aboutsummaryrefslogtreecommitdiff
path: root/elf/dl-profile.c
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>1997-08-10 18:37:15 +0000
committerUlrich Drepper <drepper@redhat.com>1997-08-10 18:37:15 +0000
commit0413b54c02d31cae62e8d13b3ee7ac109ceeff0e (patch)
tree5159587edd2bf4a39fcb5c42588aa35c7350fe8d /elf/dl-profile.c
parent55c14926be46b12fda4e01d0977911d3b0883db7 (diff)
downloadglibc-0413b54c02d31cae62e8d13b3ee7ac109ceeff0e.zip
glibc-0413b54c02d31cae62e8d13b3ee7ac109ceeff0e.tar.gz
glibc-0413b54c02d31cae62e8d13b3ee7ac109ceeff0e.tar.bz2
1997-08-10 18:48 Ulrich Drepper <drepper@cygnus.com> * Makeconfig: Define build-programs to no if not set and $(config-os) is none. * Makerules (+depfiles): Don't add $(others) if not build-programs. * Rules (others): Don't depend on $(install-bin), $(install-rootbin) and $(install-sbin) if not build-programs. * Makefile (subdirs): Remove login. * sysdeps/mach/hurd/Subdirs: Add login. * sysdeps/unix/Subdirs: Add login. * sysdeps/generic/sys/mman.h: Test feature macros before defining non-POSIX things. Add MAP_FAILED. * sysdeps/unix/bsd/osf/sys/mman.h: Likewise. * sysdeps/unix/bsd/sun/sunos4/sys/mman.h: Likewise. * sysdeps/unix/bsd/ultrix4/sys/mman.h: Likewise. * sysdeps/unix/sysv/irix4/sys/mman.h: Likewise. * sysdeps/unix/sysv/linux/sys/mman.h: Rewrite to not use kernel header but bits/mman.h. Test feature macros before definitions non-POSIX functions. * sysdeps/unix/sysv/linux/alpha/bits/mman.h: New file. * sysdeps/unix/sysv/linux/i386/bits/mman.h: New file. * sysdeps/unix/sysv/linux/m68k/bits/mman.h: New file. * sysdeps/unix/sysv/linux/mips/bits/mman.h: New file. * sysdeps/unix/sysv/linux/powerpc/bits/mman.h: New file. * sysdeps/unix/sysv/linux/sparc/bits/mman.h: New file. * sysdeps/unix/sysv/linux/sparc64/bits/mman.h: New file. * sysdeps/unix/sysv/linux/alpha/Dist: Add bits/mman.h. * sysdeps/unix/sysv/linux/i386/Dist: Likewise. * sysdeps/unix/sysv/linux/m68k/Dist: Likewise. * sysdeps/unix/sysv/linux/mips/Dist: Likewise. * sysdeps/unix/sysv/linux/powerpc/Dist: Likewise. * sysdeps/unix/sysv/linux/sparc/Dist: Likewise. * sysdeps/unix/sysv/linux/sparc64/Dist: New file. Likewise. * catgets/open_catalog.c (__open_catalog): Compare result of mmap with MAP_FAILED and not -1. * elf/dl-load.c (_dl_map_object_from_fd): Likewise. * elf/dl-minimal.c (malloc): Likewise. * elf/dl-misc.c (_dl_sysdep_read_whole_file): Likewise. * locale/loadlocale.c (_nl_load_locale): Likewise. * locale/programs/localedef.c: Likewise. * malloc/malloc.c (mmap_chunk): Likewise. (new_heap): Likewise. * string/stratcliff.c: Likewise. * string/tester.c: Add tests for stpcpy. * gmon/gmon.c (__monstartup): Use calloc instead of malloc+memset. * gmon/sys/gmon.h: Add prototype for write_profiling. * elf/dl-profile.c: Add decsriptions and implement reading of existing data in profiling file. * gmon/sys/gmon_out.h (GMON_SHOBJ_VERSION): New macro for shared lib profiling data. * sysdeps/stub/bits/libc-lock.h (__libc_once_define): Add new first parameter for class. * inet/inet_ntoa.c: Make once control variable static. Correctly handle case where key cannot be retrieved. * inet/Makefile (tests): Add tst-ntoa. * inet/tst-ntoa.c: New file. * manual/time.texi: Document localtime_r, gmtime_r, asctime_r, and ctime_r. Mention that tzname values must not be changed. * manual/users.texi: Document UTMP/WTMP handling functions. Mainly written by Mark Kettenis. * math/libm-test.c (cbrt_test): Add test for number with aboslute value < 1.0. * nss/nss_files/files-XXX.c (internal_setent): If opening of