] 0x80fbf63c\n 4.43% [k] ._spin_lock_irqsave\n 1.07% [k] ._spin_lock\n 0.65% [H] 0x33d43c\n\nSo it was almost all userspace, not hypervisor as the initial profile\nsuggested.\n\nI found another issue while adding this. Symbol sorting sometimes shows\nmultiple entries for the unknown bucket:\n\n...\n 16.65% [.] 0x6cd3a8\n 7.25% [.] 0x422460\n 5.37% [.] yylex\n 4.79% [.] malloc\n 4.78% [.] _int_malloc\n 4.03% [.] _int_free\n 3.95% [.] hash_source_code_string\n 2.82% [.] 0x532908\n 2.64% [.] 0x36b538\n 0.94% [H] 0x8000000000e132a4\n 0.82% [H] 0x800000000000e8b0\n\nThis happens because we aren\u0027t consistent with our sorting. On\none hand we check to see if both symbols match and for two unresolved\nsamples sym is NULL so we match:\n\n if (left-\u003ems.sym \u003d\u003d right-\u003ems.sym)\n return 0;\n\nOn the other hand we use sample IP for unresolved samples when\ncomparing against a symbol:\n\n ip_l \u003d left-\u003ems.sym ? left-\u003ems.sym-\u003estart : left-\u003eip;\n ip_r \u003d right-\u003ems.sym ? right-\u003ems.sym-\u003estart : right-\u003eip;\n\nThis means unresolved samples end up spread across the rbtree and we\ncan\u0027t merge them all.\n\nIf we use cmp_null all unresolved samples will end up in the one bucket\nand the output makes more sense:\n\n...\n 39.12% [.] 0x36b538\n 5.37% [.] yylex\n 4.79% [.] malloc\n 4.78% [.] _int_malloc\n 4.03% [.] _int_free\n 3.95% [.] hash_source_code_string\n 2.26% [H] 0x800000000000e8b0\n\nAcked-by: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Ian Munsie \u003cimunsie@au1.ibm.com\u003e\nLink: http://lkml.kernel.org/r/20110831115145.4f598ab2@kryten\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "6a0e55d85babfccfd976703852ec8bab388b3a10", "tree": "965a6075c05d2600c50508b1dba4a0a7c5606614", "parents": [ "764e16a30a77a9c8346fbae6615e7c818ce9d00f" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Tue Aug 30 09:15:06 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:37:06 2011 -0300" }, "message": "perf symbols: Synthesize anonymous mmap events\n\nperf_event__synthesize_mmap_events does not create anonymous mmap events\neven though the kernel does. As a result an already running application\nwith dynamically created code will not get profiled - all samples end up\nin the unknown bucket.\n\nThis patch skips any entries with \u0027[\u0027 in the name to avoid adding events\nfor special regions (eg the vsyscall page). All other executable mmaps\nare assumed to be anonymous and an event is synthesized.\n\nAcked-by: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nLink: http://lkml.kernel.org/r/20110830091506.60b51fe8@kryten\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "764e16a30a77a9c8346fbae6615e7c818ce9d00f", "tree": "584d41f3bd611dfbf1345396b47629971fa035fd", "parents": [ "694bf407b06113f5e0f71764756f11903126fec0" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Thu Aug 25 10:17:55 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:36:53 2011 -0300" }, "message": "perf record: Create events initially disabled and enable after init\n\nperf-record currently creates events enabled. When doing a system wide\ncollection (-a arg) this causes data collection for perf\u0027s\ninitialization activities -- eg., perf_event__synthesize_threads().\n\nFor some events (e.g., context switch S/W event or tracepoints like\nsyscalls) perf\u0027s initialization causes a lot of events to be captured\nfrequently generating \"Check IO/CPU overload!\" warnings on larger\nsystems (e.g., 2 socket, quad core, hyperthreading).\n\nperf\u0027s initialization phase can be skipped by creating events\ndisabled and then enabling them once the initialization is done.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1314289075-14706-1-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "694bf407b06113f5e0f71764756f11903126fec0", "tree": "ee1593aa431242c12d9be39b7330dc70e5c4b57a", "parents": [ "318779086086f46127a249878eeebb3dc80578eb" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Aug 24 16:40:17 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:36:36 2011 -0300" }, "message": "perf symbols: Add some heuristics for choosing the best duplicate symbol\n\nTry and pick the best symbol based on a few heuristics:\n\n- Prefer a non weak symbol over a weak one\n- Prefer a global symbol over a non global one\n- Prefer a symbol with less underscores (idea taken from kallsyms.c)\n- If all else fails, choose the symbol with the longest name\n\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110824065243.161953371@samba.org\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "318779086086f46127a249878eeebb3dc80578eb", "tree": "e75fe854b2a6ae9bf2aed3a40e7614d65e5b05db", "parents": [ "3f5a42722b9e78a434d5a4ee5e607dc33c69ac80" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Aug 24 16:40:16 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:36:25 2011 -0300" }, "message": "perf symbols: Preserve symbol scope when parsing /proc/kallsyms\n\nkallsyms__parse capitalises the symbol type, so every symbol is marked\nglobal. Remove this and fix symbol_type__is_a to handle both local and\nglobal symbols.\n\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110824065243.077125989@samba.org\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "3f5a42722b9e78a434d5a4ee5e607dc33c69ac80", "tree": "9e6afedc145ecb85a3cd80916cac5717547e9755", "parents": [ "adb091846318f86e4f46c7d6a7b40d2f478abdbe" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Aug 24 16:40:15 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:36:12 2011 -0300" }, "message": "perf symbols: /proc/kallsyms does not sort module symbols\n\nkallsyms__parse assumes that /proc/kallsyms is sorted and sets the end\nof the previous symbol to the start of the current one.\n\nUnfortunately module symbols are not sorted, eg:\n\nffffffffa0081f30 t e1000_clean_rx_irq [e1000e]\nffffffffa00817a0 t e1000_alloc_rx_buffers [e1000e]\n\nSome symbols end up with a negative length and others have a length\nlarger than they should. This results in confusing perf output.\n\nWe already have a function to fixup the end of zero length symbols so\nuse that instead.\n\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110824065242.969681349@samba.org\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "adb091846318f86e4f46c7d6a7b40d2f478abdbe", "tree": "d5144d3e61af6632cbc13069555e71bc35e4a7b0", "parents": [ "f66fedcb723a9f118170200e21dbabb305f8c702" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Aug 24 16:40:14 2011 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:35:57 2011 -0300" }, "message": "perf symbols: Fix ppc64 SEGV in dso__load_sym with debuginfo files\n\n64bit PowerPC debuginfo files have an empty function descriptor section.\nI hit a SEGV when perf tried to use this section for symbol resolution.\n\nTo fix this we need to check the section is valid and we can do this by\nchecking for type SHT_PROGBITS.\n\nCc: \u003cstable@kernel.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nLink: http://lkml.kernel.org/r/20110824065242.895239970@samba.org\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "f66fedcb723a9f118170200e21dbabb305f8c702", "tree": "22ba9f64a356baf04737f8875c96a6a24146bd35", "parents": [ "d93dc5c4478c1fd5de85a3e8aece9aad7bbae044" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Sat Aug 20 14:39:23 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Sep 23 14:33:19 2011 -0300" }, "message": "perf probe: Fix regression of variable finder\n\nFix to call convert_variable() if previous call does not fail.\n\nTo call convert_variable, it ensures \"ret\" is 0. However, since\n\"ret\" has the return value of synthesize_perf_probe_arg() which\nalways returns positive value if it succeeded, perf probe doesn\u0027t\ncall convert_variable(). This will cause a SEGV when we add an\nevent with arguments.\n\nThis has to be fixed as it ensures \"ret\" is greater than 0\n(or not negative).\n\nThis regression has been introduced by my previous patch, f182e3e1.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110820053922.3286.65805.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "90e93648c41bd29a72f6ec55ce27a23c209eab8c", "tree": "705afc522c361f681567187018d80cf028fcb334", "parents": [ "3ae627b5a6c8f6bf992eee6a3399a1854641a476", "25904157168ddc8841748a729914f00e53d7e049" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 29 16:34:07 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 29 16:34:07 2011 -0700" }, "message": "Merge branch \u0027fixes\u0027 of master.kernel.org:/home/rmk/linux-2.6-arm\n\n* \u0027fixes\u0027 of master.kernel.org:/home/rmk/linux-2.6-arm:\n ARM: pm: avoid writing the auxillary control register for ARMv7\n ARM: pm: some ARMv7 requires a dsb in resume to ensure correctness\n ARM: pm: arm920/926: fix number of registers saved\n ARM: pm: CPU specific code should not overwrite r1 (v:p offset)\n ARM: 7066/1: proc-v7: disable SCTLR.TE when disabling MMU\n ARM: 7065/1: kexec: ensure new kernel is entered in ARM state\n ARM: 7003/1: vexpress: Add clock definition for the SP805.\n ARM: 7051/1: cpuimx* boards: fix mach-types errors\n ARM: 7019/1: Footbridge: select CLKEVT_I8253 for ARCH_NETWINDER\n ARM: 7015/1: ARM errata: Possible cache data corruption with hit-under-miss enabled\n ARM: 7014/1: cache-l2x0: Fix L2 Cache size calculation.\n ARM: 6967/1: ep93xx: ts72xx: fix board model detection\n ARM: 6965/1: ep93xx: add model detection for ts-7300 and ts-7400 boards\n ARM: cache: detect VIPT aliasing I-cache on ARMv6\n ARM: twd: register clockevents device before enabling PPI\n ARM: realview: ensure visibility of writes during reset\n ARM: perf: make name of arm_pmu_type consistent\n ARM: perf: fix prototype of release_pmu\n ARM: fix perf build with uclibc toolchains\n" }, { "commit": "43bece79796c2a39ec98998fd3f1071f04f3d8c3", "tree": "14aa396f084d9229fa1a164826115f3f0bd63a58", "parents": [ "d53e8365eaacfdb29253b39d186109f5b4fcc08d" ], "author": { "name": "Lin Ming", "email": "ming.m.lin@intel.com", "time": "Wed Aug 17 18:42:07 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 18 07:35:46 2011 -0300" }, "message": "perf tools: Add group event scheduling option to perf record/stat\n\nGroup event scheduling command line option is missing in perf\nrecord/stat.\n\nAdd it to perf record/stat, which is same as in perf top.\n\nReported-by: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/1313577727.2754.5.camel@hp6530s\nSigned-off-by: Lin Ming \u003cming.m.lin@intel.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "195bcbf5078d74c8e00d68f04eb8695196fb31e8", "tree": "16be79165faf9f56dfa93bcb96ae634c6582db91", "parents": [ "777d1d71db622a5e1ff703495741c3d257b532e5" ], "author": { "name": "Josh Boyer", "email": "jwboyer@redhat.com", "time": "Thu Aug 18 07:37:21 2011 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 18 07:24:53 2011 -0300" }, "message": "perf tools: Fix build against newer glibc\n\nUpstream glibc commit 295e904 added a definition for __attribute_const__\nto cdefs.h. This causes the following error when building perf:\n\nutil/include/linux/compiler.h:8:0: error: \"__attribute_const__\"\nredefined [-Werror] /usr/include/sys/cdefs.h:226:0: note: this is the\nlocation of the previous definition\n\nWrap __attribute_const__ in #ifndef as we do for __always_inline.