d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
a27ac4644a
freebsd-dev/sys/amd64/include/profile.h

200 lines
5.7 KiB
C
Raw Normal View History

Begin all license/copyright comments with /*-
2005-01-05 20:17:21 +00:00
/*-
sys: further adoption of SPDX licensing ID tags. Mainly focus on files that use BSD 3-Clause license. The Software Package Data Exchange (SPDX) group provides a specification to make it easier for automated tools to detect and summarize well known opensource licenses. We are gradually adopting the specification, noting that the tags are considered only advisory and do not, in any way, superceed or replace the license texts. Special thanks to Wind River for providing access to "The Duke of Highlander" tool: an older (2014) run over FreeBSD tree was useful as a starting point.
2017-11-20 19:43:44 +00:00
* SPDX-License-Identifier: BSD-3-Clause
*
BSD 4.4 Lite Kernel Sources
1994-05-25 01:34:38 +00:00
* Copyright (c) 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
Renumber copyright clause 4 Renumber cluase 4 to 3, per what everybody else did when BSD granted them permission to remove clause 3. My insistance on keeping the same numbering for legal reasons is too pedantic, so give up on that point. Submitted by: Jan Schaumann <jschauma@stevens.edu> Pull Request: https://github.com/freebsd/freebsd/pull/96
2017-02-28 23:42:47 +00:00
* 3. Neither the name of the University nor the names of its contributors
BSD 4.4 Lite Kernel Sources
1994-05-25 01:34:38 +00:00
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)profile.h 8.1 (Berkeley) 6/11/93
$Id$ -> $FreeBSD$
1999-08-28 01:08:13 +00:00
* $FreeBSD$
BSD 4.4 Lite Kernel Sources
1994-05-25 01:34:38 +00:00
*/
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
#ifndef _MACHINE_PROFILE_H_
#define _MACHINE_PROFILE_H_
Made idempotent. Reviewed by: Submitted by:
1994-08-21 04:55:31 +00:00
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#ifndef _SYS_CDEFS_H_
#error this file needs sys/cdefs.h as a prerequisite
#endif
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#ifdef _KERNEL
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
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
/*
* Config generates something to tell the compiler to align functions on 16
* byte boundaries. A strict alignment is good for keeping the tables small.
*/
#define FUNCTION_ALIGNMENT 16
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
/*
* The kernel uses assembler stubs instead of unportable inlines.
* This is mainly to save a little time when profiling is not enabled,
* which is the usual case for the kernel.
*/
#define _MCOUNT_DECL void mcount
#define MCOUNT
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
#ifdef GUPROF
#define MCOUNT_DECL(s)
#define MCOUNT_ENTER(s)
#define MCOUNT_EXIT(s)
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#ifdef __GNUCLIKE_ASM
MFi386 (1.37: GUPROF calibration macros; only routine adjustments needed).
2004-05-20 16:22:57 +00:00
#define MCOUNT_OVERHEAD(label) \
__asm __volatile("pushq %0; call __mcount; popq %%rcx" \
: \
In MCOUNT_OVERHEAD(label), actually use the `label' parameter. We were still using the global label named "profil", and this worked accidentally because all callers use the same name.
2006-10-28 07:59:11 +00:00
: "i" (label) \
Fix high resolution kernel profiling just enough to not crash at boot time, especially for SMP. If configured, it turns itself on at boot time for calibration, so is fragile even if never otherwise used. Both types of kernel profiling were supposed to use a global spinlock in the SMP case. If hi-res profiling is configured (but not necessarily used), this was supposed to be optimized by only using it when necessary, and slightly more efficiently, in asm. But it was not done at all for mcount entry where it is necessary. This caused crashes in the SMP case when either type of profiling was enabled. For mcount exit, it only caused wrong times. The times were wrongest with an i8254 timer since using that requires exclusive access to the hardware. The i8254 timer was too slow to use here 20 years ago and is much less usable now, but it is the default for the SMP case since TSCs weren't invariant when SMP was new. Do the locking in all hi-res SMP cases for simplicity. Calibration uses special asms, and the clobber lists in these were sort of inverted. They contained the arg and return registers which are not clobbered, but on amd64 they didn't contain the residue of the call-used registers which may be clobbered (%r10 and %r11). This usually caused hangs at boot time. This usually affected even the UP case.
2018-06-02 05:48:44 +00:00
: "cx", "r10", "r11", "memory")
MFi386 (1.37: GUPROF calibration macros; only routine adjustments needed).