file failed with EGAIN return NSS_STATUS_TRYAGAIN. * nss/nss_files/files-alias.c (internal_setent): Likewise. * sysdeps/generic/bits/utmp.h: Pretty print. * sysdeps/i386/i586/strcpy.S: New file. Much faster implementation. * sysdeps/i386/i586/stpcpy.S: New file. * sysdeps/i386/i686/Implies: Don't fall back on i586 versions since these are less efficient than i486/i386 versions. * sysdeps/libm-i387/e_rem_pio2.c: Add empty file to prevent the version from libm-ieee754 be compiled since the later is not needed. * sysdeps/libm-i387/e_rem_pio2f.c: Likewise. * sysdeps/libm-i387/e_rem_pio2l.c: Likewise. * sysdeps/libm-i387/k_rem_pio2.c: Likewise. * sysdeps/libm-i387/k_rem_pio2f.c: Likewise. * sysdeps/libm-i387/k_rem_pio2l.c: Likewise. * sysdeps/m68k/fpu/e_rem_pio2.c: Likewise. * sysdeps/m68k/fpu/e_rem_pio2f.c: Likewise. * sysdeps/m68k/fpu/e_rem_pio2l.c: Likewise. * sysdeps/m68k/fpu/k_rem_pio2.c: Likewise. * sysdeps/m68k/fpu/k_rem_pio2f.c: Likewise. * sysdeps/m68k/fpu/k_rem_pio2l.c: Likewise. * sysdeps/libm-i387/s_cbrt.S: Fix several bugs. * sysdeps/libm-i387/s_cbrtf.S: Likewise. * sysdeps/libm-i387/s_cbrtl.S: Likewise. * sysdeps/unix/sysv/linux/if_index.c (if_indextoname): Correct little bug. * sysdeps/unix/sysv/linux/bits/socket.h (struct msghdr): Make field msg_iovlen of type int. * time/tzfile.c: Change return type of __tzstring to char *. * time/tzset.c: Likewise. Change definition of __tzstring. * time/tzset.c: Interpret no DST information in user provided time zone specification as it is meant: no DST. Patch by Paul Eggert <eggert@twinsun.com>. 1997-07-20 03:01 Geoff Keating <geoffk@ozemail.com.au> * sysdeps/elf/dl-load.c (add_name_to_object): New procedure. (_dl_map_object_from_fd): Use add_name_to_object. (_dl_map_object): If an object's SONAME is used to resolve a dependency, add it to the list of the object's names. * inet/getnameinfo.c: Make `domain' non-const. * sysdeps/unix/sysv/linux/powerpc/kernel_termios.c: Clean up. * math/test-fenv.c (feenv_nomask_test): Don't execute if FE_NOMASK_ENV is not defined, or if fesetenv(FE_NOMASK_ENV) sets errno to ENOSYS. * sysdeps/powerpc/dl-machine.h: Print proper error message on unknown reloc type (rather than using assert). * sysdeps/unix/sysv/linux/powerpc/profil-counter.h: New file. * sysdeps/unix/sysv/linux/powerpc/profil.c: Deleted. 1997-07-16 12:47 Geoff Keating <geoffk@ozemail.com.au> * sysdeps/powerpc/bits/fenv.h (feraiseexcept): New optimising macro. (feclearexcept): New optimising macro. (FE_NOMASK_ENV): Change to procedure so it can enable exceptions. (FE_ENABLED_ENV): Add. (FE_NONIEEE_ENV): Add. * sysdeps/powerpc/bits/fenv_const.c: Add __fe_enabled_env, __fe_nonieee_env; delete __fe_nomask_env. * sysdeps/powerpc/bits/fe_nomask.c: New file (stub warning until it gets implemented in the kernel). * sysdeps/powerpc/fraiseenv.c: Deal with chips that don't have FE_INVALID_SOFTWARE implemented. Use macros for bit names for clarity. * sysdeps/powerpc/fsetexcptflag.c: Likewise. * io/ftw.c: Don't compare holes in structures. * sysdeps/unix/sysv/linux/sys/sysmacros.h: Cast the result of the macros to `int', because otherwise it might be `long long' which the calling code is probably not expecting. * sysdeps/libm-ieee754/s_lround.c [NO_LONG_DOUBLE]: Fix a few bugs, document the existence of some more. * sysdeps/powerpc/s_llrint.c: New file. * sysdeps/powerpc/s_lrint.c: New file. * sysdeps/powerpc/s_llround.c: New file. * sysdeps/powerpc/s_lround.c: New file. * sysdeps/powerpc/s_sqrt.c: New file. * sysdeps/powerpc/s_sqrtf.c: New file. * sysdeps/powerpc/w_sqrt.s: New empty file. * sysdeps/powerpc/w_sqrtf.s: New empty file. * sysdeps/powerpc/t_sqrt.c: New file. * sysdeps/powerpc/test-arithf.c: New file. * sysdeps/powerpc/Makefile [subdir=math]: Add t_sqrt to support routines. Add test-arithf to test programs. * sysdeps/powerpc/bits/mathdef.h: Add FP_ILOGB0, FP_ILOGBNAN. * sysdeps/powerpc/strcmp.s: Simplify drastically. Now much neater, and possibly faster (or possibly slower, depending on input). 