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110818113720.GL2227@zod.bos.redhat.com\nSigned-off-by: Josh Boyer \u003cjwboyer@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "777d1d71db622a5e1ff703495741c3d257b532e5", "tree": "924cf43db988a0d08f42dfb7e271157869a4fc3a", "parents": [ "cc2d86b04d9ac28a6be6cb05da6ea8f014fd5aa0" ], "author": { "name": "Stephane Eranian", "email": "eranian@google.com", "time": "Sat Jul 23 04:10:43 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 18 07:21:13 2011 -0300" }, "message": "perf tools: Fix error handling of unknown events\n\nThere was a problem with the parse_events() code not printing the\ncorrect event name when an event was unknown and starting with an \u0027r\u0027.\nThe source of the problem was the way raw notation was parsed.\n\nWithout the patch:\n\t$ perf stat -e retired_foo\n\tinvalid event modifier: \u0027tired_foo\u0027\n\nWith the patch:\n\t$ perf stat -e retired_foo\n\tinvalid or unsupported event: \u0027retired_foo\u0027\n\nThis also covers the case where the name of the event was not printed at\nall when perf was linked with libpfm4.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/20110723021043.GA20178@quad\nSigned-off-by: Stephane Eranian \u003ceranian@google.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "cc2d86b04d9ac28a6be6cb05da6ea8f014fd5aa0", "tree": "a6111ef0349b82b982a504f633c0d820f0c95ae7", "parents": [ "77e57297b4ff3f602ba5105398d342a4b4a54774" ], "author": { "name": "Stephane Eranian", "email": "eranian@google.com", "time": "Tue Jun 07 18:19:36 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 18 07:20:31 2011 -0300" }, "message": "perf evlist: Fix missing event name init for default event\n\nWhen no event is given to perf record, perf top, a default event is\ninitialized (cycles). However, perf_evlist__add_default() was not\nsetting the symbolic name for the event. Perf top worked simply because\nit was reconstructing the name from the event code. But it should not\nhave to do this. This patch initializes the evsel-\u003ename field properly.\n\nThis second version improves the code flow on the non error path.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/20110607161936.GA8163@quad\nSigned-off-by: Stephane Eranian \u003ceranian@google.com\u003e\n[committer note: Use perf_evsel__delete() instead of plain free()]\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "77e57297b4ff3f602ba5105398d342a4b4a54774", "tree": "c77d759e51ceac8fe71c862a50b5fc2d08a5be54", "parents": [ "bdc2209fd246820de2816691ac0e82600885e1a8" ], "author": { "name": "Stephane Eranian", "email": "eranian@google.com", "time": "Mon May 23 14:39:17 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 18 07:19:15 2011 -0300" }, "message": "perf list: Fix exit value\n\nThis patch fixes an issue with the exit value of perf list:\n\n$ perf list; echo $?\n129\n\nperf list returns an error exit code even though there is no error.\n\nThere was a stray exit(129) in print_events(). This patch removes this\nexit().\n\n$ perf list; echo $?\n0\n\n$ perf list hw sw\n cpu-cycles OR cycles [Hardware event]\n stalled-cycles-frontend OR idle-cycles-frontend [Hardware event]\n stalled-cycles-backend OR idle-cycles-backend [Hardware event]\n instructions [Hardware event]\n cache-references [Hardware event]\n cache-misses [Hardware event]\n branch-instructions OR branches [Hardware event]\n branch-misses [Hardware event]\n bus-cycles [Hardware event]\n\n cpu-clock [Software event]\n task-clock [Software event]\n page-faults OR faults [Software event]\n minor-faults [Software event]\n major-faults [Software event]\n context-switches OR cs [Software event]\n cpu-migrations OR migrations [Software event]\n alignment-faults [Software event]\n emulation-faults [Software event]\n$ echo $?\n0\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/20110523123917.GA31060@quad\nSigned-off-by: Stephane Eranian \u003ceranian@google.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "bdc2209fd246820de2816691ac0e82600885e1a8", "tree": "34dca4b8f1a94d1a4b6a79cff6931e8284e27718", "parents": [ "eeca7360f756f7e36e846f35018df20808c7ef63", "3f4460a28fb2f73df6c32c3a305797abc01c0f9c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 14 11:48:29 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 14 11:48:29 2011 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent\n" }, { "commit": "e426f8e39bb612bfdd38fa7a75d10ba95787d1af", "tree": "37bb57051eabb390ea19bcd5ddfaebb8675e24fe", "parents": [ "73e0881d31406acc09eb11fa073108b43c89124e", "72dc53acd50db066a5a5ebe1f39fae73d7e62aa8" ], "author": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Aug 13 09:43:19 2011 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Aug 13 09:43:19 2011 +0100" }, "message": "Merge branch \u00273.1-fixes-for-rmk\u0027 of git://linux-arm.org/linux-2.6-wd into fixes\n" }, { "commit": "0ac8e58f3818795d02ac309bd57b4d93ec283a77", "tree": "4d1587423e36e19298ba0d0b4fbfd726fca832e5", "parents": [ "322a8b034003c0d46d39af85bf24fee27b902f48" ], "author": { "name": "Florian Fainelli", "email": "florian@openwrt.org", "time": "Tue Aug 09 12:24:17 2011 +0100" }, "committer": { "name": "Will Deacon", "email": "will.deacon@arm.com", "time": "Fri Aug 12 15:40:20 2011 +0100" }, "message": "ARM: fix perf build with uclibc toolchains\n\nlibio.h is not provided by uClibc, in order to be able to test the\ndefinition of __UCLIBC__ we need to include stdlib.h, which also\nincludes stddef.h, providing the definition of \u0027NULL\u0027.\n\nSigned-off-by: Florian Fainelli \u003cflorian@openwrt.org\u003e\nSigned-off-by: Will Deacon \u003cwill.deacon@arm.com\u003e\n" }, { "commit": "3f4460a28fb2f73df6c32c3a305797abc01c0f9c", "tree": "b3c6864c3da3d864471f74a5014800ac38f62dcd", "parents": [ "db0d2c6420eeb8fd669bac84d72f1ab828bbaa64" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:03:18 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:34:35 2011 -0300" }, "message": "perf probe: Filter out redundant inline-instances\n\nWith gcc4.6, some instances of concrete inlined function looks redundant\nand broken, because it appears inside of a concrete instance and its\ncall_file and call_line are same as the original abstruct\u0027s decl_file\nand decl_line respectively.\n\ne.g.\n [ d1aa] subprogram\n external (flag) Yes\n name (strp) \"add_timer\"\n decl_file (data1) 2\t\t;here is original\n decl_line (data2) 847\t\t;line and file\n prototyped (flag) Yes\n inline (data1) inlined (1)\n sibling (ref4) [ d1c6]\n...\n [ 11d84] subprogram\n abstract_origin (ref4) [ d1aa]\t; concrete instance\n low_pc (addr) .text+0x000000000000246f \u003cadd_timer\u003e\n high_pc (addr) .text+0x000000000000248b \u003cmod_timer_pending\u003e\n frame_base (block1) [ 0] call_frame_cfa\n sibling (ref4) [ 11dd9]\n [ 11d9f] formal_parameter\n abstract_origin (ref4) [ d1b9]\n location (data4) location list [ 701b]\n [ 11da8] inlined_subroutine\n abstract_origin (ref4) [ d1aa]\t; redundant instance\n low_pc (addr) .text+0x000000000000247e \u003cadd_timer+0xf\u003e\n high_pc (addr) .text+0x0000000000002480 \u003cadd_timer+0x11\u003e\n call_file (data1) 2\t\t; call line and file\n call_line (data2) 847\t\t; are same as above\n\nThose redundant instances leads unwilling results;\n\ne.g. find probe points inside of functions even if we specify\na function entry as below;\n\n$ perf probe -V add_timer\nAvailable variables at add_timer\n @\u003cadd_timer+0\u003e\n struct timer_list* timer\n @\u003cadd_timer+15\u003e\n (No matched variables)\n\nSo, this filters out those redundant instances based on call-site and\ndecl-site information.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110317.19900.59525.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "db0d2c6420eeb8fd669bac84d72f1ab828bbaa64", "tree": "da076fa408f501005fc851a28bbade134ad4ca62", "parents": [ "f182e3e13ca71b64b40fab1aef31fa6a78271648" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:03:11 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:32:10 2011 -0300" }, "message": "perf probe: Search concrete out-of-line instances\n\ngcc 4.6 generates a concrete out-of-line instance when there is a\nfunction which is implicitly inlined somewhere but also has its own\ninstance. The concrete out-of-line instance means that it has an\nabstract origin of the function which is referred by not only\ninlined-subroutines but also a concrete subprogram.\n\nSince current dwarf_func_inline_instances() can find only instances of\ninlined-subroutines, this introduces new die_walk_instances() to find\nboth of subprogram and inlined-subroutines.\n\ne.g. without this,\nAvailable variables at sched_group_rt_period\n @\u003ccpu_rt_period_read_uint+9\u003e\n struct task_group* tg\n\nperf probe failed to find actual subprogram instance of\nsched_group_rt_period().\n\nWith this,\n\nAvailable variables at sched_group_rt_period\n @\u003ccpu_rt_period_read_uint+9\u003e\n struct task_group* tg\n @\u003csched_group_rt_period+0\u003e\n struct task_group* tg\n\nNow it found the sched_group_rt_period() itself.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110311.19900.63997.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "f182e3e13ca71b64b40fab1aef31fa6a78271648", "tree": "6432a921ffc434d475093dca76bca745f9bc10b9", "parents": [ "221d061182b8ff5507d5768aeeecbc74f01c5dfa" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:03:05 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:29:34 2011 -0300" }, "message": "perf probe: Avoid searching variables in intermediate scopes\n\nFix variable searching logic to search one in inner than local scope or\nglobal(CU) scope. In the other words, skip searching in intermediate\nscopes.\n\ne.g., in the following code,\n\nint var1;\n\nvoid inline infunc(int i)\n{\n i++; \u003c--- [A]\n}\n\nvoid func(void)\n{\n int var1, var2;\n infunc(var2);\n}\n\nAt [A], \"var1\" should point the global variable \"var1\", however, if user\nmis-typed as \"var2\", variable search should be failed. However, current\nlogic searches variable infunc() scope, global scope, and then func()\nscope. Thus, it can find \"var2\" variable in func() scope. This may not\nbe what user expects.\n\nSo, it would better not search outer scopes except outermost (compile\nunit) scope which contains only global variables, when it failed to find\ngiven variable in local scope.\n\nE.g.\n\nWithout this:\n$ perf probe -V pre_schedule --externs \u003e without.vars\n\nWith this:\n$ perf probe -V pre_schedule --externs \u003e with.vars\n\nCheck the diff:\n$ diff without.vars with.vars\n88d87\n\u003c int cpu\n133d131\n\u003c long unsigned int* switch_count\n\nThese vars are actually in the scope of schedule(), the caller of\npre_schedule().\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "221d061182b8ff5507d5768aeeecbc74f01c5dfa", "tree": "79cd224ca76fd520e089860a3a0482ed2b718b0d", "parents": [ "13e27d7686c457c625242fc2c20be30eef942408" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:59 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:28:45 2011 -0300" }, "message": "perf probe: Fix to search local variables in appropriate scope\n\nFix perf probe to search local variables in appropriate local inlined\nfunction scope. For example, pre_schedule() has only 2 local variables,\nas below;\n\n$ perf probe -L pre_schedule\n\u003cpre_schedule@/home/mhiramat/ksrc/linux-2.6/kernel/sched.c:0\u003e\n 0 static inline void pre_schedule(struct rq *rq, struct task_struct *prev)\n {\n 2 if (prev-\u003esched_class-\u003epre_schedule)\n 3 prev-\u003esched_class-\u003epre_schedule(rq, prev);\n }\n\nHowever, current perf probe shows 4 local variables on pre_schedule(),\nbecause it searches variables in the caller(schedule()) scope.\n\n$ perf probe -V pre_schedule\nAvailable variables at pre_schedule\n @\u003cschedule+445\u003e\n int cpu\n long unsigned int* switch_count\n struct rq* rq\n struct task_struct* prev\n\nThis patch fixes this issue by searching variables in the local scope of\nthe instance of inlined function. Here is the result.