Commit Graph

18 Commits

Author SHA1 Message Date
John Polstra
5584f22bb3 Make profiling work for ELF. gprof now autodetects the format of
the executable file, so it will work for both a.out and ELF format
files.  I have split the object format specific code into separate
source files.  It's cleaner than it was before, but it's still
pretty crufty.

Don't cheat on your make world for this update.  A lot of things
have to be rebuilt for it to work, including the compiler and all
of the profiled libraries.
1998-09-07 23:32:00 +00:00
Bruce Evans
37889b394a Changed to the C9x draft spelling of the (unsigned) integral type
suitable for holding object pointers (ptrint_t -> uintptr_t).
Added corresponding signed type (intptr_t).  Changed/added
corresponding non-C9x types for function pointers to match.  Don't
use nonstandard types to implement these types, and don't comment
on them in <machine/types.h>.
1998-07-14 05:09:48 +00:00
Bruce Evans
930a642372 Oops, fptrint_t still needs to be declared in <machine/profile.h> in the
!KERNEL case.  The kludge to get it declared in libc/gmon/mcount.c wasn't
sufficient because fptrint_t is used in <sys/gmon.h>.
1998-07-10 09:26:41 +00:00
Bruce Evans
2e480d34aa Added a kernel-only typedef (ptrint_t) giving an integral type that is
least unsuitable for holding an object pointer.  This should have been
used to fix warnings about casts between pointers and ints on alphas.

Moved corresponding existing general typedef (fptrint_t) for function
pointers from the i386 <machine/profile.h> to a kernel-only typedef
in <machine/types.h>.  Kludged libc/gmon/mcount.c so that it can
still see this typedef.
1998-07-10 02:27:16 +00:00
Bruce Evans
7a1a679ecb Ifdefed use of a GNU feature. 1998-02-03 20:32:38 +00:00
Tor Egge
5c623cb649 Add support for low resolution SMP kernel profiling.
- A nonprofiling version of s_lock (called s_lock_np) is used
    by mcount.

  - When profiling is active, more registers are clobbered in
    seemingly simple assembly routines. This means that some
    callers needed to save/restore extra registers.

  - The stack pointer must have space for a 'fake' return address
    in idle, to avoid stack underflow.
1997-12-15 02:18:35 +00:00
Steve Passe
78292efeef Another round of lock pushdown.
Add a simplelock to deal with disable_intr()/enable_intr() as used in UP kernel.
UP kernel expects that this is enough to guarantee exclusive access to
regions of code bracketed by these 2 functions.
Add a simplelock to bracket clock accesses in clock.c: clock_lock.

Help from:	Bruce Evans <bde@zeta.org.au>
1997-08-30 08:08:10 +00:00
Peter Wemm
6875d25465 Back out part 1 of the MCFH that changed $Id$ to $FreeBSD$. We are not
ready for it yet.
1997-02-22 09:48:43 +00:00
Bruce Evans
a7d00b5bf6 Moved definition of FUNCTION_ALIGNMENT to a machine-dependent place.
Changed it from 4 to 16 for i386's.  It can be anything for i386's,
but compiler options limit it to a power of 2, and assembler and
linker deficiencies limit it to a small power of 2 (<= 16).
We use 16 in the kernel to get smaller tables (see Makefile.i386 and
<machine/asmacros.h>).  We still use the default of 4 in user mode.

Use HISTCOUNTER instead of (*kcount) in the definition of KCOUNT()
for consistency with other macros.
1997-02-13 10:47:29 +00:00
Jordan K. Hubbard
1130b656e5 Make the long-awaited change from $Id$ to $FreeBSD$
This will make a number of things easier in the future, as well as (finally!)
avoiding the Id-smashing problem which has plagued developers for so long.