1997-06-08 22:55 Geoff Keating <geoffk@ozemail.com.au> * sysdeps/powerpc/fenvbits.h: Correct FE_DFL_ENV and FE_NOMASK_ENV macros. * sysdeps/powerpc/s_rint.c: New file. 1997-05-22 08:47 Geoff Keating <geoffk@ozemail.com.au> * sysdeps/powerpc/Makefile [subdir=math]: Add q_* routines. * sysdeps/powerpc/Dist: Add quad_float.h. * sysdeps/powerpc/q_dtoq.c: New file. * sysdeps/powerpc/q_itoq.c: New file. * sysdeps/powerpc/q_lltoq.c: New file. * sysdeps/powerpc/q_neg.c: New file. * sysdeps/powerpc/q_qtoi.c: New file. * sysdeps/powerpc/q_qtoll.c: New file. * sysdeps/powerpc/q_qtos.c: New file. * sysdeps/powerpc/q_qtou.c: New file. * sysdeps/powerpc/q_qtoull.c: New file. * sysdeps/powerpc/q_stoq.c: New file. * sysdeps/powerpc/q_ulltoq.c: New file. * sysdeps/powerpc/q_utoq.c: New file. * sysdeps/powerpc/quad_float.h: New file. * sysdeps/powerpc/test-arith.c: New file. * sysdeps/powerpc/fpu_control.h: Fix _FPU_GETCW. * sysdeps/powerpc/fegetround.c: Use mcrfs to be faster and not require a stack frame. * sysdeps/powerpc/bits/fenv.h: Include inline macro for fegetround. 1997-05-18 05:55 Geoff Keating <geoffk@ozemail.com.au> * sysdeps/powerpc/fenv_libc.h (fegetenv_register, fesetenv_register): Add 'volatile'. (set_fpscr_bit, reset_fpscr_bit): New macros, FPSCR_* constants to use with them. * sysdeps/powerpc/s_copysign.S: New file. * sysdeps/powerpc/s_copysignf.s: New file. * sysdeps/powerpc/s_fabs.S: New file. * sysdeps/powerpc/s_fabsf.s: New file. * sysdeps/powerpc/s_isnan.c: New file. * sysdeps/powerpc/s_isnanf.s: New file. * sysdeps/powerpc/s_rintf.c: New file. * sysdeps/powerpc/fenvbits.h: Make FE_INVALID the summary bit in the FPSCR, not the enable bit. * sysdeps/powerpc/fraiseexcpt.c: Consequent change to the above. * sysdeps/powerpc/fclrexcpt.c: Correct. * sysdeps/powerpc/fsetexcptflag.c: Correct. * sysdeps/powerpc/ftestexcpt.c: Is now much simpler. * sysdeps/powerpc/fgetexcptflg.c: Simplify. * sysdeps/powerpc/strlen.s: Schedule better, save 3 clocks :-). * sysdeps/powerpc/dl-machine.h (elf_machine_rela): Add comment explaining some reentrancy issues with lazy PLT entries. 1997-08-09 13:04 Mark Kettenis <kettenis@phys.uva.nl> * login/logout.c (logout): utmpname returns -1 on error. * login/libutil.map: Remove updwtmp. * login/getutline.c: Rename getutline to __getutline and make getutline a weak alias. Make getutxline a weak alias for __getutline. * login/getutid.c: Rename getutid to __getutid and make getutid a weak alias. Make getutxid a weak alias for __getutid. * libc.map: Add getutxid, getutxline. * login/utmpname.c (__utmpname): Reset backend right after backend endutent call. * login/utmp_file.c: Reordered functions. Remove unecessary header files. (getutent_r_file, pututline_file): Do not call setutent_file. At this point the file is guaranteed to be open (assert!). (getutid_r_file, getutline_r_file): Remove check for validity of file descriptor. At this point the file is guaranteed to be open. (getutent_r_file, internal_getut_r, getutline_r_file, pututline_file, updwtmp_file): Do not wait when unlocking file. * login/utmp_daemon.c: General cleanup and a bit of reordering. (getutent_r_daemon, pututline_daemon): Do not call setutent_daemon. At this point the socket is guaranteed to be open (assert!). (getutid_r_daemon, getutline_r_daemon): Do not check if daemon_sock is valid. At this point the socket is guaranteed to be open (assert!). * login/getutline_r.c: Remove unnecessary header files. (__getutline_r): Do not call backend setutent. * login/getutid_r.c: Remove unnecessary header files. (__getutid_r): Do not call backend setutent. * login/getutent_r.c: Remove unneccesary header files. (__libc_utmp_unknown_functions): Added getutid_r_unknown, getutline_r_unknown. (setutent_unknown): Only set file backend if setutent for the file backend was successful. (getutent_r_unknown, pututline_unknown): Call setutent_unknown instead of __setutent. Report failure if no backend was selected. (getutid_r_unknown): New function. (getutline_r_unknown): New function. (__endutent): Reset backend. This makes sure all backends are checked on the next setutent call. 1997-08-08 20:20 Thorsten Kukuk <kukuk@vt.uni-paderborn.de> * nis_cache.c: Replace dummy functions. * libc.map: Add xdr_sizeof symbol. * sunrpc/Makefile: Add xdr_sizeof to routines. * sunrpc/rpc/xdr.h: Add xdr_sizeof prototype. * sunrpc/xdr_sizeof.c: New, from tirpc 2.3. 1997-08-08 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/bits/libc-lock.h (__libc_once): Define correctly. 1997-08-07 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/hurd/profil.c (fetch_samples): Put parens in the right place. 1997-08-06 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/hurd/profil.c (fetch_samples): Do arithmetic on PC's in long long to avoid overflow. 1997-08-07 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/bits/libc-lock.h (__libc_once, __libc_once_define): New macros. 1997-08-06 Andreas Jaeger <aj@arthur.rhein-neckar.de> * nis/Makefile (headers): Remove bits/nislib.h. 1997-08-06 14:54 Ulrich Drepper <drepper@cygnus.com> * sysdeps/mach/hurd/Subdirs: Add login. 1997-08-06 14:23 Klaus Espenlaub <kespenla@hydra.informatik.uni-ulm.de> * db/hash/hash.c (init_hash): Don't use stat() if it doesn't provide the preferred block size. * login/programs/database.c (store_state_entry): Don't compile if there is no ut_type field. (store_state_entry, store_process_entry): Use the ut_tv field for timestamps if supported. * login/programs/utmpdump.c (print_entry): Always use ut_tv field. * login/programs/xtmp.c: Fix numerous xtmp/utmp typos. Use the ut_tv field for timestamps if supported. * login/programs/xtmp.h: Fix xtmp/utmp typo. * sysdeps/posix/defs.c (stdstream): Change (PTR) to (void *). * sysdeps/stub/connect.c (connect): Change to __connect, add alias. * sysdeps/stub/send.c (send): Likewise. * sysdeps/stub/s_exp2f.c: Emit correct stub_warning(). * sysdeps/stub/statfs.c: Move stub_warning() to the usual place. * sysdeps/stub/init-first.c: Add definition of __libc_pid. 1997-08-05 13:28 Philip Blundell <pb@spring.nexus.co.uk> * sysdeps/standalone/arm/bits/errno.h: Add EISDIR, EOPNOTSUPP; tidy up formatting. * Makefile (subdirs): Remove `login'. * sysdeps/unix/Subdirs: New file; build `login' subdirectory for Unix systems. 1997-08-05 Andreas Schwab <schwab@issan.informatik.uni-dortmund.de> * sysdeps/generic/bits/utmpx.h: New file. * sysdeps/mach/hurd/Dist: Add some files. * sysdeps/mips/Dist: Likewise. * sysdeps/mips/mips64/Dist: Likewise. * sysdeps/sparc/Dist: Likewise. * sysdeps/unix/sysv/linux/mips/Dist: Likewise. * sysdeps/unix/sysv/linux/sparc/Dist: Likewise. * sysdeps/mips/mipsel/Dist: New file. * sysdeps/sparc64/elf/Dist: New file. * sysdeps/unix/sysv/linux/sparc64/Dist: New file. 1997-08-05 Andreas Schwab <schwab@issan.informatik.uni-dortmund.de> * libc.map: Add missing symbols. 