\n\n$ perf probe -V pre_schedule\nAvailable variables at pre_schedule\n @\u003cschedule+445\u003e\n struct rq* rq\n struct task_struct* prev\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110259.19900.85664.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "13e27d7686c457c625242fc2c20be30eef942408", "tree": "8afd13bcf1201d4d7b25c9d46698cf05f359364d", "parents": [ "36c0c588b9ea979b619d6ddced410f9551e4c5fa" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:53 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:27:11 2011 -0300" }, "message": "perf probe: Warn when more than one line are given\n\nCheck multiple --lines option and print warning informing that only the\nfirst specified --line option is valid.\n\nChanges from the 1st post:\n\n- Accept only the first option instead of the last.\n- Fix warning message according to David\u0027s comment.\n- Mark as a bugfix.\n\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110253.19900.96192.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "36c0c588b9ea979b619d6ddced410f9551e4c5fa", "tree": "a8a9ae6d431a1305d00d8e2e4044e41bd0253525", "parents": [ "b0e9cb2802d4bf50955cca8a7d87cf94ebf750a5" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:47 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:25:38 2011 -0300" }, "message": "perf probe: Fix to walk all inline instances\n\nFix line-range collector to walk all instances of inlined function,\nbecause some execution paths can be optimized out depending on the\nfunction argument of instances.\n\nE.g.)\ninline_func (arg) {\n\tif (arg)\n\t\tdo_something;\n\telse\n\t\tdo_another;\n}\n\nfunc_A() {\n\tinline_func(1)\n}\n\nfunc_B() {\n\tinline_func(0)\n}\n\nIn this case, func_A may have only do_something code and func_B may have\nonly do_another.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Masami Hiramatsu \u003cmasami.hiramatsu@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110247.19900.93702.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "b0e9cb2802d4bf50955cca8a7d87cf94ebf750a5", "tree": "4ad27542e70558f7b3f13b4d56a031d3c53fc452", "parents": [ "a128405c6b40371c59c34b00cc66ed06285b9551" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:41 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:23:39 2011 -0300" }, "message": "perf probe: Fix to search nested inlined functions in CU\n\nFix perf probe to walk through the lines of all nested inlined function\ncall sites and declared lines when a whole CU is passed to the line\nwalker.\n\nThe die_walk_lines() can have two different type of DIEs, subprogram (or\ninlined-subroutine) DIE and CU DIE.\n\nIf a caller passes a subprogram DIE, this means that the walker walk on\nlines of given subprogram. In this case, it just needs to search on\ndirect children of DIE tree for finding call-site information of inlined\nfunction which directly called from given subprogram.\n\nOn the other hand, if a caller passes a CU DIE to the walker, this means\nthat the walker have to walk on all lines in the source files included\nin given CU DIE. In this case, it has to search whole DIE trees of all\nsubprograms to find the call-site information of all nested inlined\nfunctions.\n\nWithout this patch:\n\n$ perf probe --line kernel/cpu.c:151-157\n\u003c/home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151\u003e\n\n static int cpu_notify(unsigned long val, void *v)\n {\n 154 return __cpu_notify(val, v, -1, NULL);\n }\n\nWith this:\n$ perf probe --line kernel/cpu.c:151-157\n\u003c/home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151\u003e\n\n 152 static int cpu_notify(unsigned long val, void *v)\n {\n 154 return __cpu_notify(val, v, -1, NULL);\n }\n\nAs you can see, --line option with source line range shows the declared\nlines as probe-able.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110241.19900.34994.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "a128405c6b40371c59c34b00cc66ed06285b9551", "tree": "4ce07ab8dd02161b5acd678498652916ef07b309", "parents": [ "8afa2a707d3d1320df5d35966729ac5262da737d" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:35 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:22:46 2011 -0300" }, "message": "perf probe: Fix line walker to check CU correctly\n\nFix line walker to check whether a given DIE is CU or not.\n\nActually this function accepts CU, subprogram and inlined_subroutine\nDIEs.\n\nWithout this fix, perf probe always fails to analyze lines on inlined\nfunctions;\n\n$ perf probe -L pre_schedule\nDebuginfo analysis failed. (-2)\n Error: Failed to show lines. (-2)\n\nThis fixes that bug, as below.\n\n$ perf probe -L pre_schedule\n\u003cpre_schedule@/home/mhiramat/ksrc/linux-2.6/kernel/sched.c:0\u003e\n 0 static inline void pre_schedule(struct rq *rq, struct task_struct *prev\n {\n 2 if (prev-\u003esched_class-\u003epre_schedule)\n 3 prev-\u003esched_class-\u003epre_schedule(rq, prev);\n }\n\n /* rq-\u003elock is NOT held, but preemption is disabled */\n\nChanges from v1:\n - Update against current tip tree.(Fix dwarf-aux.c)\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Masami Hiramatsu \u003cmasami.hiramatsu@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110235.19900.20614.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "8afa2a707d3d1320df5d35966729ac5262da737d", "tree": "92126a1e215cb43bd1f29db65e33f9ad3c5fd5e9", "parents": [ "e9b52ef2228cd0bed7a4465c693a39489e2c338d" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Thu Aug 11 20:02:29 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 09:21:15 2011 -0300" }, "message": "perf probe: Fix a memory leak for scopes array\n\nFix a memory leak for scopes array when it finds a variable in the\nglobal scope.\n\nReviewed-by: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: yrl.pp-manager.tt@hitachi.com\nLink: http://lkml.kernel.org/r/20110811110229.19900.63019.stgit@fedora15\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "e9b52ef2228cd0bed7a4465c693a39489e2c338d", "tree": "5a3ea5c427fc93cbdf48b383a8a7d37e7cac567f", "parents": [ "f57b05ed532ccf3b3e22878a5678ca10de50ad29" ], "author": { "name": "Vasiliy Kulikov", "email": "segoon@openwall.com", "time": "Fri Aug 12 00:55:37 2011 +0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Aug 12 08:28:17 2011 -0300" }, "message": "perf: fix temporary file ownership check\n\nA file in /tmp/ might be a symlink, so lstat() should be used instead of\nstat().\n\nAcked-by: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@kernel.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/20110811205537.GA22864@albatros\nSigned-off-by: Vasiliy Kulikov \u003csegoon@openwall.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "f57b05ed532ccf3b3e22878a5678ca10de50ad29", "tree": "97fed90fc6181939af5a29dfc9624163832b34e6", "parents": [ "fc8ed7be738ffb1b3b0140ed2de6def38b9a7101" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Wed Jun 01 21:43:46 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Aug 11 08:58:03 2011 -0300" }, "message": "perf report: Use properly build_id kernel binaries\n\nIf we bring the recorded perf data together with kernel binary from another\nmachine using:\n\n\ton server A:\n\tperf archive\n\n\ton server B:\n\ttar xjvf perf.data.tar.bz2 -C ~/.debug\n\nthe build_id kernel dso is not properly recognized during the \"perf report\"\ncommand on server B.\n\nThe reason is, that build_id dsos are added during the session initialization,\nwhile the kernel maps are created during the sample event processing.\n\nThe machine__create_kernel_maps functions ends up creating new dso object for\nkernel, but it does not check if we already have one added by build_id\nprocessing.\n\nAlso the build_id reading ABI quirk added in commit:\n\n - commit b25114817a73bbd2b84ce9dba02ee1ef8989a947\n perf build-id: Add quirk to deal with perf.data file format breakage\n\npopulates the \"struct build_id_event::pid\" with 0, which\nis later interpreted as DEFAULT_GUEST_KERNEL_ID.\n\nThis is not always correct, so it\u0027s better to guess the pid\nvalue based on the \"struct build_id_event::header::misc\" value.\n\n- Tested with data generated on x86 kernel version v2.6.34\n and reported back on x86_64 current kernel.\n- Not tested for guest kernel case.\n\nNote the problem stays for PERF_RECORD_MMAP events recorded by perf that\ndoes not use proper pid (HOST_KERNEL_ID/DEFAULT_GUEST_KERNEL_ID). They are\nmisinterpreted within the current perf code. Probably there\u0027s not much we\ncan do about that.\n\nCc: Avi Kivity \u003cavi@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Yanmin Zhang \u003cyanmin_zhang@linux.intel.com\u003e\nLink: http://lkml.kernel.org/r/20110601194346.GB1934@jolsa.brq.redhat.com\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "fc8ed7be738ffb1b3b0140ed2de6def38b9a7101", "tree": "756a46bd805d24a36176987d553928b3defa2b41", "parents": [ "981c1252691f4b855f2bb47ea93fb6052ea3aee2" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Aug 10 12:42:26 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Aug 10 12:42:26 2011 -0300" }, "message": "perf top browser: Remove spurious helpline update\n\nIt will be immediately replaced in perf_top_browser__run.\n\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-q7e2jzb44elqpkvdllk94x0i@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "7676ebbaf21c3828e6315baadb6fcde448aa79b4", "tree": "f940029a96b3d82b84a4433d1e2b917ff1d2b166", "parents": [ "e710574de10b181c159a67af75af0245de33a4b9", "981c1252691f4b855f2bb47ea93fb6052ea3aee2" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 10 10:20:52 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 10 10:20:52 2011 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent\n" }, { "commit": "981c1252691f4b855f2bb47ea93fb6052ea3aee2", "tree": "7cb1acf6cbaf11c1baf3a474c891a4798a8bbcda", "parents": [ "580cabed88ebc631e740b16010f2fa6ba882652f" ], "author": { "name": "Pekka Enberg", "email": "penberg@kernel.org", "time": "Tue Aug 09 22:54:18 2011 +0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Aug 09 15:23:08 2011 -0300" }, "message": "perf symbols: Check \u0027/tmp/perf-\u0027 symbol file ownership\n\nThe external symbol files are generated by JIT compilers, for example, but we\nneed to make sure they\u0027re ours before injecting them to \u0027perf report\u0027.\n\nRequested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLink: http://lkml.kernel.org/r/1312919658-17158-1-git-send-email-penberg@kernel.org\nSigned-off-by: Pekka Enberg \u003cpenberg@kernel.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "580cabed88ebc631e740b16010f2fa6ba882652f", "tree": "4a62164f6936927bbc1b41681dff3cf7bb2638be", "parents": [ "4c09bafae37d870ab8efc50faeeb4855cb55b5b7" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Tue Aug 09 14:46:51 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Aug 09 13:32:12 2011 -0300" }, "message": "perf sched: Usage leftover from trace -\u003e script rename\n\nThe \u0027perf sched\u0027 command usage still showing \u0027trace\u0027 command instead of\nthe \u0027script\u0027 command.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110809124651.GD2056@jolsa.brq.redhat.com\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "4c09bafae37d870ab8efc50faeeb4855cb55b5b7", "tree": "9e750321369285dec47289fe4af8acd221140c0d", "parents": [ "069e3725dd9be3b759a98e8c80ac5fc38b392b23" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Mon Aug 08 23:03:34 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Aug 09 13:31:38 2011 -0300" }, "message": "perf sched: Do not delete session object prematurely\n\nThe session object is released prematurely when processing events for\nlatency command. The session\u0027s thread objects are used within the\noutput_lat_thread function.