Boy, I'm glad we're not using sup anymore.  This update would have been
insane otherwise.
1997-01-14 07:20:47 +00:00
Bruce Evans
d6b9e17eb5 Improved non-statistical (GUPROF) profiling:
- use a more accurate and more efficient method of compensating for
  overheads.  The old method counted too much time against leaf
  functions.
- normally use the Pentium timestamp counter if available.
  On Pentiums, the times are now accurate to within a couple of cpu
  clock cycles per function call in the (unlikely) event that there
  are no cache misses in or caused by the profiling code.
- optionally use an arbitrary Pentium event counter if available.
- optionally regress to using the i8254 counter.
- scaled the i8254 counter by a factor of 128.  Now the i8254 counters
  overflow slightly faster than the TSC counters for a 150MHz Pentium :-)
  (after about 16 seconds).  This is to avoid fractional overheads.

files.i386:
permon.c temporarily has to be classified as a profiling-routine
because a couple of functions in it may be called from profiling code.

options.i386:
- I586_CTR_GUPROF is currently unused (oops).
- I586_PMC_GUPROF should be something like 0x70000 to enable (but not
  use unless prof_machdep.c is changed) support for Pentium event
  counters.  7 is a control mode and the counter number 0 is somewhere
  in the 0000 bits (see perfmon.h for the encoding).

profile.h:
- added declarations.
- cleaned up separation of user mode declarations.

prof_machdep.c:
Mostly clock-select changes.  The default clock can be changed by
editing kmem.  There should be a sysctl for this.

subr_prof.c:
- added copyright.
- calibrate overheads for the new method.
- documented new method.
- fixed races and and machine dependencies in start/stop code.

mcount.c:
Use the new overhead compensation method.

gmon.h:
- changed GPROF4 counter type from unsigned to int.  Oops, this should
  be machine-dependent and/or int32_t.
- reorganized overhead counters.

Submitted by:	Pentium event counter changes mostly by wollman
1996-10-17 19:32:31 +00:00
Bruce Evans
1f403fcfbf Cleaned up interrupt masking by declaring the state variable in a
machine-dependent macro and passing it to all machine-dependent
macros.

Eliminated the state variable for the GUPROF case.
1996-08-28 20:15:32 +00:00
Bruce Evans
e5171bbec0 Fixed user-mode mcount which I broke in the previous revision.
Do it the old way for now.

Moved recent additions around a lot to minimise ifdefs.

Added prototypes.
1996-01-01 17:11:21 +00:00
Bruce Evans
912e603778 Implemented non-statistical kernel profiling. This is based on
looking at a high resolution clock for each of the following events:
function call, function return, interrupt entry, interrupt exit,
and interesting branches.  The differences between the times of
these events are added at appropriate places in a ordinary histogram
(as if very fast statistical profiling sampled the pc at those
places) so that ordinary gprof can be used to analyze the times.

gmon.h:
Histogram counters need to be 4 bytes for microsecond resolutions.
They will need to be larger for the 586 clock.
The comments were vax-centric and wrong even on vaxes.  Does anyone
disagree?

gprof4.c:
The standard gprof should support counters of all integral sizes
and the size of the counter should be in the gmon header.  This
hack will do until then.  (Use gprof4 -u to examine the results
of non-statistical profiling.)

config/*:
Non-statistical profiling is configured with `config -pp'.
`config -p' still gives ordinary profiling.

kgmon/*:
Non-statistical profiling is enabled with `kgmon -B'.  `kgmon -b'
still enables ordinary profiling (and distables non-statistical
profiling) if non-statistical profiling is configured.
1995-12-29 15:30:05 +00:00
Paul Richards
8db02de884 Added MCOUNT_ENTER and MCOUNT_EXIT macros to profile.h
Removed inb function since it's more correctly in pio.h

Copied write_eflags and read_eflags over from npx.c

(Some changes to the macros suggested by Bruce were not made at this
time since his suggestions probably apply to all the macros and
these inlined/macro definitions need a lot of cleaning up at some
point in the future.)

Reviewed by:	Bruce
1994-09-15 16:27:14 +00:00
Paul Richards
836dc83b6a Made idempotent.
Reviewed by:
Submitted by:
1994-08-21 04:55:31 +00:00
David Greenman
3c4dd3568f Added $Id$ 1994-08-02 07:55:43 +00:00
Rodney W. Grimes
6cda32c071 BSD 4.4 Lite Kernel Sources 1994-05-25 01:34:38 +00:00