1997-08-05 Andreas Jaeger <aj@arthur.rhein-neckar.de> * manual/socket.texi: Correct typos. * manual/math.texi: Correct typos. * manual/time.texi (Formatting Date and Time): Likewise. 1997-08-04 13:06 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * gmon/gmon.c (write_gmon): New function; guts from _mcleanup. (_mcleanup): Use write_gmon. (write_profiling): This function can be safely called at any time to write a current histogram without interfering with ongoing profiling. * sysdeps/mach/hurd/profil.c (fetch_samples): Initialize NSAMPLES. 1997-08-01 17:53 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/hurd/profil.c (fetch_samples): Sample buffer need not be vm_deallocated; it's a stack buffer. (profil_vm_deallocate): Delete prototype. (#include <../mach/RPC_vm_deallocate_rpc.c>): Drop this inclusion. * sysdeps/mach/hurd/Makefile ($(common-objpfx)hurd/../mach/RPC_vm_deallocate_rpc.c): Delete this rule. * sysdeps/mach/hurd/profil.c (fetch_samples): New function, guts from profile_waiter. (profile_waiter): Use fetch_samples. (profil): When turning off profiling, fetch the last bunch of samples before disabling PC sampling. (fetch_samples): Add prototype. 1997-07-30 12:53 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/hurd/Makefile: Give normal rules for the mach RPC source included by profil.c instead of trying to use before-compile grot. 1997-07-23 15:04 Thomas Bushnell, n/BSG <thomas@gnu.ai.mit.edu> * sysdeps/mach/hurd/profil.c (profile_waiter): Do vm_deallocate after releasing lock. Use special RPC stubs and avoid assert, thus making this function entirely independent of the threadvar mechanism and of cthreads. (lock): Convert to be a spin lock instead of a mutex, so that the waiter thread need not use cthreads. Use a fork prepare hook instead of _hurd_fork_locks to make sure we are clean before forking. (fork_profil_child): Renamed from fork_profil. (profil_reply_port): New variable. (profil_vm_deallocate, profil_task_get_sampled_pcs): Special RPC stubs made by special hacks. * sysdeps/mach/hurd/Makefile (before-compile): Add the mach RPC source files that profil.c needs if we are in the gmon directory. * mach/setup-thread.c (__mach_setup_thread): Delete avoidance of a cthreads bug that hasn't existed for two years. * stdio-common/printf_fp.c (__printf_fp): Correct rounding of numbers * locale/programs/locale.c (print_escaped): New function. * time/australasia: Likewise. (open_database, synchronize_database, initialize_database): * nss/nss_files/files-netgrp.c (_nss_netgroup_parseline): Don't * Makerules (load-map-file): Currectly handle missing map file. cannot rely on M_SQRT2 being defined. (log1p): Use __M_SQRT2 not M_SQRT2.
Diffstat (limited to 'elf/dl-profile.c')
-rw-r--r--elf/dl-profile.c251
1 files changed, 199 insertions, 52 deletions
diff --git a/elf/dl-profile.c b/elf/dl-profile.c
index 8056249..c8028a7 100644
--- a/elf/dl-profile.c
+++ b/elf/dl-profile.c
@@ -50,29 +50,129 @@
This approach is very different from the normal profiling. We have
to use the profiling data in exactly the way they are expected to
- be written to disk. */
+ be written to disk. But the normal format used by gprof is not usable
+ to do this. It is optimized for size. It writes the tags as single
+ bytes but this means that the following 32/64 bit values are
+ unaligned.