\n\nRunnning following commands:\n\n # perf sched record\n # perf sched latency\n\nthe latter displays incorrect data and might cause access violation.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/1312837414-3819-1-git-send-email-jolsa@redhat.com\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "069e3725dd9be3b759a98e8c80ac5fc38b392b23", "tree": "0696e18fcf5eb6f2908876b1a09647c82af5b31a", "parents": [ "9941c96ad869d10f7e34e03990ce450ab8fcb83d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Aug 09 12:42:13 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Aug 09 12:42:13 2011 -0300" }, "message": "perf tools: Check $HOME/.perfconfig ownership\n\nJust like we do already for perf.data files.\n\nRequested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Ben Hutchings \u003cben@decadent.org.uk\u003e\nCc: Christian Ohm \u003cchr.ohm@gmx.net\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Jonathan Nieder \u003cjrnieder@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-qgokmxsmvppwpc5404qhyk7e@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "e710574de10b181c159a67af75af0245de33a4b9", "tree": "292aeb4ab31d7e954c146b8b00829c67501fd0d6", "parents": [ "a34668f6beb4ab01e07683276d6a24bab6c175e0", "9941c96ad869d10f7e34e03990ce450ab8fcb83d" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 09 16:44:27 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 09 16:44:27 2011 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent\n" }, { "commit": "9941c96ad869d10f7e34e03990ce450ab8fcb83d", "tree": "df08be9a56eccc1c7cf184d19e66b2a24192c318", "parents": [ "aba8d056078e47350d85b06a9cabd5afcc4b72ea" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Fri Jul 22 13:33:07 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Aug 08 12:54:26 2011 -0300" }, "message": "perf tools: Add support to install perf python extension\n\nAdding install-python_ext target to install python extension related\nfiles. Installation directory is governed by python distutils package\nand follows the DESTDIR variable settings.\n\nAlso moving python extension build output into \u0027$(O)python_ext_build\u0027\ndirectory and making it configurable via PYTHON_EXTBUILD variable.\n\nKeeping the \u0027$(O)python/perf.so\u0027 file, so it could be used for testing\nas of until now.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110722113307.GA1931@jolsa.brq.redhat.com\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "aba8d056078e47350d85b06a9cabd5afcc4b72ea", "tree": "9ad19d7d6e98a459010796e80b70a5964b8dbe82", "parents": [ "8b7e0b34b8e94f34597e4b804bbb8bb7e27df040" ], "author": { "name": "Jonathan Nieder", "email": "jrnieder@gmail.com", "time": "Fri Aug 05 18:58:38 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Aug 08 09:46:32 2011 -0300" }, "message": "perf tools: do not look at ./config for configuration\n\nIn addition to /etc/perfconfig and $HOME/.perfconfig, perf looks for\nconfiguration in the file ./config, imitating git which looks at\n$GIT_DIR/config. If ./config is not a perf configuration file, it\nfails, or worse, treats it as a configuration file and changes behavior\nin some unexpected way.\n\n\"config\" is not an unusual name for a file to be lying around and perf\ndoes not have a private directory dedicated for its own use, so let\u0027s\njust stop looking for configuration in the cwd. Callers needing\ncontext-sensitive configuration can use the PERF_CONFIG environment\nvariable.\n\nRequested-by: Christian Ohm \u003cchr.ohm@gmx.net\u003e\nCc: 632923@bugs.debian.org\nCc: Ben Hutchings \u003cben@decadent.org.uk\u003e\nCc: Christian Ohm \u003cchr.ohm@gmx.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110805165838.GA7237@elie.gateway.2wire.net\nSigned-off-by: Jonathan Nieder \u003cjrnieder@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "8b7e0b34b8e94f34597e4b804bbb8bb7e27df040", "tree": "1e57495b6a2dd79ad85eb5b77b155e7b48fa6ed7", "parents": [ "cf8dc9ff29b55955197ae6f628b19f7f41f6e582" ], "author": { "name": "Kusanagi Kouichi", "email": "slash@ac.auone-net.jp", "time": "Sun Aug 07 17:39:31 2011 +0900" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Aug 08 09:43:22 2011 -0300" }, "message": "perf tools: Make clean leaves some files\n\nUse LIB_OBJS and BUILTIN_OBJS for .o files.\n\nLIB_FILE is already prefixed with OUTPUT.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/20110807083932.9C0E514C03B@msa103.auone-net.jp\nSigned-off-by: Kusanagi Kouichi \u003cslash@ac.auone-net.jp\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "cf8dc9ff29b55955197ae6f628b19f7f41f6e582", "tree": "0477fefda15fbfee777db0e22f4cff0d11d0be1c", "parents": [ "ce27a443d17dccf613079a7147cf0d220bc4ec82" ], "author": { "name": "Zhu Yanhai", "email": "zhu.yanhai@gmail.com", "time": "Sat Jul 30 22:13:52 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Aug 08 09:41:35 2011 -0300" }, "message": "perf lock: Dropping unsupported \u0027:r\u0027 modifier\n\nLooks to me like the :r modifier is not supported anymore, so remove it\nfrom the list of events. Without this fix \u0027perf lock record\u0027 doesn\u0027t\nwork.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Zhu Yanhai \u003cgaoyang.zyh@taobao.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/1312035232-9534-1-git-send-email-gaoyang.zyh@taobao.com\nSigned-off-by: Zhu Yanhai \u003cgaoyang.zyh@taobao.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "ce27a443d17dccf613079a7147cf0d220bc4ec82", "tree": "c9fecd9884b167a2c4bdae80653d919b2ba6474e", "parents": [ "00894ce9b85887caa0c16e18757004b9cc9f64cf" ], "author": { "name": "Jovi Zhang", "email": "bookjovi@gmail.com", "time": "Mon Jul 25 22:08:08 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Aug 08 09:35:41 2011 -0300" }, "message": "perf probe: Fix coredump introduced by probe module option\n\nperf will coredump if the user doesn\u0027t give the \"-m\" option in probe\ncommand, this patch fixes it.\n\n[root@localhost perf]# ./perf probe --add\u003d\u0027PROBE\u0027\nSegmentation fault (core dumped)\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/1311602888-2389-1-git-send-email-bookjovi@gmail.com\nSigned-off-by: Jovi Zhang \u003cbookjovi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "6d158f3ec537bd6d3786196b6db97fcc0f973aef", "tree": "be45a7498c9e24f6759adb9c0cd2153a6686fe22", "parents": [ "3272cab4063467410802367a8d69f06c65b2a866", "00894ce9b85887caa0c16e18757004b9cc9f64cf" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 05 10:35:55 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 05 10:35:55 2011 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent\n" }, { "commit": "00894ce9b85887caa0c16e18757004b9cc9f64cf", "tree": "0f64fd92048d0b782c7fa025625f97bb06391207", "parents": [ "3e9f45a7a4179604ccbae1589de0e7165bc6fcd0" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Aug 03 12:33:24 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Aug 03 12:33:24 2011 -0300" }, "message": "perf report: Use ui__warning in some more places\n\nSo that we get a proper warning in the TUI in cases like:\n\n $ perf report --stdio -g fractal,0.5,caller --sort pid\n Selected -g but no callchain data. Did you call \u0027perf record\u0027 without -g?\n $\n\nThe --stdio case is ok because it uses fprintf, ui__warning is needed to\nfigure out if --stdio or --tui is being used.\n\nCc: Arun Sharma \u003casharma@fb.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-ag9fz2wd17mbbfjsbznq1wms@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "3e9f45a7a4179604ccbae1589de0e7165bc6fcd0", "tree": "c686afbfa9d5e67d15a0941c8e718cf56fc2aa08", "parents": [ "4152ab377b55e9d3e5700de00ef799519ead698d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Jul 25 17:13:27 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Jul 25 17:13:27 2011 -0300" }, "message": "perf python: Add PERF_RECORD_{LOST,READ,SAMPLE} routine tables\n\nSo those friggin \"spurious\" PERF_RECORD_MMAP events were actually a\nbrain fart copy\u0027n\u0027paste error in the python binding, doh. I.e. they\nweren\u0027t MMAPs, just SAMPLEs.\n\nFix it by providing routines for these events instead of using the MMAP\nones.\n\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-b0rc8y5jd03f9f11kftodvkm@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "4152ab377b55e9d3e5700de00ef799519ead698d", "tree": "f0b01d51b9efe519ecbc9827bf1116de2a2317c3", "parents": [ "4f9bae351d299149a84f76cd34bf0150614e8c8e" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Jul 25 11:06:19 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Jul 25 11:06:19 2011 -0300" }, "message": "perf evlist: Introduce \u0027disable\u0027 method\n\nTo remove the last case of access to the FD() macro outside the library.\n\nInspired by a patch by Borislav that moved the FD() macro to util.h, for\nnamespace concerns I rather preferred to constrain it to ev{sel,list}.c.\n\nCc: Borislav Petkov \u003cbp@amd64.org\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-qn893qsstcg366tkucu649qj@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c0c463d34adf0c150e5e24fa412fa23f3f7ddc27", "tree": "dfdf2ee7c6bb6662e8aa750c9145618085b092fd", "parents": [ "e72542191cbba4cf7fda21cb22e26b42d7415daf", "a03fc8c375511b6ab43184ab191af3218a919646", "f505c553dbe24b18a8590eb0eb5890a839acd0c3", "a7de915383a6d5c05663f9badbd10d5a87bc1586", "08a4a43fc407d780bdde36d98f89c0dbb2a6be6b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 23 10:33:08 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 23 10:33:08 2011 -0700" }, "message": "Merge branches \u0027x86-urgent-for-linus\u0027, \u0027core-debug-for-linus\u0027, \u0027irq-core-for-linus\u0027 and \u0027perf-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n um: Make rwsem.S depend on CONFIG_RWSEM_XCHGADD_ALGORITHM\n\n* \u0027core-debug-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n debug: Make CONFIG_EXPERT select CONFIG_DEBUG_KERNEL to unhide debug options\n\n* \u0027irq-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n genirq: Remove unused CHECK_IRQ_PER_CPU()\n\n* \u0027perf-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n perf tools, x86: Fix 32-bit compile on 64-bit system\n" }, { "commit": "4f9bae351d299149a84f76cd34bf0150614e8c8e", "tree": "342086b25b25b3074cf3d91b2568957b5baf668d", "parents": [ "7fcfd1abd6480d3b9ef17f5759c175e036e835cf" ], "author": { "name": "Han Pingtian", "email": "phan@redhat.com", "time": "Mon Jul 18 11:13:14 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jul 22 08:59:26 2011 -0300" }, "message": "perf buildid-cache: Zero out buffer of filenames when adding/removing buildid\n\nThe readlink() function doesn\u0027t append a null byte to buf. So we should\nzero out buf with zalloc(). Or we\u0027ll see sometimes error like this:\n\n[root@intel-s3e36-01]~# /usr/bin/perf buildid-cache -a /lib/modules/2.6.32-130.el6.x86_64/kernel/crypto/twofish_common.ko -v\nAdding f64ba8efd5f53c7ad332fc17db1d21de309038e1 /lib/modules/2.6.32-130.el6.x86_64/kernel/crypto/twofish_common.ko: Ok\n[root@intel-s3e36-01]~# /usr/bin/perf buildid-cache -r /lib/modules/2.6.32-130.el6.x86_64/kernel/crypto/twofish_common.ko -v\nRemoving f64ba8efd5f53c7ad332fc17db1d21de309038e1 /lib/modules/2.6.32-130.el6.x86_64/kernel/crypto/twofish_common.ko: FAIL\n/lib/modules/2.6.32-130.el6.x86_64/kernel/crypto/twofish_common.ko wasn\u0027t in the cache\n\nThe change in build_id_cache__add_s() is a defense.