- 15 Aug, 2012 2 commits
-
-
Arnaldo Carvalho de Melo authored
To replace the longer list_entry constructs for things that are widely used: perf_evlist__{first,last}(evlist) perf_evsel__next(evsel) Acked-by:Jiri Olsa <jolsa@redhat.com> Acked-by:
Namhyung Kim <namhyung@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-ng7azq26wg1jd801qqpcozwp@git.kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Arnaldo Carvalho de Melo authored
Just like was done for parse_events__set_leader. Also we need to have the list_entry set_leader method in evlist.c so that we don't grow another dep in the python binding: # ~acme/git/linux/tools/perf/python/twatch.py Traceback (most recent call last): File "/home/acme/git/linux/tools/perf/python/twatch.py", line 16, in <module> import perf ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: parse_events__set_leader And also remove a pr_debug from evsel.c so that we avoid this one too: # ~acme/git/linux/tools/perf/python/twatch.py Traceback (most recent call last): File "/home/acme/git/linux/tools/perf/python/twatch.py", line 16, in <module> import perf ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: eprintf Acked-by:
-
- 14 Aug, 2012 6 commits
-
-
Jiri Olsa authored
Adding 5 more tests for new event group syntax. Tests are executed within the 'perf test parse' test suite. Reviewed-by:
Namhyung Kim <namhyung@kernel.org> Signed-off-by:
Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-dmhsv8mpoksx2wp97balqiem@git.kernel.orgSigned-off-by:
-
Jiri Olsa authored
This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: -
Jiri Olsa authored
Adding support to update already defined event's attribute with event modifier. This change will allow to use group modifier as an update to the existing event modifiers. Adding 'add' parameter to the parse_events__modifier_event function. Calling it with 'add' = false/true, the event modifier is initialized/updated respectively. Added exclude_GH flag to evsel struct, because we need to remember if one of 'GH' modifiers was used for event. The reason is that the default settings for exclude_guest is 1 and during the group modifier processing we have no other way of knowing if it was set by default or by event modifier. Keeping the current behaviour, that any event/group modifier reset the defaults for exclude_host (0) and exclude_guest (1). Reviewed-by:
-
Jiri Olsa authored
Adding scanner/parser bits to parse event groups. The grammar for group is: groups: groups ',' group | group group: group_name '{' events '}' group_mod group_name: name | empty group_mod: ':' group_mods | empty group_mods: event_mod It's possible to use standard event modifier as a modifier for group. It'll be used as an update to existing event modifiers. It's necessary to use quoting ("'\) when specifying group on command line, since {} characters are interpreted by most of the shells. It is now possible to specify groups in event syntax like: '{cycles,faults}' - anonymous group 'group1{cycles,faults} - group with name 'group1' '{cycles,faults}:k - anonymous group with event modifier 'k' '{cpu-clock,task-clock},{minor-faults,major-faults}' - two anonymous groups The grouping functionality itself is coming shortly. Reviewed-by: -
Arnaldo Carvalho de Melo authored
Changeset 0f6a3015: "perf tools: Support user regs and stack in sample parsing" uses hweight_long in evsel.c, so we need to drag util/hweight.c to the python binding. Ditto for ee8dd3ca: "perf tools: Change strlist to use the new rblist" where we need to add util/rblist.c. Now twatch.py works again: # export PYTHONPATH=~acme/git/build/perf/python/ # ~acme/git/linux/tools/perf/python/twatch.py cpu: 4, pid: 23639, tid: 23639 { type: fork, pid: 30659, ppid: 23639, tid: 30659, ptid: 23639, time: 36287872076780} cpu: 5, pid: 30659, tid: 30659 { type: comm, pid: 30659, tid: 30659, comm: ls } cpu: 5, pid: 30659, tid: 30659 { type: exit, pid: 30659, ppid: 30659, tid: 30659, ptid: 30659, time: 36287873681539} cpu: 4, pid: 23639, tid: 23639 { type: fork, pid: 30660, ppid: 23639, tid: 30660, ptid: 23639, time: 36291720420480} cpu: 5, pid: 30659, tid: 30659 { type: exit, pid: 30659, ppid: 30659, tid: 30659, ptid: 30659, time: 36287873685714} cpu: 5, pid: 30660, tid: 30660 { type: comm, pid: 30660, tid: 30660, comm: git } ^C KeyboardInterrupt Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-gmq82zp5blin9aml9g5tzokr@git.kernel.orgSigned-off-by:
-
Namhyung Kim authored
If 'perf script --gen-script' was called with a perf.data which contains no tracepoint event, it'd segfault due to NULL pevent pointer. Fix it. Signed-off-by:
-
- 13 Aug, 2012 17 commits
-
-
Andi Kleen authored