+
+ Therefore we use a new format. This will look like this
+
+ 0 1 2 3 <- byte is 32 bit word
+ 0000 g m o n
+ 0004 *version* <- GMON_SHOBJ_VERSION
+ 0008 00 00 00 00
+ 000c 00 00 00 00
+ 0010 00 00 00 00
+
+ 0014 *tag* <- GMON_TAG_TIME_HIST
+ 0018 ?? ?? ?? ??
+ ?? ?? ?? ?? <- 32/64 bit LowPC
+ 0018+A ?? ?? ?? ??
+ ?? ?? ?? ?? <- 32/64 bit HighPC
+ 0018+2*A *histsize*
+ 001c+2*A *profrate*
+ 0020+2*A s e c o
+ 0024+2*A n d s \0
+ 0028+2*A \0 \0 \0 \0
+ 002c+2*A \0 \0 \0
+ 002f+2*A s
+
+ 0030+2*A ?? ?? ?? ?? <- Count data
+ ... ...
+ 0030+2*A+K ?? ?? ?? ??
+
+ 0030+2*A+K *tag* <- GMON_TAG_CG_ARC
+ 0034+2*A+K *lastused*
+ 0038+2*A+K ?? ?? ?? ??
+ ?? ?? ?? ?? <- FromPC#1
+ 0038+3*A+K ?? ?? ?? ??
+ ?? ?? ?? ?? <- ToPC#1
+ 0038+4*A+K ?? ?? ?? ?? <- Count#1
+ ... ... ...
+ 0038+(2*(CN-1)+2)*A+(CN-1)*4+K ?? ?? ?? ??
+ ?? ?? ?? ?? <- FromPC#CGN
+ 0038+(2*(CN-1)+3)*A+(CN-1)*4+K ?? ?? ?? ??
+ ?? ?? ?? ?? <- ToPC#CGN
+ 0038+(2*CN+2)*A+(CN-1)*4+K ?? ?? ?? ?? <- Count#CGN
+
+ We put (for now? no basic block information in the file since this would
+ introduce rase conditions among all the processes who want to write them.
+
+ `K' is the number of count entries which is computed as
+
+ textsize / HISTFRACTION
+
+ `CG' in the above table is the number of call graph arcs. Normally,
+ the table is sparse and the profiling code writes out only the those
+ entries which are really used in the program run. But since we must
+ not extend this table (the profiling file) we'll keep them all here.
+ So CN can be executed in advance as
+
+ MINARCS <= textsize*(ARCDENSITY/100) <= MAXARCS
+
+ Now the remaining question is: how to build the data structures we can
+ work with from this data. We need the from set and must associate the
+ froms with all the associated tos. We will do this by constructing this
+ data structures at the program start. To do this we'll simply visit all
+ entries in the call graph table and add it to the appropriate list. */
extern char *_strerror_internal __P ((int, char *buf, size_t));
extern int __profile_frequency __P ((void));
-
-static struct gmonparam param;
-
/* We define a special type to address the elements of the arc table.
This is basically the `gmon_cg_arc_record' format but it includes
the room for the tag and it uses real types. */
struct here_cg_arc_record
{
- char tag;
- uintptr_t from_pc __attribute__ ((packed));
- uintptr_t self_pc __attribute__ ((packed));
- uint32_t count __attribute__ ((packed));
- };
+ uintptr_t from_pc;
+ uintptr_t self_pc;
+ uint32_t count;
+ } __attribute__ ((packed));
static struct here_cg_arc_record *data;
+/* This is the number of entry which have been incorporated in the toset. */
+static uint32_t narcs;
+/* This is a pointer to the object representing the number of entries
+ currently in the mmaped file. At no point of time this has to be the
+ same as NARCS. If it is equal all entries from the file are in our
+ lists. */
+static uint32_t *narcsp;
+
+/* Description of the currently profiled object. */
+static long int state;
+static volatile uint16_t *kcount;
+static size_t kcountsize;
+
+struct here_tostruct
+ {
+ struct here_cg_arc_record volatile *here;
+ uint16_t link;
+ };
+
+static uint16_t *froms;
+static size_t fromssize;
+
+static struct here_tostruct *tos;
+static size_t tossize;
+static size_t tolimit;
+static size_t toidx;