\n\nTested-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: Jiri Olsa \u003cjolsa@redhat.com\u003e\nLink: http://lkml.kernel.org/r/20110718031314.GA5802@hpt.nay.redhat.com\nSigned-off-by: Han Pingtian \u003cphan@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "08a4a43fc407d780bdde36d98f89c0dbb2a6be6b", "tree": "2ec7649b3a6423d633508f1a293920d8f5ee8665", "parents": [ "cf6ace16a3cd8b728fb0afa68368fd40bbeae19f" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Mon Jul 11 15:38:24 2011 -0600" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 13:42:30 2011 +0200" }, "message": "perf tools, x86: Fix 32-bit compile on 64-bit system\n\nBuilds for 32-bit perf binaries on a 64-bit host currently fail\nwith this error:\n\n [...]\n bench/../../../arch/x86/lib/memcpy_64.S: Assembler messages:\n bench/../../../arch/x86/lib/memcpy_64.S:29: Error: bad register name `%rdi\u0027\n bench/../../../arch/x86/lib/memcpy_64.S:34: Error: invalid instruction suffix for `movs\u0027\n bench/../../../arch/x86/lib/memcpy_64.S:50: Error: bad register name `%rdi\u0027\n bench/../../../arch/x86/lib/memcpy_64.S:61: Error: bad register name `%rdi\u0027\n ...\n\nThe problem is the detection of the host arch without considering passed in\nflags. This change fixes 32-bit builds via:\n\nmake EXTRA_CFLAGS\u003d-m32\n\nand 64-bit builds still reference the memcpy_64.S.\n\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: \u003cstable@kernel.org\u003e\nLink: http://lkml.kernel.org/r/1310420304-21452-1-git-send-email-dsahern@gmail.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "baf040a0d1ac6319725c0fe400503683ac016580", "tree": "7491f6dbaf6d26017cbf9a0ec0428f8c90619530", "parents": [ "13b62567e909125145f90e91625b1062196d1258" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Thu Jul 14 11:25:34 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 10:41:14 2011 +0200" }, "message": "perf tools: Make test use the preset debugfs path\n\nUse preset debugfs path instead of hardcoded one.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: acme@redhat.com\nCc: a.p.zijlstra@chello.nl\nCc: paulus@samba.org\nLink: http://lkml.kernel.org/r/1310635534-4013-4-git-send-email-jolsa@redhat.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "13b62567e909125145f90e91625b1062196d1258", "tree": "1a8ad571b39ad97fdae1db6a33753ee94de21747", "parents": [ "f120f9d51be3a7db8991e7b78dc08bab5f8ab8f3" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Thu Jul 14 11:25:33 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 10:41:13 2011 +0200" }, "message": "perf tools: Add automated tests for events parsing\n\nAdding builtin test for parse_events function, which is\nresponsible for parsing/processing \"-e\" option for\nstat/top/record commands.\n\nThis new test will run within the builtin test command suite\n(perf test).\n\nOne or several tests were added for each type of event.\nMore tests could be added easily if needed.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: acme@redhat.com\nCc: a.p.zijlstra@chello.nl\nCc: paulus@samba.org\nLink: http://lkml.kernel.org/r/1310635534-4013-3-git-send-email-jolsa@redhat.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f120f9d51be3a7db8991e7b78dc08bab5f8ab8f3", "tree": "237926a6231f4009015b8ce4119935a455069395", "parents": [ "adc4bf9955856f8aa081ba613dbf56ffd664f0b7" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Thu Jul 14 11:25:32 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 10:41:11 2011 +0200" }, "message": "perf tools: De-opt the parse_events function\n\nMoving out the option parameter from parse_events function,\nand adding new parse_events_option function instead.\n\nThe option parameter is used only to carry \"struct perf_evlist\"\npointer for chaining new events. Putting it away, enable us\nto call parse_events from other places without using the\noption parameter.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: acme@redhat.com\nCc: a.p.zijlstra@chello.nl\nCc: paulus@samba.org\nLink: http://lkml.kernel.org/r/1310635534-4013-2-git-send-email-jolsa@redhat.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "adc4bf9955856f8aa081ba613dbf56ffd664f0b7", "tree": "c110522a1a45d95b3452987e141d383ffd9ac81a", "parents": [ "eda3913bb70ecebac13adccffe1e7f96e93cee02" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Mon May 30 09:16:27 2011 -0600" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 10:09:28 2011 +0200" }, "message": "perf script: Fix display of IP address for non-callchain path\n\nNon-callchain path is using al.addr which prints as:\n openssl 14564 17672.003587: 7862d _x86_64_AES_encrypt_compact\n\nThis should be sample-\u003eip to print as:\n openssl 14564 17672.003587: 3f7867862d _x86_64_AES_encrypt_compact\n\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: acme@ghostprotocols.net\nCc: peterz@infradead.org\nCc: paulus@samba.org\nLink: http://lkml.kernel.org/r/1306768587-15376-1-git-send-email-dsahern@gmail.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "eda3913bb70ecebac13adccffe1e7f96e93cee02", "tree": "832f84f625dcfcf30eeb0ca88d58fe7774f4327e", "parents": [ "0111919da268e1ced315e009ad0d0435a2fb32ac" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Fri Jul 15 12:34:09 2011 -0600" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:57:36 2011 +0200" }, "message": "perf tools: Fix endian conversion reading event attr from file header\n\nThe perf_event_attr struct has two __u32\u0027s at the top and\nthey need to be swapped individually.\n\nWith this change I was able to analyze a perf.data collected in a\n32-bit PPC VM on an x86 system. I tested both 32-bit and 64-bit\nbinaries for the Intel analysis side; both read the PPC perf.data\nfile correctly.\n\n-v2:\n - changed the existing perf_event__attr_swap() to swap only elements\n of perf_event_attr and exported it for use in swapping the\n attributes in the file header\n - updated swap_ops used for processing events\n\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: acme@ghostprotocols.net\nCc: peterz@infradead.org\nCc: paulus@samba.org\nCc: \u003cstable@kernel.org\u003e\nLink: http://lkml.kernel.org/r/1310754849-12474-1-git-send-email-dsahern@gmail.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "0111919da268e1ced315e009ad0d0435a2fb32ac", "tree": "41a9f36b810820df712b6cb5e1c222891b2f972c", "parents": [ "40bcea7bbe8fe452a2d272e2ffd3dea281eec9ff" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Wed Jul 13 22:58:18 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:54:51 2011 +0200" }, "message": "perf tools: Add missing \u0027node\u0027 alias to the hw_cache[] array\n\nAdd \"node\" as a simple alias for NODE cache events.\n\nThe addition of NODE cache events broke the parse_alias\nfunction, so any mismatched event caused the segfault, like:\n\n # ./perf stat -e krava ls\n\nThe hw_cache/hw_cache_op/hw_cache_result arrays needs to follow\nPERF_COUNT_HW_CACHE_*MAX enums. Adding those MAXs to be size\nof those arrays, so possible ommision in future wil not lead to\nsegfault.\n\nAdding read/write/prefetch as allowed operations for node cache\nevent.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: acme@redhat.com\nLink: http://lkml.kernel.org/r/20110713205818.GB7827@jolsa.brq.redhat.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "14a8fd7ceea6915c613746203d6e9a2bf273f16c", "tree": "738803bc847efa3a17e9076922f06ceaca20d8f0", "parents": [ "190b57fcb9c5fed5414935a174094f534fc510bc" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:51 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:25:12 2011 -0400" }, "message": "perf probe: Support adding probes on offline kernel modules\n\nSupport adding probes on offline kernel modules. This enables\nperf-probe to trace kernel-module init functions via perf-probe.\nIf user gives the path of module with -m option, perf-probe\nexpects the module is offline.\nThis feature works with --add, --funcs, and --vars.\n\nE.g)\n # perf probe -m /lib/modules/`uname -r`/kernel/fs/btrfs/btrfs.ko \\\n -a \"extent_io_init:5 extent_state_cache\"\n Add new events:\n probe:extent_io_init (on extent_io_init:5 with extent_state_cache)\n probe:extent_io_init_1 (on extent_io_init:5 with extent_state_cache)\n\n You can now use it on all perf tools, such as:\n\n perf record -e probe:extent_io_init_1 -aR sleep 1\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072751.6528.10230.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "190b57fcb9c5fed5414935a174094f534fc510bc", "tree": "952c19ed78abe454715d357fd5d0f8c6af9efd55", "parents": [ "ff741783506c340035659a71be68ddb4068760d1" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:45 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:19:08 2011 -0400" }, "message": "perf probe: Add probed module in front of function\n\nAdd probed module name and \":\" in front of function name\nif -m module option is given. In the result, the symbol\nname passed to kprobe-tracer becomes MODULE:FUNCTION,\nso that kallsyms can solve it as a symbol in the module\ncorrectly.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072745.6528.26416.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "ff741783506c340035659a71be68ddb4068760d1", "tree": "90ccff5203ae54e738ab98d6a73f88fa5bc5a5b1", "parents": [ "e0d153c69040bb37cbdf09deb52fee3013c07742" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:39 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:14:19 2011 -0400" }, "message": "perf probe: Introduce debuginfo to encapsulate dwarf information\n\nIntroduce debuginfo to encapsulate dwarf information.\nThis new object allows us to reuse and expand debuginfo easily.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072739.6528.12438.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "e0d153c69040bb37cbdf09deb52fee3013c07742", "tree": "e008ba8ac1f328b6938e80b9208d64c4548f8e8e", "parents": [ "bcfc082150c6b1e9443c1277bca8be80094150b5" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:27 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:10:17 2011 -0400" }, "message": "perf-probe: Move dwarf library routines to dwarf-aux.{c, h}\n\nMove dwarf library related routines to dwarf-aux.{c,h}.\nThis includes several minor changes.\n- Add simple documents for each API.\n- Rename die_find_real_subprogram() to die_find_realfunc()\n- Rename line_walk_handler_t to line_walk_callback_t.\n- Minor cleanups.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072727.6528.57647.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "bcfc082150c6b1e9443c1277bca8be80094150b5", "tree": "fcb522f8c9bd2ab926065cfb9799defbddb4353b", "parents": [ "bad03ae476214d9d66bb96be02b630385936f788" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:21 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:04:47 2011 -0400" }, "message": "perf probe: Remove redundant dwarf functions\n\nSince there are dwarf_bitsize, dwarf_bitoffset and dwarf_bytesize\ndefined in libdw, we don\u0027t need die_get_bit_size, die_get_bit_offset\nand die_get_byte_size anymore.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072721.6528.2747.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "bad03ae476214d9d66bb96be02b630385936f788", "tree": "91f1273f08104fb457b436141de431f1fc6e5b7c", "parents": [ "baad2d3e69ba154dae340904a47ae12414f1894f" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:15 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 16:00:47 2011 -0400" }, "message": "perf probe: Move strtailcmp to string.c\n\nSince strtailcmp() is enough generic, it should be defined in string.c.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/20110627072715.6528.10677.