Add a description of the JIT interface in the perf symbol resolution code. I reverse engineered the format from the source. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Acked-by:
Pekka Enberg <penberg@cs.helsinki.fi> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Link: http://lkml.kernel.org/r/1344526260-18721-1-git-send-email-andi@firstfloor.orgSigned-off-by:
-
Cody P Schafer authored
We keep both a 'runtime' elf image as well as a 'debug' elf image around and generate symbols by looking at both of these. This eliminates the need for the want_symtab/goto restart mechanism combined with iterating over and reopening the elf images a second time. Also give dso__synthsize_plt_symbols() the runtime image (which has dynsyms) instead of the symbol image (which may only have a symtab and no dynsyms). Previously if a debug image was found all runtime images were ignored. This fixes 2 issues: - Symbol resolution to failure on PowerPC systems with debug symbols installed, as the debug images lack a '.opd' section which contains function descriptors. - On all archs, plt synthesis failed when a debug image was loaded and that debug image lacks a dynsym section while a runtime image has a dynsym section. Assumptions: - If a .opd section exists, it is contained in the highest priority image with a dynsym section. - This generally implies that the debug image lacks a dynsym section (ie: it is marked as NO_BITS). Signed-off-by:
Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Hansen <dave@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Hellsley <matthltc@us.ibm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1344637382-22789-17-git-send-email-cody@linux.vnet.ibm.comSigned-off-by:
-
Cody P Schafer authored
To properly handle platforms with an opd section, both a runtime image (which contains the opd section but possibly lacks symbols) and a symbol image (which probably lacks an opd section but has symbols). The next patch ("perf symbol: use both runtime and debug images") adjusts the callsite in dso__load() to take advantage of being able to pass both runtime & debug images. Assumptions made here: - The opd section, if it exists in the runtime image, has headers in both the runtime image and the debug/syms image. - The index of the opd section (again, only if it exists in the runtime image) is the same in both the runtime and debug/symbols image. Both of these are true on RHEL, but it is unclear how accurate they are in general (on platforms with function descriptors in opd sections). Signed-off-by: -
Cody P Schafer authored
Only one callsite of dso__load_sym() uses the want_symtab functionality, so place the logic at the callsite instead of within dso__load_sym(). This sets us up for removal of want_symtab completely once we keep multiple elf handles (within symsrc's) around. Setup for the later patch "perf symbols: Use both runtime and debug images" Signed-off-by:
-
Cody P Schafer authored
Previously dso__synthesize_plt_symbols() was reopening the elf file to obtain dynsyms from it. Rather than reopen the file, use the already opened reference within the symsrc to access it. Setup for the later patch "perf symbols: Use both runtime and debug images" Signed-off-by:
-
Cody P Schafer authored
In certain cases, dso__load requires dso->symbol_type to be set prior to calling it. With the introduction of symsrc*, the symtab_type is now stored in a symsrc which is then passed to dso__load_sym(). Change dso__load_sym() to use the symtab_type from them symsrc (setting dso->symtab_type as well). Setup for later patch "perf symbols: Use both runtime and debug images" Signed-off-by:
-
Cody P Schafer authored
Factors opening of certain sections & tracking certain elf info into an external structure. The goal here is to keep multiple elfs (and their looked up sections/indexes) around during the symbol generation process (in dso__load()). We need this to properly resolve symbols on PPC due to the use of function descriptors & the .opd section (ie: symbols which are functions don't point to their actual location, they point to their function descriptor in .opd which contains their actual location. It would be possible to just keep the (Elf *) around, but then we'd end up with duplicate code for looking up the same sections and checking for the existence of an important section wouldn't be as clean (and we need to keep the Elf stuff confined to symtab-elf.c). Utilized by the later patch "perf symbols: Use both runtime and debug images" Signed-off-by:
-
Cody P Schafer authored
Previously, symtab_type would have been left at 0, or KALLSYMS, which is not quite accurate. Introduce DSO_BINARY_TYPE__VMLINUX[_GUEST]. Signed-off-by:
-
Cody P Schafer authored
If we call elf_section_by_name() with a truncated elf image (ie: the file header indicates that the section headers are placed past the end of the file), elf_strptr() causes a segfault within libelf. Avoid this by checking that we can access the section string table properly. Should really be fixed in libelf/elfutils. Signed-off-by:
-
Cody P Schafer authored
dso__load_vmlinux() uses the filename passed to it to directly set the dso long_name, which resulted in a use after free due to dso__load_vmlinux_path() treating 0 symbols as a load failure and subsequently freeing the contents of dso->long_name. Change dso__load_vmlinux() so that finding 0 symbols does not cause it to consider itself loaded, and do not set long_name in such a case. Signed-off-by:
-
Cody P Schafer authored
The only site that jumps to out_fixup has (kallsyms_filename == NULL). And all paths that reach 'if (err > 0)' without 'goto out_fixup' have kallsyms_filename != NULL. So skip over both the check & dso__set_long_name(), and remove the check. Signed-off-by:
-
Cody P Schafer authored
kallsyms__parse() takes a callback that is called on every discovered symbol. As /proc/kallsyms does not supply symbol sizes, the callback was simply called with end=start, faking the symbol size to 1. All of the callbacks (there are 2) used in calls to kallsyms__parse() are _only_ used as callbacks for kallsyms__parse(). Given that kallsyms__parse() lacks real information about what end/length should be, don't make up a length in kallsyms__parse(). Instead have the callbacks handle guessing the length. Also relocate a comment regarding symbol creation to the callback which does symbol creation (kallsyms__parse() is not in general used to create symbols). Signed-off-by:
-
Cody P Schafer authored
In kallsyms_parse() when calling process_symbol() (a callback argument to kallsyms_parse()), we pass start as both start & end (ie: start=start, end=start). In map__process_kallsym_symbol(), the length is calculated as 'end - start + 1', making the length 1, not 0. Essentially, start & end define an inclusive range. Signed-off-by:
-
Cody P Schafer authored
dso__set_long_name() is already called by dso__load_vmlinux(), avoid calling it a second time unnecessarily. Signed-off-by:
-
Cody P Schafer authored
If .dynsym exists but .dynstr is empty (NO_BITS or size==0), a segfault occurs. Avoid this by checking that .dynstr is not empty. Signed-off-by:
-
Cody P Schafer authored
map__objdump_2ip was introduced in: ee11b90b perf top: Fix annotate for userspace And it's last user removed in: 36532461 perf top: Ditch private annotation code, share perf annotate's Remove it. Signed-off-by:
-
Cody P Schafer authored
Prelink only adjusts the addresses of non-zero symbols. Do the same when we reverse the adjustments. Signed-off-by:
-
- 11 Aug, 2012 2 commits
-
-
Jiri Olsa authored
This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by:Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.comSigned-off-by:
-
Jiri Olsa authored
This brings the support for DWARF cfi unwinding on perf post processing. Call frame informations are retrieved and then passed to libunwind that requests memory and register content from the applications. Adding unwind object to handle the user stack backtrace based on the user register values and user stack dump. The unwind object access the libunwind via remote interface and provides to it all the necessary data to unwind the stack. The unwind interface provides following function: unwind__get_entries And callback (specified in above function) to retrieve the backtrace entries: typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); Signed-off-by:
-
- 10 Aug, 2012 10 commits
-
-
Jiri Olsa authored
Adding following info to be parsed out of the event sample: - user register set - user stack dump Both are global and specific to all events within the session. This info will be used in the unwind patches coming in shortly. Adding simple output printout (report -D) for both register and stack dumps. Signed-off-by:
-
Jiri Olsa authored
Adding libunwind to be linked with perf if available. It's required for the to get dwarf cfi unwinding support. Also building perf with the dwarf call frame informations by default, so that we can unwind callchains in perf itself. Adding LIBUNWIND_DIR Makefile variable allowing user to specify the directory with libunwind to be linked. This is used for debug purposes. Signed-off-by:
-
Jiri Olsa authored