+
+static uintptr_t lowpc;
+static uintptr_t highpc;
+static size_t textsize;
+static unsigned int hashfraction;
+static unsigned int log_hashfraction;
+
+/* This is the information about the mmaped memory. */
+static struct gmon_hdr *addr;
+static off_t expected_size;
+
+
+/* Set up profiling data to profile object desribed by MAP. The output
+ file is found (or created) in OUTPUT_DIR. */
void
_dl_start_profile (struct link_map *map, const char *output_dir)
{
@@ -82,11 +182,10 @@ _dl_start_profile (struct link_map *map, const char *output_dir)
const ElfW(Phdr) *ph;
ElfW(Addr) mapstart = ~((ElfW(Addr)) 0);
ElfW(Addr) mapend = 0;
- off_t expected_size;
struct gmon_hdr gmon_hdr;
struct gmon_hist_hdr hist_hdr;
- struct gmon_hdr *addr;
char *hist;
+ size_t idx;
/* Compute the size of the sections which contain program code. */
for (ph = map->l_phdr; ph < &map->l_phdr[map->l_phnum]; ++ph)
@@ -104,40 +203,41 @@ _dl_start_profile (struct link_map *map, const char *output_dir)
/* Now we can compute the size of the profiling data. This is done
with the same formulars as in `monstartup' (see gmon.c). */
- param.state = GMON_PROF_OFF;
- param.lowpc = mapstart + map->l_addr;
- param.highpc = mapend + map->l_addr;
- param.textsize = mapend - mapstart;
- param.kcountsize = param.textsize / HISTFRACTION;
- param.hashfraction = HASHFRACTION;
- param.log_hashfraction = -1;
+ state = GMON_PROF_OFF;
+ lowpc = ROUNDDOWN (mapstart + map->l_addr,
+ HISTFRACTION * sizeof(HISTCOUNTER));
+ highpc = ROUNDUP (mapend + map->l_addr,
+ HISTFRACTION * sizeof(HISTCOUNTER));
+ textsize = highpc - lowpc;
+ kcountsize = textsize / HISTFRACTION;
+ hashfraction = HASHFRACTION;
if ((HASHFRACTION & (HASHFRACTION - 1)) == 0)
/* If HASHFRACTION is a power of two, mcount can use shifting
instead of integer division. Precompute shift amount. */
- param.log_hashfraction = ffs (param.hashfraction
- * sizeof (*param.froms)) - 1;
- param.fromssize = param.textsize / HASHFRACTION;
- param.tolimit = param.textsize * ARCDENSITY / 100;
- if (param.tolimit < MINARCS)
- param.tolimit = MINARCS;
- if (param.tolimit > MAXARCS)
- param.tolimit = MAXARCS;
- param.tossize = param.tolimit * sizeof (struct tostruct);
+ log_hashfraction = __builtin_ffs (hashfraction * sizeof (*froms)) - 1;
+ else
+ log_hashfraction = -1;
+ fromssize = textsize / HASHFRACTION;
+ tolimit = textsize * ARCDENSITY / 100;
+ if (tolimit < MINARCS)
+ tolimit = MINARCS;
+ if (tolimit > MAXARCS)
+ tolimit = MAXARCS;
+ tossize = tolimit * sizeof (struct here_tostruct);
expected_size = (sizeof (struct gmon_hdr)
- + 1 + sizeof (struct gmon_hist_hdr)
- + ((1 + sizeof (struct gmon_cg_arc_record))
- * (param.fromssize / sizeof (*param.froms))));
+ + 4 + sizeof (struct gmon_hist_hdr) + kcountsize
+ + 4 + 4 + tossize * sizeof (struct here_cg_arc_record));
/* Create the gmon_hdr we expect or write. */
memset (&gmon_hdr, '\0', sizeof (struct gmon_hdr));
memcpy (&gmon_hdr.cookie[0], GMON_MAGIC, sizeof (gmon_hdr.cookie));
- *(int32_t *) gmon_hdr.version = GMON_VERSION;
+ *(int32_t *) gmon_hdr.version = GMON_SHOBJ_VERSION;
/* Create the hist_hdr we expect or write. */
*(char **) hist_hdr.low_pc = (char *) mapstart;
*(char **) hist_hdr.high_pc = (char *) mapend;
- *(int32_t *) hist_hdr.hist_size = param.kcountsize / sizeof (HISTCOUNTER);