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "baad2d3e69ba154dae340904a47ae12414f1894f", "tree": "c755b2695300cd8f99ef9d2d570cf85cc1ea2661", "parents": [ "7f6878a3d707b947603e09d95df0c3a98987e3a4" ], "author": { "name": "Masami Hiramatsu", "email": "masami.hiramatsu.pt@hitachi.com", "time": "Mon Jun 27 16:27:09 2011 +0900" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Jul 15 15:55:57 2011 -0400" }, "message": "perf probe: Rename DIE_FIND_CB_FOUND to DIE_FIND_CB_END\n\nSince die_find/walk* callbacks use DIE_FIND_CB_FOUND for\nboth of failed and found cases, it should be \"END\"\ninstead \"FOUND\" for avoiding confusion.\n\nSigned-off-by: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e\nReported-by: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLink: http://lkml.kernel.org/r/20110627072709.6528.45706.stgit@fedora15\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "259032bfe379281bf7cba512b7705bdb4ce41db5", "tree": "56c656f3ecb9779e70f6c9a3ad1db68a7a38a6ca", "parents": [ "6331c28c962561aee59e5a493b7556a4bb585957" ], "author": { "name": "Sonny Rao", "email": "sonnyrao@chromium.org", "time": "Thu Jul 14 13:34:43 2011 +1000" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 14 15:53:01 2011 -0400" }, "message": "perf: Robustify proc and debugfs file recording\n\nWhile attempting to create a timechart of boot up I found perf didn\u0027t\ntolerate modules being loaded/unloaded. This patch fixes this by\nreading the file once and then writing the size read at the correct\npoint in the file. It also simplifies the code somewhat.\n\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nSigned-off-by: Sonny Rao \u003csonnyrao@chromium.org\u003e\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nLink: http://lkml.kernel.org/r/10011.1310614483@neuling.org\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5d67be97f8903d05ce53597fb5f3bc25a45e8026", "tree": "5ce8c2407d50570d7fee79b9c7f24e8eb89384b4", "parents": [ "9f8b6a6cf0ee78de87ebe1e87f54bec1c1741ef7" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Mon Jul 04 21:57:50 2011 +1000" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 05 10:44:44 2011 +0200" }, "message": "perf report/annotate/script: Add option to specify a CPU range\n\nAdd an option to perf report/annotate/script to specify which\nCPUs to operate on. This enables us to take a single system wide\nprofile and analyse each CPU (or group of CPUs) in isolation.\n\nThis was useful when profiling a multiprocess workload where the\nbottleneck was on one CPU but this was hidden in the overall\nprofile. Per process and per thread breakdowns didn\u0027t help\nbecause multiple processes were running on each CPU and no\nsingle process consumed an entire CPU.\n\nThe patch converts the list of CPUs returned by cpu_map__new\ninto a bitmap for fast lookup. I wanted to use -C to be\nconsistent with perf top/record/stat, but unfortunately perf\nreport already uses -C \u003ccomms\u003e.\n\n v2: Incorporate suggestions from David Ahern:\n\t- Added -c to perf script\n\t- Check that SAMPLE_CPU is set when -c is used\n\t- Update documentation\n\n v3: Create perf_session__cpu_bitmap()\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nAcked-by: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLink: http://lkml.kernel.org/r/20110704215750.11647eb9@kryten\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3ae9a34d747f9abf2bcc85dc0e77b951513ccdf2", "tree": "592baba4f60e156f9b0d596ade75e282ea21f1ab", "parents": [ "343a031f3c4a7a663192cf56368bb5a6c56870c0" ], "author": { "name": "Zhengyu He", "email": "zhengyuh@google.com", "time": "Thu Jun 23 13:45:42 2011 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 01 12:52:40 2011 +0200" }, "message": "perf stat: Add noise output for csv mode\n\nPreviously, when you want perf-stat to output the statistics in\ncsv mode, no information of the noise will be printed out.\n\nFor example right now we output this --repeat information:\n\n ./perf stat -r3 -x, sleep 1\n 1.164789,task-clock\n 8,context-switches\n 0,CPU-migrations\n 219,page-faults\n 3337800,cycles\n\nWith this patch, the output will be appended with an additional\nentry for the noise value:\n\n ./perf stat -r3 -x, sleep 1\n 1.164789,task-clock,3.75%\n 8,context-switches,75.00%\n 0,CPU-migrations,100.00%\n 219,page-faults,0.00%\n 3337800,cycles,3.36%\n\nSigned-off-by: Zhengyu He \u003czhengyuh@google.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Venkatesh Pallipadi \u003cvenki@google.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLink: http://lkml.kernel.org/r/1308861942-4945-1-git-send-email-zhengyuh@google.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "343a031f3c4a7a663192cf56368bb5a6c56870c0", "tree": "ee6c7fddf5de92f64f3759694cc6a4b7c28fa80a", "parents": [ "26ca5c11fb45ae2b2ac7e3574b8db6b3a3c7d350", "cb1955b86c86782ff20037da42ef030057501c34" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 01 11:51:58 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 01 11:51:58 2011 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core\n" }, { "commit": "10e6962765f8213941eaa1cbb9de425ff0689e2e", "tree": "c277e4ac5b2b7156152454578c39e90da5127dd8", "parents": [ "af07ce3e77d3b24ab1d71fcc5833d41800f23b2b", "b0af8dfdd67699e25083478c63eedef2e72ebd85" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 01 10:28:42 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 01 10:28:46 2011 +0200" }, "message": "Merge commit \u0027v3.0-rc5\u0027 into perf/core\n\nMerge reason: Pick up the latest fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cb1955b86c86782ff20037da42ef030057501c34", "tree": "4d4ed06f8ec32ddc4a47259d82fa470673cdf510", "parents": [ "fd8ea21276adefc7f0133bd42fcf3b2faf0b15f8" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jun 29 23:52:52 2011 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:26:49 2011 +0200" }, "message": "perf tools: Only display parent field if explictly sorted\n\nWe don\u0027t need to display the parent field if the parent\nsorting machinery is only used for parent filtering\n(as in \"-p foo\").\n\nHowever if parent filtering is used in combination with\nexplicit parent sorting ( -s parent), we want to\ndisplay it.\n\nResult with:\n\n perf report -p kernel_thread -s parent\n\nBefore:\n\n # Overhead Parent symbol\n # ........ .............\n #\n 0.07%\n |\n --- ioread8\n ata_sff_check_status\n ata_sff_tf_load\n ata_sff_qc_issue\n ata_bmdma_qc_issue\n ata_qc_issue\n ata_scsi_translate\n ata_scsi_queuecmd\n scsi_dispatch_cmd\n scsi_request_fn\n __blk_run_queue\n __make_request\n generic_make_request\n submit_bio\n submit_bh\n journal_submit_commit_record\n jbd2_journal_commit_transaction\n kjournald2\n kthread\n kernel_thread_helpe\n\nAfter:\n\n # Overhead Parent symbol\n # ........ .............\n #\n 0.07% kernel_thread_helper\n |\n --- ioread8\n ata_sff_check_status\n ata_sff_tf_load\n ata_sff_qc_issue\n ata_bmdma_qc_issue\n ata_qc_issue\n ata_scsi_translate\n ata_scsi_queuecmd\n scsi_dispatch_cmd\n scsi_request_fn\n __blk_run_queue\n __make_request\n generic_make_request\n submit_bio\n submit_bh\n journal_submit_commit_record\n jbd2_journal_commit_transaction\n kjournald2\n kthread\n kernel_thread_helper\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\n" }, { "commit": "fd8ea21276adefc7f0133bd42fcf3b2faf0b15f8", "tree": "7d4025ed1c68162f118bc29005ac76f0e9ea8dd8", "parents": [ "e84d21227c6865fe1f3d0c79d1539b6877f54c84" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jun 29 23:08:14 2011 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:26:41 2011 +0200" }, "message": "perf tools: Allow sort dimensions to be registered more than once\n\nSo that the parent sort dimension can be registered twice: once\nif we add it as an explicit sort dimension (-s parent) and twice\nif we request a parent filter (-p foo).\n\nWe\u0027ll have only one parent sort dimension in the end but this\nallows to override the default parent filter with we gave in \"-p\"\noption. The goal of this is to prepare to allow the use of\n\"-s parent\" and \"-p foo\" at the same time, ie: sort by filtered\nparent.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\n" }, { "commit": "e84d21227c6865fe1f3d0c79d1539b6877f54c84", "tree": "51890e149dc9946b8300c38bfb1ebc1a643bfd85", "parents": [ "2fd701bc782fad8792059dd586e1f00b64f6a52e" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jun 29 22:23:03 2011 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:26:33 2011 +0200" }, "message": "perf tools: Don\u0027t display ignored entries on stdio ui\n\nAs for newt ui, don\u0027t display entries that have been marked\nas ignored.\n\nThe practical current effect of this is to make parent\nfiltering really working. Before, entries that were ignored\nwere given a null parent but were still displayed. This\nresulted in some weird effects:\n\n # Overhead Command Shared Object Symbol\n # ........ ........... ................. ............\n #\n^A\n |\n --- __lock_acquire\n |\n |--95.97%-- lock_acquire\n | |\n | |--30.75%-- _raw_spin_lock\n\nDiscard these from the stdio display.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\n" }, { "commit": "2fd701bc782fad8792059dd586e1f00b64f6a52e", "tree": "5ed938913571fd1052814f490333db26aed5e421", "parents": [ "872a878fb1ee53e21c90040de2c01b3fc53b5942" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jun 29 03:25:14 2011 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:26:19 2011 +0200" }, "message": "perf tools: Remove sort print helpers declarations\n\nThese are probably some old leftovers.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\n" }, { "commit": "872a878fb1ee53e21c90040de2c01b3fc53b5942", "tree": "1ee4c10d94e9946a6c8b35a5515fe4feab976a0d", "parents": [ "d797fdc5c5c245fbb05f553e68cb95d962fbdd01" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jun 29 03:14:52 2011 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:25:12 2011 +0200" }, "message": "perf tools: Make sort operations static\n\nThese don\u0027t need to be globally visible.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nCc: Sam Liao \u003cphyomh@gmail.com\u003e\n" }, { "commit": "d797fdc5c5c245fbb05f553e68cb95d962fbdd01", "tree": "aa28d98f61df71a2fba55e2b4b526c77aec8de0a", "parents": [ "af07ce3e77d3b24ab1d71fcc5833d41800f23b2b" ], "author": { "name": "Sam Liao", "email": "phyomh@gmail.com", "time": "Tue Jun 07 23:49:46 2011 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jun 30 00:24:30 2011 +0200" }, "message": "perf tools: Add inverted call graph report support.\n\nAdd \"caller/callee\" option to support inverted butterfly report,\nin the inverted report (with caller option), the call graph start\nfrom the callee\u0027s ancestor. Users can use such view to catch system\u0027s\nperformance bottleneck from a sysprof like view. Using this option\nwith specified sort order like pid gives us high level view of call\ngraph statistics.\n\nAlso add \"-G\" alias for inverted call graph.