2004-05-20 16:22:57 +00:00
#define MEXITCOUNT_OVERHEAD() \
__asm __volatile("call .mexitcount; 1:" \
: : \
Fix high resolution kernel profiling just enough to not crash at boot time, especially for SMP. If configured, it turns itself on at boot time for calibration, so is fragile even if never otherwise used. Both types of kernel profiling were supposed to use a global spinlock in the SMP case. If hi-res profiling is configured (but not necessarily used), this was supposed to be optimized by only using it when necessary, and slightly more efficiently, in asm. But it was not done at all for mcount entry where it is necessary. This caused crashes in the SMP case when either type of profiling was enabled. For mcount exit, it only caused wrong times. The times were wrongest with an i8254 timer since using that requires exclusive access to the hardware. The i8254 timer was too slow to use here 20 years ago and is much less usable now, but it is the default for the SMP case since TSCs weren't invariant when SMP was new. Do the locking in all hi-res SMP cases for simplicity. Calibration uses special asms, and the clobber lists in these were sort of inverted. They contained the arg and return registers which are not clobbered, but on amd64 they didn't contain the residue of the call-used registers which may be clobbered (%r10 and %r11). This usually caused hangs at boot time. This usually affected even the UP case.
2018-06-02 05:48:44 +00:00
: "r10", "r11", "memory")
MFi386 (1.37: GUPROF calibration macros; only routine adjustments needed).
2004-05-20 16:22:57 +00:00
#define MEXITCOUNT_OVERHEAD_GETLABEL(labelp) \
__asm __volatile("movq $1b,%0" : "=rm" (labelp))
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
#else
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#error this file needs to be ported to your compiler
Remove diffs to i386 version that came in via the compiler support ifdefs. This changes things like whitespace, inconsistent use of #ifndef vs #if !defined(), different macro argument orders, mismatched comments, etc.
2005-03-11 22:16:09 +00:00
#endif /* !__GNUCLIKE_ASM */
MFi386 (1.37: GUPROF calibration macros; only routine adjustments needed).
2004-05-20 16:22:57 +00:00
#else /* !GUPROF */
Use intr_disable() and intr_restore() instead of frobbing the flags register directly to disable interrupts. Reviewed by: bde (earlier version) MFC after: 2 weeks
2010-10-25 15:28:03 +00:00
#define MCOUNT_DECL(s) register_t s;
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
#ifdef SMP
Finish revs.1.23 and 1.24 so that MCOUNT_ENTER really actually compiles for SMP in the plain profiling case. It seems to work too. This error was not detected by LINT because LINT only compiles the GUPROF profiling case, which is is a superset of the plain profiling case for !SMP but which is so broken for SMP that the buggy code is not compiled.
2002-01-31 13:49:55 +00:00
extern int mcount_lock;
Use intr_disable() and intr_restore() instead of frobbing the flags register directly to disable interrupts. Reviewed by: bde (earlier version) MFC after: 2 weeks
2010-10-25 15:28:03 +00:00
#define MCOUNT_ENTER(s) { s = intr_disable(); \
Fix MCOUNT_ENTER() so it actually compiles in the profiling case. Pointy hat to: me Submitted by: Danny J. Zerkel <dzerkel@columbus.rr.com>
2001-07-14 21:40:53 +00:00
while (!atomic_cmpset_acq_int(&mcount_lock, 0, 1)) \
Get kernel profiling on SMP systems closer to working by replacing the mcount spin mutex with a very simple non-recursive spinlock implemented using atomic operations.