Adding header files to access unified API for arch registers. util/perf_regs.h - global perf_reg declarations arch/x86/include/perf_regs.h - x86 arch specific Adding perf_reg_name function to obtain register name based on the reg ID value, and PERF_REGS_MASK macro with mask definition of all current arch registers (will be used in unwind patches). Signed-off-by:
-
Jiri Olsa authored
Updating attr_file_abi_sizes array with PERF_ATTR_SIZE_VER2 version, so we have the swap check complete. Signed-off-by:
-
Frederic Weisbecker authored
Introducing following bits to the the perf_event_attr struct: - exclude_callchain_kernel to filter out kernel callchain from the sample dump - exclude_callchain_user to filter out user callchain from the sample dump We need to be able to disable standard user callchain dump when we use the dwarf cfi callchain mode, because frame pointer based user callchains are useless in this mode. Implementing also exclude_callchain_kernel to have complete set of options. Signed-off-by: -
Jiri Olsa authored
Introducing PERF_SAMPLE_STACK_USER sample type bit to trigger the dump of the user level stack on sample. The size of the dump is specified by sample_stack_user value. Being able to dump parts of the user stack, starting from the stack pointer, will be useful to make a post mortem dwarf CFI based stack unwinding. Added HAVE_PERF_USER_STACK_DUMP config option to determine if the architecture provides user stack dump on perf event samples. This needs access to the user stack pointer which is not unified across architectures. Enabling this for x86 architecture. Signed-off-by:
-
Jiri Olsa authored
Introducing perf_output_skip function to be able to skip data within the perf ring buffer. When writing data into perf ring buffer we first reserve needed place in ring buffer and then copy the actual data. There's a possibility we won't be able to fill all the reserved size with data, so we need a way to skip the remaining bytes. This is going to be useful when storing the user stack dump, where we might end up with less data than we originally requested. Signed-off-by:
-
Frederic Weisbecker authored
Adding a generic way to use __output_copy function with specific copy function via DEFINE_PERF_OUTPUT_COPY macro. Using this to add new __output_copy_user function, that provides output copy from user pointers. For x86 the copy_from_user_nmi function is used and __copy_from_user_inatomic for the rest of the architectures. This new function will be used in user stack dump on sample, coming in next patches. Signed-off-by:
-
Jiri Olsa authored
Introducing PERF_SAMPLE_REGS_USER sample type bit to trigger the dump of user level registers on sample. Registers we want to dump are specified by sample_regs_user bitmask. Only user level registers are dumped at the moment. Meaning the register values of the user space context as it was before the user entered the kernel for whatever reason (syscall, irq, exception, or a PMI happening in userspace). The layout of the sample_regs_user bitmap is described in asm/perf_regs.h for archs that support register dump. This is going to be useful to bring Dwarf CFI based stack unwinding on top of samples. Original-patch-by:
Stephane Eranian <eranian@google.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-3-git-send-email-jolsa@redhat.comSigned-off-by:
-
Jiri Olsa authored
This brings a new API to help the selective dump of registers on event sampling, and its implementation for x86 arch. Added HAVE_PERF_REGS config option to determine if the architecture provides perf registers ABI. The information about desired registers will be passed in u64 mask. It's up to the architecture to map the registers into the mask bits. For the x86 arch implementation, both 32 and 64 bit registers bits are defined within single enum to ensure 64 bit system can provide register dump for compat task if needed in the future. Original-patch-by:
-
- 09 Aug, 2012 3 commits
-
-
Namhyung Kim authored
Implement a minimal elf parser for getting build-id. It assumes that required elf.h header is provided by libc header on the system and the parser only looks for PT_NOTE program header to check build-id. Signed-off-by:
-
Namhyung Kim authored
Now we have isolated all ELF-specific stuff, it's possible to build without libelf. The output binary can do most of jobs but lacks (user level) symbol information - kernel symbols are still accessable thanks to the kallsyms. To build perf without libelf (elfutils), give NO_LIBELF=1 to make. For now, only 'perf probe' command is removed since it depends on libelf/libdw heavily. Signed-off-by:
-
Namhyung Kim authored
Factor out the dependency of ELF handling into separate symbol-elf.c file. It is a preparation of building a minimalistic version perf tools which doesn't depend on the elfutils. Signed-off-by:
-