\n\nSigned-off-by: Sam Liao \u003cphyomh@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "8816ead9d8e7c2745788e0684797e1912b504f33", "tree": "2a619a821024d31be2ce6ff422f287792379fe5b", "parents": [ "357ed6b1a110048ff8106f99092d6c4a7aadb45a", "203db2952bc87f5d610c9ad53a7d02b85897721f", "d8ad7d1123a960cc9f276bd499f9325c6f5e1bd1", "b5199515c25cca622495eb9c6a8a1d275e775088", "c1f5c54b57341e872a9d375dccef7257f86033ef" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jun 19 09:00:18 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jun 19 09:00:18 2011 -0700" }, "message": "Merge branches \u0027perf-urgent-for-linus\u0027, \u0027sched-urgent-for-linus\u0027, \u0027timers-urgent-for-linus\u0027 and \u0027x86-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027perf-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n tools/perf: Fix static build of perf tool\n tracing: Fix regression in printk_formats file\n\n* \u0027sched-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n generic-ipi: Fix kexec boot crash by initializing call_single_queue before enabling interrupts\n\n* \u0027timers-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n clocksource: Make watchdog robust vs. interruption\n timerfd: Fix wakeup of processes when timer is cancelled on clock change\n\n* \u0027x86-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86, MAINTAINERS: Add x86 MCE people\n x86, efi: Do not reserve boot services regions within reserved areas\n" }, { "commit": "357ed6b1a110048ff8106f99092d6c4a7aadb45a", "tree": "ff4eb7e809e547bc3c0680dfd51793a8f57b2063", "parents": [ "de505e709ffb09a7382ca8e0d8c7dbb171ba5830", "f8b7fc6b514f34a51875dd48dff70d4d17a54f38" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jun 19 08:56:56 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jun 19 08:56:56 2011 -0700" }, "message": "Merge branch \u0027core-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n rcu: Move RCU_BOOST #ifdefs to header file\n rcu: use softirq instead of kthreads except when RCU_BOOST\u003dy\n rcu: Use softirq to address performance regression\n rcu: Simplify curing of load woes\n" }, { "commit": "7cc2ed05891f424c2e323bc1a368ddb5c78b90f2", "tree": "db628f2dcbb51c0fe9ce15da5897c4ea1404be9f", "parents": [ "8dac6bee32425dd5145b40fa2307648cb7fb4d4a", "569658dddf276ceb0780776e7f5d61d9f8d8cb88" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 16 10:26:58 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 16 10:26:58 2011 -0700" }, "message": "Merge branch \u0027rc-fixes\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6\n\n* \u0027rc-fixes\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6:\n kbuild: Call depmod.sh via shell\n perf: clear out make flags when calling kernel make kernelver\n" }, { "commit": "b4f9f2b64aa189c5584f266f4f0343af7a705441", "tree": "f410718bb93590ff61682b566c10f70d5883bbcd", "parents": [ "76369139ceb955deefc509e6e12ce9d6ce50ccab", "2c53b436a30867eb6b47dd7bab23ba638d1fb0d2" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 16 13:23:15 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 16 13:23:22 2011 +0200" }, "message": "Merge commit \u0027v3.0-rc3\u0027 into perf/core\n\nMerge reason: add the latest fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "203db2952bc87f5d610c9ad53a7d02b85897721f", "tree": "215302011c4fa0669e1856466dc077bf9245f0fa", "parents": [ "afbee42706090fa59dac299c9607e4fd4361ec82" ], "author": { "name": "Mathias Krause", "email": "minipli@googlemail.com", "time": "Wed Jun 15 23:03:38 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 16 10:17:39 2011 +0200" }, "message": "tools/perf: Fix static build of perf tool\n\nTo build a statically linked version of the perf tool all needed\nlibraries must be added in the correct order to get the symbols\nresolved. Currently this is broken when, e.g. python or newt\nsupport is enabled -- libpython needs libpthread which is an\nunconditional link dependency of the perf tool; libslang needs\nlibm, another unconditional dependency. To solve the problem in\nthe long run without the need to keep track of transitive\nlibrary dependencies, simply make the linker look at the EXTLIBS\nmultiple times until it has all symbols resolved.\n\nSigned-off-by: Mathias Krause \u003cminipli@googlemail.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nLink: http://lkml.kernel.org/r/1308171818-20370-1-git-send-email-minipli@googlemail.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "37aa9a2eb4d9b1a4aec1fd18bb2bb6bca029de27", "tree": "548a93ad0b76c121bf74471b67f638fda3bbc3c0", "parents": [ "5d61b9fd19d9f3cf653dbba615876e7792eea5ea" ], "author": { "name": "Andy Whitcroft", "email": "apw@canonical.com", "time": "Wed Jun 15 14:35:00 2011 +0100" }, "committer": { "name": "Michal Marek", "email": "mmarek@suse.cz", "time": "Wed Jun 15 22:12:55 2011 +0200" }, "message": "perf: clear out make flags when calling kernel make kernelver\n\nWhen generating the perf version from the kernel version using \u0027make\nkernelver\u0027 it is necessary to clear out any MAKEFLAGS otherwise they may\ntrigger additional output which pollute the contents.\n\nSigned-off-by: Andy Whitcroft \u003capw@canonical.com\u003e\nSigned-off-by: Michal Marek \u003cmmarek@suse.cz\u003e\n" }, { "commit": "09223371deac67d08ca0b70bd18787920284c967", "tree": "0ad0354a93ac209c8cfd2b79d03d0462aa3c5c58", "parents": [ "9a432736904d386cda28b987b38ba14dae960ecc" ], "author": { "name": "Shaohua Li", "email": "shaohua.li@intel.com", "time": "Tue Jun 14 13:26:25 2011 +0800" }, "committer": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.com", "time": "Tue Jun 14 15:25:39 2011 -0700" }, "message": "rcu: Use softirq to address performance regression\n\nCommit a26ac2455ffcf3(rcu: move TREE_RCU from softirq to kthread)\nintroduced performance regression. In an AIM7 test, this commit degraded\nperformance by about 40%.\n\nThe commit runs rcu callbacks in a kthread instead of softirq. We observed\nhigh rate of context switch which is caused by this. Out test system has\n64 CPUs and HZ is 1000, so we saw more than 64k context switch per second\nwhich is caused by RCU\u0027s per-CPU kthread. A trace showed that most of\nthe time the RCU per-CPU kthread doesn\u0027t actually handle any callbacks,\nbut instead just does a very small amount of work handling grace periods.\nThis means that RCU\u0027s per-CPU kthreads are making the scheduler do quite\na bit of work in order to allow a very small amount of RCU-related\nprocessing to be done.\n\nAlex Shi\u0027s analysis determined that this slowdown is due to lock\ncontention within the scheduler. Unfortunately, as Peter Zijlstra points\nout, the scheduler\u0027s real-time semantics require global action, which\nmeans that this contention is inherent in real-time scheduling. (Yes,\nperhaps someone will come up with a workaround -- otherwise, -rt is not\ngoing to do well on large SMP systems -- but this patch will work around\nthis issue in the meantime. And \"the meantime\" might well be forever.)\n\nThis patch therefore re-introduces softirq processing to RCU, but only\nfor core RCU work. RCU callbacks are still executed in kthread context,\nso that only a small amount of RCU work runs in softirq context in the\ncommon case. This should minimize ksoftirqd execution, allowing us to\nskip boosting of ksoftirqd for CONFIG_RCU_BOOST\u003dy kernels.\n\nSigned-off-by: Shaohua Li \u003cshaohua.li@intel.com\u003e\nTested-by: \"Alex,Shi\" \u003calex.shi@intel.com\u003e\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\n" }, { "commit": "6aecceccf5aa626b0af203e54ca62cbf308c53d8", "tree": "5d4889d531c1a92b38a36ea7a8d4f4e40252082d", "parents": [ "dfb863a714b81848504d3b73ca0ecae90b91cbc0", "5d61b9fd19d9f3cf653dbba615876e7792eea5ea" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 09 16:27:42 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 09 16:27:42 2011 -0700" }, "message": "Merge branch \u0027rc-fixes\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6\n\n* \u0027rc-fixes\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6:\n perf: Use make kernelversion instead of parsing the Makefile\n kbuild: Hack for depmod not handling X.Y versions\n kbuild: Move depmod call to a separate script\n kbuild: Fix \u003clinux/version.h\u003e for empty SUBLEVEL or PATCHLEVEL\n kbuild: Fix KERNELVERSION for empty SUBLEVEL or PATCHLEVEL\n kbuild: silence Nothing to be done for \u0027all\u0027 message\n" }, { "commit": "5d61b9fd19d9f3cf653dbba615876e7792eea5ea", "tree": "8feaee398ec0bf43f94c759562e4d10f1c5eeebb", "parents": [ "bfe5424a8b31624e7a476f959d552999f931e7c7" ], "author": { "name": "Michal Marek", "email": "mmarek@suse.cz", "time": "Mon May 30 14:12:09 2011 +0200" }, "committer": { "name": "Michal Marek", "email": "mmarek@suse.cz", "time": "Thu Jun 09 23:05:54 2011 +0200" }, "message": "perf: Use make kernelversion instead of parsing the Makefile\n\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\nSigned-off-by: Michal Marek \u003cmmarek@suse.cz\u003e\n" }, { "commit": "b273fa9716aa1564bee88ceee62f9042981cdc81", "tree": "06535a98fdf11d5a680d22a91b3013b412ca56f1", "parents": [ "56722381b8506733852c44dacf6d7bc5f90aedaf" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Mar 31 18:27:42 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jun 03 10:09:22 2011 -0300" }, "message": "perf python: Fix argument name list of read_on_cpu()\n\nMandatory arguments need to be present in the argument name list, as\nwell as optional arguments, otherwise python barfs:\n\n\t# ./python/twatch.py\n\tTraceback (most recent call last):\n\t File \"./python/twatch.py\", line 41, in \u003cmodule\u003e\n\t main()\n\t File \"./python/twatch.py\", line 32, in main\n\t event \u003d evlist.read_on_cpu(cpu)\n\tRuntimeError: more argument specifiers than keyword list entries\n\nHence, add cpu to the name list.\n\nCc: David Ahern \u003cdaahern@cisco.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLink: http://lkml.kernel.org/r/1301588863-20210-1-git-send-email-fweisbec@gmail.com\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "56722381b8506733852c44dacf6d7bc5f90aedaf", "tree": "867f605305c4e4fa94cea3eacaeb7e1b9ba62bdc", "parents": [ "9c850d6c4b95bb07fb066eb7f43dd4e3b4842b85" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 11:04:54 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jun 03 10:07:52 2011 -0300" }, "message": "perf evlist: Don\u0027t die if sample_{id_all|type} is invalid\n\nFixes two more cases where the python binding would not load:\n\n. Not finding die(), which it shouldn\u0027t anyway, not good to just stop the\n world because some particular perf.data file is invalid, just propagate\n the error to the caller.\n\n. Not finding perf_sample_size: fix it by moving it from event.c to evsel,\n where it belongs, as most cases are moving to operate on an evsel object.o\n\nOne of the fixed problems:\n\n[root@emilia ~]# python\n\u003e\u003e\u003e import perf\nTraceback (most recent call last):\n File \"\u003cstdin\u003e\", line 1, in \u003cmodule\u003e\nImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: perf_sample_size\n\u003e\u003e\u003e\n[root@emilia ~]#\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-1hkj7b2cvgbfnoizsekjb6c9@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "9c850d6c4b95bb07fb066eb7f43dd4e3b4842b85", "tree": "5f6429b7558b215593f274b061c2979196df877a", "parents": [ "d21cc9f67d689effbfd24bac878bc2c057de8c46" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:55:10 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jun 03 10:07:01 2011 -0300" }, "message": "perf python: Use exception to propagate errors\n\nWe were using pr_debug to tell the user about not being able to parse a sample\nwhere we should really use the python way of reporting errors: exceptions.\n\nFixes this problem:\n\n[root@emilia ~]# python\n\u003e\u003e\u003e import perf\nTraceback (most recent call last):\n File \"\u003cstdin\u003e\", line 1, in \u003cmodule\u003e\nImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: eprintf\n\u003e\u003e\u003e\n[root@emilia ~]\n\nAs we want to keep the objects linked in the python binding (and in the future\nin a shared library) minimal.