2001-06-28 04:03:29 +00:00
/* nothing */ ; }
#define MCOUNT_EXIT(s) { atomic_store_rel_int(&mcount_lock, 0); \
Use intr_disable() and intr_restore() instead of frobbing the flags register directly to disable interrupts. Reviewed by: bde (earlier version) MFC after: 2 weeks
2010-10-25 15:28:03 +00:00
intr_restore(s); }
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
#else
Use intr_disable() and intr_restore() instead of frobbing the flags register directly to disable interrupts. Reviewed by: bde (earlier version) MFC after: 2 weeks
2010-10-25 15:28:03 +00:00
#define MCOUNT_ENTER(s) { s = intr_disable(); }
#define MCOUNT_EXIT(s) (intr_restore(s))
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
#endif
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
#endif /* GUPROF */
Move the kernel-specific logic to adjust frompc from MI to MD. For these two reasons: 1. On ia64 a function pointer does not hold the address of the first instruction of a functions implementation. It holds the address of a function descriptor. Hence the user(), btrap(), eintr() and bintr() prototypes are wrong for getting the actual code address. 2. The logic forces interrupt, trap and exception entry points to be layed-out contiguously. This can not be achieved on ia64 and is generally just bad programming. The MCOUNT_FROMPC_USER macro is used to set the frompc argument to some kernel address which represents any frompc that falls outside the kernel text range. The macro can expand to ~0U to bail out in that case. The MCOUNT_FROMPC_INTR macro is used to set the frompc argument to some kernel address to represent a call to a trap or interrupt handler. This to avoid that the trap or interrupt handler appear to be called from everywhere in the call graph. The macro can expand to ~0U to prevent adjusting frompc. Note that the argument is selfpc, not frompc. This commit defines the macros on all architectures equivalently to the original code in sys/libkern/mcount.c. People can take it from here... Compile-tested on: alpha, amd64, i386, ia64 and sparc64 Boot-tested on: i386
2004-08-27 19:42:35 +00:00
void bintr(void);
void btrap(void);
void eintr(void);
void user(void);
#define MCOUNT_FROMPC_USER(pc) \
((pc < (uintfptr_t)VM_MAXUSER_ADDRESS) ? (uintfptr_t)user : pc)
#define MCOUNT_FROMPC_INTR(pc) \
((pc >= (uintfptr_t)btrap && pc < (uintfptr_t)eintr) ? \
((pc >= (uintfptr_t)bintr) ? (uintfptr_t)bintr : \
(uintfptr_t)btrap) : ~0UL)
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#else /* !_KERNEL */
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
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
#define FUNCTION_ALIGNMENT 4
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
#define _MCOUNT_DECL \
Use newly added __used attribute to keep static function symbol from being eliminated.
2004-07-29 18:02:28 +00:00
static void _mcount(uintfptr_t frompc, uintfptr_t selfpc) __used; \
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
static void _mcount
BSD 4.4 Lite Kernel Sources
1994-05-25 01:34:38 +00:00
Remove diffs to i386 version that came in via the compiler support ifdefs. This changes things like whitespace, inconsistent use of #ifndef vs #if !defined(), different macro argument orders, mismatched comments, etc.
2005-03-11 22:16:09 +00:00
#ifdef __GNUCLIKE_ASM
Fixed some style bugs (mainly misalignment of backslashes).
2004-05-19 16:04:26 +00:00
#define MCOUNT __asm(" \n\
In the userland .mcount(): - Don't use a frame pointer. Our callers need a frame pointer, but we could only use one to support things that aren't supported. (These things are: - profiling of profiling - debugging of profiling. The core ENTRY() macro doesn't support forcing a frame pointer for debugging, so don't do more here.) - Ensure that we are in the text section and have normal alignment. - Use the normal syntax for `.type'.
2006-10-28 13:12:06 +00:00
.text \n\
.p2align 4,0x90 \n\
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
.globl .mcount \n\
In the userland .mcount(): - Don't use a frame pointer. Our callers need a frame pointer, but we could only use one to support things that aren't supported. (These things are: - profiling of profiling - debugging of profiling. The core ENTRY() macro doesn't support forcing a frame pointer for debugging, so don't do more here.) - Ensure that we are in the text section and have normal alignment. - Use the normal syntax for `.type'.
2006-10-28 13:12:06 +00:00
.type .mcount,@function \n\
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
.mcount: \n\
pushq %rdi \n\
pushq %rsi \n\
pushq %rdx \n\
pushq %rcx \n\
pushq %r8 \n\
pushq %r9 \n\
Make profiling work for varargs functions.. %al is an additional argument which indicates the number of xmm registers used in the varargs. This stops the explosion that happened when profiling printf() etc.
2004-06-10 22:00:58 +00:00
pushq %rax \n\
In the userland .mcount(): - Don't use a frame pointer. Our callers need a frame pointer, but we could only use one to support things that aren't supported. (These things are: - profiling of profiling - debugging of profiling. The core ENTRY() macro doesn't support forcing a frame pointer for debugging, so don't do more here.) - Ensure that we are in the text section and have normal alignment. - Use the normal syntax for `.type'.
2006-10-28 13:12:06 +00:00
movq 8(%rbp),%rdi \n\
movq 7*8(%rsp),%rsi \n\
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
call _mcount \n\
Make profiling work for varargs functions.. %al is an additional argument which indicates the number of xmm registers used in the varargs. This stops the explosion that happened when profiling printf() etc.
