__ppc__ isn't defined here on Debian powerpc. Grepping through the headers
installed in /usr/include, there are a few references to __ppc__ and
__ppc64__, but I suspect they're for other OSs.
Signed-off-by: Michel Dänzer <michel@daenzer.net>
perf lets you decide to only get events that concerns a single process
and thus make sysprof profile this process instead of the whole system
(it can happen that you don't really care about other processes that are
just then noise).
As a side effect, this allows sysprof to not run as root if you have the
rights on the process you want to profile.
It has issues on various architectures, such as ARM, and there was
never any guarantee that it would actually work. So since we'd need
fallback code anyway, and the main point of it was simplifying the
code, just get rid of it and handle the overflow conditions manually.
Currently, sysprof hardwires the syscall number of
__NR_perf_counter_open. That's all very well, except... like other
syscall numbers, it varies per-arch. With a few exceptions
(e.g. sparc64), it even varies between 32-bit and 64-bit x86 arches.
This patch provides the defines for every number I could see assigned
in git trunk right now, with the exception of some of the ARM ones, where
I couldn't see how to differentiate between the various sorts of ARM to
figure out what the syscall base was. For those, let's wait for libc to
catch up.
The only arch I've been unable even to guess at is the very new S-Core,
which is the only user so far of the generic syscall table in
<include/asm-generic>. This specifies a value of 241, but I can't hook
it up because I can't find an S-Core toolchain anywhere so I don't know
what #define to check for, and googling gives no clues.
Only tested on x86-64 (where it now works) so there may be all sorts of
bugs in the rest of it (well, in the #defines anyway, though most were
checked against GCC trunk).
If hardware counters are not available, fall back to SW regardless of
why the hardware counters aren't available. The error code can be
either ENOTSUPP or ENODEV depending on CPU type, so it's simpler to
just retry in all cases, and only fail if the software fallback
failed.
There is a bug in the kernel where it includes the stack of the IRQ
that generated the event, so that the stack ends up looking like this:
[ip] [irq stack] [real stack].
As a temporary workaround, this patch filters out the irq stack
symbols.
2008-02-17 Soren Sandmann <sandmann@redhat.com>
* collector.c (lookup_symbol): Add commented out code to reject
callback.
* elfparser.c (struct ElfParser): Store the filename if any
(elf_parser_get_sym_address): Subtract the load address, so the
result will be an offset into the text section.
* process.[ch] (process_lookup_symbol): Add an offset out-argument
* binfile.[ch] (bin_symbol_get_address): New function
* TODO: updates
svn path=/trunk/; revision=397
2007-11-16 Soren Sandmann <sandmann@daimi.au.dk>
* TODO: updates
* module/sysprof-module.c (sysprof_poll): Only select readable
when there is at least eight traces available
* collector.c (collect_traces): New function, old on_read()
* collector.c (collector_create_profile): Collect traces here as
well.
svn path=/trunk/; revision=388
2007-10-22 Soren Sandmann <sandmann@daimi.au.dk>
* process.c (look_for_vmlinux): Use an array instead of a
list. Look for vmlinux in the source directory.
* elfparser.c (elf_parser_get_crc32): Only use MADV_DONTNEED if
the data is file-backed.
* TODO: updates.
Various formatting fixes
svn path=/trunk/; revision=385
2007-10-20 Soren Sandmann <sandmann@daimi.au.dk>
* collector.c (on_read): Call callback with an extra boolean
indicating whether the sample read was the first one
* collector.c (add_trace_to_stash): Allocate addresses on the
stack if possible.
* sysprof.c (on_new_sample): Only call update_sensitivity() on the
first sample.
* stackstash.c (stack_stash_add_trace): Move match to front
svn path=/trunk/; revision=373
2007-09-16 Soren Sandmann <sandmann@daimi.au.dk>
* process.c (process_lookup_kernel_symbol): Add support for
looking up kernel symbols from /proc/kallsyms
* sysprof-text.c (dump_data): Print note that the file is being
saved.
* module/sysprof-module.[ch] (timer_notify): Send a copy of the
kernel stack to userspace.
* collector.c: Do kernel symbol lookups.
svn path=/trunk/; revision=372