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-m9dba9kaluas0kq8r58z191c@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "d21cc9f67d689effbfd24bac878bc2c057de8c46", "tree": "24b0f76ac764ca708923045dbe617875a9a09ea2", "parents": [ "1fa7b6a29c61358cc2ca6f64cef4aa0e1a7ca74c" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:39:43 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jun 03 10:05:23 2011 -0300" }, "message": "perf evlist: Remove dependency on debug routines\n\nSo far we avoided having to link debug.o in the python binding, keep it\nthat way by not using ui__warning() in evlist.c.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-4wtew8hd3g7ejnlehtspys2t@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "7cec0922389e080d11ec43dd23aa778e136bd1e1", "tree": "0d772b32f38b4ef16e4256711e947b38baa2c2f9", "parents": [ "610723f24eeb842025178a6722fa9108c4e157b6" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Mon May 30 13:08:23 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:31:01 2011 -0300" }, "message": "perf script: Add printing of sample address\n\nResolve to a function or variable if possible and if the sym option is\nenabled.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1306782503-22002-1-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "610723f24eeb842025178a6722fa9108c4e157b6", "tree": "e184c3b2242ba9b9da065221d4673603dd9d8e86", "parents": [ "787bef174f055343c69a9639e6e05a564980ed4c" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Fri May 27 14:28:44 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:29:14 2011 -0300" }, "message": "perf script: Make printing of dso a separate field option\n\nThe \u0027sym\u0027 option displays both the function name and the DSO it comes\nfrom. Split the display of the dso into a separate option. This allows\ndisplay of the ip address and symbol without the dso, thus shortening\nline lengths - and decluttering the output a bit.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1306528124-25861-3-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "787bef174f055343c69a9639e6e05a564980ed4c", "tree": "d37e4fae03454e74684798bc112ba161786f978a", "parents": [ "2cee77c4505fc581f41b44e18ffc0953b67a414c" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Fri May 27 14:28:43 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:28:34 2011 -0300" }, "message": "perf script: \"sym\" field really means show IP data\n\nCurrently the \"sym\" output field is used to dump instruction pointers\nand callchain stack. Sample addresses can also be converted to symbols,\nso the meaning of \"sym\" needs to be fixed. This patch adds an \"ip\"\noption and if it is selected the user can also opt to dump symbols for\nthem. If the user opts to dump IP without syms only the address is\nshown.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1306528124-25861-2-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "2cee77c4505fc581f41b44e18ffc0953b67a414c", "tree": "12777ada659829082c27a1da31a295387355fd4b", "parents": [ "64348153c63b8c1f99f19f14a9c3cbd5df70c9d3" ], "author": { "name": "David Ahern", "email": "dsahern@gmail.com", "time": "Mon May 30 08:55:59 2011 -0600" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:26:15 2011 -0300" }, "message": "perf stat: clarify unsupported events from uncounted events\n\nperf stat continues running even if the event list contains counters\nthat are not supported. The resulting output then contains \u003cnot counted\u003e\nfor those events which gets confusing as to which events are supported,\nbut not counted and which are not supported.\n\nBefore:\n\nperf stat -ddd -- sleep 1\n\n Performance counter stats for \u0027sleep 1\u0027:\n\n 0.571283 task-clock # 0.001 CPUs utilized\n 1 context-switches # 0.002 M/sec\n 0 CPU-migrations # 0.000 M/sec\n 157 page-faults # 0.275 M/sec\n 1,037,707 cycles # 1.816 GHz\n \u003cnot counted\u003e stalled-cycles-frontend\n \u003cnot counted\u003e stalled-cycles-backend\n 654,499 instructions # 0.63 insns per cycle\n 136,129 branches # 238.286 M/sec\n \u003cnot counted\u003e branch-misses\n \u003cnot counted\u003e L1-dcache-loads\n \u003cnot counted\u003e L1-dcache-load-misses\n \u003cnot counted\u003e LLC-loads\n \u003cnot counted\u003e LLC-load-misses\n \u003cnot counted\u003e L1-icache-loads\n \u003cnot counted\u003e L1-icache-load-misses\n \u003cnot counted\u003e dTLB-loads\n \u003cnot counted\u003e dTLB-load-misses\n \u003cnot counted\u003e iTLB-loads\n \u003cnot counted\u003e iTLB-load-misses\n \u003cnot counted\u003e L1-dcache-prefetches\n \u003cnot counted\u003e L1-dcache-prefetch-misses\n\n 1.001004836 seconds time elapsed\n\nAfter:\n\nperf stat -ddd -- sleep 1\n\n Performance counter stats for \u0027sleep 1\u0027:\n\n 1.350326 task-clock # 0.001 CPUs utilized\n 2 context-switches # 0.001 M/sec\n 0 CPU-migrations # 0.000 M/sec\n 157 page-faults # 0.116 M/sec\n 11,986 cycles # 0.009 GHz\n \u003cnot supported\u003e stalled-cycles-frontend\n \u003cnot supported\u003e stalled-cycles-backend\n 496,986 instructions # 41.46 insns per cycle\n 138,065 branches # 102.246 M/sec\n 7,245 branch-misses # 5.25% of all branches\n \u003cnot counted\u003e L1-dcache-loads\n \u003cnot counted\u003e L1-dcache-load-misses\n \u003cnot counted\u003e LLC-loads\n \u003cnot counted\u003e LLC-load-misses\n \u003cnot counted\u003e L1-icache-loads\n \u003cnot counted\u003e L1-icache-load-misses\n \u003cnot counted\u003e dTLB-loads\n \u003cnot counted\u003e dTLB-load-misses\n \u003cnot counted\u003e iTLB-loads\n \u003cnot counted\u003e iTLB-load-misses\n \u003cnot counted\u003e L1-dcache-prefetches\n \u003cnot supported\u003e L1-dcache-prefetch-misses\n\n 1.002397333 seconds time elapsed\n\nv1-\u003ev2:\nchanged supported type from int to bool\n\nv2-\u003ev3\nfixed vertical alignment of new struct element\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLink: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com\nSigned-off-by: David Ahern \u003cdsahern@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "64348153c63b8c1f99f19f14a9c3cbd5df70c9d3", "tree": "c1bee41565096fb2adce58125a9c936a26fa6fe4", "parents": [ "e95cc02880947e9f77540b03e166470e8ac14cbc" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Mar 31 18:27:43 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:21:26 2011 -0300" }, "message": "perf python: Cleanup useless double NULL termination in method arg names\n\nThe list of methods argument names only needs to be NULL terminated\nonce. Remove the second ones.\n\nCc: David Ahern \u003cdaahern@cisco.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLink: http://lkml.kernel.org/r/1301588863-20210-2-git-send-email-fweisbec@gmail.com\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "e95cc02880947e9f77540b03e166470e8ac14cbc", "tree": "500dca257ad17c606e96bd28d3f0d2aaedff9996", "parents": [ "c2a70653af45c9cbb0cab900e8931b062e57b1ae" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Mar 31 18:27:42 2011 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 13:21:07 2011 -0300" }, "message": "perf python: Fix argument name list of read_on_cpu()\n\nMandatory arguments need to be present in the argument name list, as\nwell as optional arguments, otherwise python barfs:\n\n\t# ./python/twatch.py\n\tTraceback (most recent call last):\n\t File \"./python/twatch.py\", line 41, in \u003cmodule\u003e\n\t main()\n\t File \"./python/twatch.py\", line 32, in main\n\t event \u003d evlist.read_on_cpu(cpu)\n\tRuntimeError: more argument specifiers than keyword list entries\n\nHence, add cpu to the name list.\n\nCc: David Ahern \u003cdaahern@cisco.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLink: http://lkml.kernel.org/r/1301588863-20210-1-git-send-email-fweisbec@gmail.com\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c2a70653af45c9cbb0cab900e8931b062e57b1ae", "tree": "e7b1b10cc71c5cccd3d3b7d20cb8001ec313fbff", "parents": [ "5c6970af2f4be4e04b06fe78214f6809777a8354" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 11:04:54 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 11:04:54 2011 -0300" }, "message": "perf evlist: Don\u0027t die if sample_{id_all|type} is invalid\n\nFixes two more cases where the python binding would not load:\n\n. Not finding die(), which it shouldn\u0027t anyway, not good to just stop the\n world because some particular perf.data file is invalid, just propagate\n the error to the caller.\n\n. Not finding perf_sample_size: fix it by moving it from event.c to evsel,\n where it belongs, as most cases are moving to operate on an evsel object.o\n\nOne of the fixed problems:\n\n[root@emilia ~]# python\n\u003e\u003e\u003e import perf\nTraceback (most recent call last):\n File \"\u003cstdin\u003e\", line 1, in \u003cmodule\u003e\nImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: perf_sample_size\n\u003e\u003e\u003e\n[root@emilia ~]#\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-1hkj7b2cvgbfnoizsekjb6c9@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "5c6970af2f4be4e04b06fe78214f6809777a8354", "tree": "ec39ed480a4d8a15fe261d6a37edf894fb2fa936", "parents": [ "bccdaba044a445eb2c391295587aa47977994777" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:55:10 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:55:10 2011 -0300" }, "message": "perf python: Use exception to propagate errors\n\nWe were using pr_debug to tell the user about not being able to parse a sample\nwhere we should really use the python way of reporting errors: exceptions.\n\nFixes this problem:\n\n[root@emilia ~]# python\n\u003e\u003e\u003e import perf\nTraceback (most recent call last):\n File \"\u003cstdin\u003e\", line 1, in \u003cmodule\u003e\nImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: eprintf\n\u003e\u003e\u003e\n[root@emilia ~]\n\nAs we want to keep the objects linked in the python binding (and in the future\nin a shared library) minimal.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-m9dba9kaluas0kq8r58z191c@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "bccdaba044a445eb2c391295587aa47977994777", "tree": "d06ca43b4150fbc7bbd6e3116d0a0b44ff64de1c", "parents": [ "64ce312618ef0e11d88def80effcefd1b59fdb1e" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:39:43 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 02 10:41:41 2011 -0300" }, "message": "perf evlist: Remove dependency on debug routines\n\nSo far we avoided having to link debug.o in the python binding, keep it\nthat way by not using ui__warning() in evlist.c.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLink: http://lkml.kernel.org/n/tip-4wtew8hd3g7ejnlehtspys2t@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "e4a338d05df93ab1ebf291aca1e753064319d301", "tree": "39a843944ca23ef9a927030de7295146e8bd5dc4", "parents": [ "5f6f55809758e106eca72c6e01402c8080a88ee8" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 27 13:42:16 2011 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 27 16:02:29 2011 -0300" }, "message": "perf top: Don\u0027t stop if no kernel symtab is found\n\nWe now just warn the user about the fact and go on providing just\nuserspace samples.\n\nThis fixes a problem when no vmlinux is explicetely passed by the user,\nthus symbol_conf.vmlinux_name is NULL, no suitable vmlinux is found, and\nthen we get:\n\n aldebaran:~\u003e perf top -p 7557\n [kernel.kallsyms] with build id 44d9a989eabbd79e486bc079d6b743d397c204e0\n not found, continuing without symbols\n The (null) file can\u0027t be used\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLink: http://lkml.kernel.org/n/tip-cj2g81hn64wv2bipmqk4fy2m@git.kernel.org\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" } ], "next": "5f6f55809758e106eca72c6e01402c8080a88ee8" }