2004-06-10 22:00:58 +00:00
popq %rax \n\
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
popq %r9 \n\
popq %r8 \n\
popq %rcx \n\
popq %rdx \n\
popq %rsi \n\
popq %rdi \n\
ret \n\
.size .mcount, . - .mcount");
#if 0
/*
* We could use this, except it doesn't preserve the registers that were
* being passed with arguments to the function that we were inserted
* into. I've left it here as documentation of what the code above is
* supposed to do.
*/
Stylify (mainly line up macro EOL-continuation \'s), and add a dummy alternative for lint.
2002-04-21 10:49:00 +00:00
#define MCOUNT \
void \
mcount() \
{ \
uintfptr_t selfpc, frompc; \
/* \
* Find the return address for mcount, \
* and the return address for mcount's caller. \
* \
* selfpc = pc pushed by call to mcount \
*/ \
Use C99 compatable asm statements.
2003-06-02 00:29:35 +00:00
__asm("movq 8(%%rbp),%0" : "=r" (selfpc)); \
Stylify (mainly line up macro EOL-continuation \'s), and add a dummy alternative for lint.
2002-04-21 10:49:00 +00:00
/* \
* frompc = pc pushed by call to mcount's caller. \
Fixed some style bugs (mainly misalignment of backslashes).
2004-05-19 16:04:26 +00:00
* The caller's stack frame has already been built, so %rbp is \
Stylify (mainly line up macro EOL-continuation \'s), and add a dummy alternative for lint.
2002-04-21 10:49:00 +00:00
* the caller's frame pointer. The caller's raddr is in the \
* caller's frame following the caller's caller's frame pointer.\
*/ \
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
__asm("movq (%%rbp),%0" : "=r" (frompc)); \
Stylify (mainly line up macro EOL-continuation \'s), and add a dummy alternative for lint.
2002-04-21 10:49:00 +00:00
frompc = ((uintfptr_t *)frompc)[1]; \
_mcount(frompc, selfpc); \
BSD 4.4 Lite Kernel Sources
1994-05-25 01:34:38 +00:00
}
The 'call mcount' hooks that gcc inserts when profiling are in a place that cannot handle the scratch registers being trashed. So we have to preserve them ourselves.
2004-05-18 22:52:32 +00:00
#endif
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#else /* !__GNUCLIKE_ASM */
i386/include/profile.h: Fixed a syntax error for the (!__KERNEL && !__GNUCLIKE_ASM) case in rev.1.36. Apparently, this case has never been reached even by lint. Submitted by: stefanf {amd64,i386}/include/profile.h: In case the above case is actually reached, break it properly by providing null support that will fail at link time instead of a stub that gives wrong (null) profiling at runtime.
2006-10-28 11:03:03 +00:00
#define MCOUNT
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#endif /* __GNUCLIKE_ASM */
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
Fixed some style bugs (mainly misalignment of backslashes).
2004-05-19 16:04:26 +00:00
typedef u_long uintfptr_t;
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
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#endif /* _KERNEL */
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
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
/*
* An unsigned integral type that can hold non-negative difference between
* function pointers.
*/
Fixed the type of fptrdiff_t. It needs to be 64 bits in theory, and in practice too since kernel addresses are almost 2^64 higher than most user addresses.
2004-05-19 16:19:11 +00:00
typedef u_long fptrdiff_t;
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
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#ifdef _KERNEL
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
Remove __P.
2002-03-20 05:48:58 +00:00
void mcount(uintfptr_t frompc, uintfptr_t selfpc);
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
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#else /* !_KERNEL */
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
#include <sys/cdefs.h>
__BEGIN_DECLS
netchild's mega-patch to isolate compiler dependencies into a central place. This moves the dependency on GCC's and other compiler's features into the central sys/cdefs.h file, while the individual source files can then refer to #ifdef __COMPILER_FEATURE_FOO where they by now used to refer to #if __GNUC__ > 3.1415 && __BARC__ <= 42. By now, GCC and ICC (the Intel compiler) have been actively tested on IA32 platforms by netchild. Extension to other compilers is supposed to be possible, of course. Submitted by: netchild Reviewed by: various developers on arch@, some time ago
2005-03-02 21:33:29 +00:00
#ifdef __GNUCLIKE_ASM
Remove __P.
2002-03-20 05:48:58 +00:00
void mcount(void) __asm(".mcount");
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
#endif
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
__END_DECLS
Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL" is an application space macro and the applications are supposed to be free to use it as they please (but cannot). This is consistant with the other BSD's who made this change quite some time ago. More commits to come.
1999-12-29 04:46:21 +00:00
#endif /* _KERNEL */
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
#endif /* !_MACHINE_PROFILE_H_ */
Reference in New Issue Copy Permalink