+ *(int32_t *) hist_hdr.hist_size = kcountsize / sizeof (HISTCOUNTER);
*(int32_t *) hist_hdr.prof_rate = __profile_frequency ();
strncpy (hist_hdr.dimen, "seconds", sizeof (hist_hdr.dimen));
hist_hdr.dimen_abbrev = 's';
@@ -193,15 +293,19 @@ _dl_start_profile (struct link_map *map, const char *output_dir)
{
__close (fd);
wrong_format:
+
+ if (addr != NULL)
+ __munmap ((void *) addr, expected_size);
+
_dl_sysdep_error (filename,
": file is no correct profile data file for `",
_dl_profile, "'\n", NULL);
return;
}
- addr = (void *) __mmap (NULL, expected_size, PROT_READ|PROT_WRITE,
- MAP_SHARED|MAP_FILE, fd, 0);
- if (addr == (void *) -1)
+ addr = (struct gmon_hdr *) __mmap (NULL, expected_size, PROT_READ|PROT_WRITE,
+ MAP_SHARED|MAP_FILE, fd, 0);
+ if (addr == (struct gmon_hdr *) MAP_FAILED)
{
char buf[400];
int errnum = errno;
@@ -217,54 +321,97 @@ _dl_start_profile (struct link_map *map, const char *output_dir)
/* Pointer to data after the header. */
hist = (char *) (addr + 1);
+ kcount = (uint16_t *) ((char *) hist + sizeof (uint32_t)
+ + sizeof (struct gmon_hist_hdr));
/* Compute pointer to array of the arc information. */
- data = (struct here_cg_arc_record *) (hist + 1
- + sizeof (struct gmon_hist_hdr));
+ data = (struct here_cg_arc_record *) ((char *) kcount + kcountsize
+ + 2 * sizeof (uint32_t));
+ narcsp = (uint32_t *) (hist + sizeof (uint32_t)
+ + sizeof (struct gmon_hist_hdr) + sizeof (uint32_t));
if (st.st_size == 0)
{
/* Create the signature. */
- size_t cnt;
-
memcpy (addr, &gmon_hdr, sizeof (struct gmon_hdr));
- *hist = GMON_TAG_TIME_HIST;
- memcpy (hist + 1, &hist_hdr, sizeof (struct gmon_hist_hdr));
+ *(uint32_t *) hist = GMON_TAG_TIME_HIST;
+ memcpy (hist + sizeof (uint32_t), &hist_hdr,
+ sizeof (struct gmon_hist_hdr));
- for (cnt = 0; cnt < param.fromssize / sizeof (*param.froms); ++cnt)
- data[cnt].tag = GMON_TAG_CG_ARC;
+ *(uint32_t *) (hist + sizeof (uint32_t) + sizeof (struct gmon_hist_hdr)
+ + kcountsize) = GMON_TAG_CG_ARC;
}
else
{
/* Test the signature in the file. */
if (memcmp (addr, &gmon_hdr, sizeof (struct gmon_hdr)) != 0
- || *hist != GMON_TAG_TIME_HIST
- || memcmp (hist + 1, &hist_hdr, sizeof (struct gmon_hist_hdr)) != 0)
+ || *(uint32_t *) hist != GMON_TAG_TIME_HIST
+ || memcmp (hist + sizeof (uint32_t), &hist_hdr,
+ sizeof (struct gmon_hist_hdr)) != 0
+ || (*(uint32_t *) (hist + sizeof (uint32_t)
+ + sizeof (struct gmon_hist_hdr) + kcountsize)
+ != GMON_TAG_CG_ARC))
goto wrong_format;
}
+ /* Allocate memory for the froms data and the pointer to the tos records. */
+ froms = (uint16_t *) calloc (fromssize + tossize, 1);
+ if (froms == NULL)
+ {
+ __munmap ((void *) addr, expected_size);
+ _dl_sysdep_fatal ("Out of memory while initializing profiler", NULL);
+ /* NOTREACHED */
+ }
+
+ tos = (struct here_tostruct *) ((char *) froms + fromssize);
+ toidx = 0;
+
+ /* Now we have to process all the arc count entries. BTW: it is
+ not critical whether the *NARCSP value changes meanwhile. Before
+ we enter a new entry in to toset we will check that everything is
+ available in TOS. This happens in _dl_mcount.
+
+ Loading the entries in reverse order should help to get the most
+ frequently used entries at the front of the list. */
+ for (idx = narcs = *narcsp; idx > 0; )
+ {
+ size_t from_index;
+ size_t newtoidx;
+ --idx;
+ from_index = ((data[idx].from_pc - lowpc)
+ / (hashfraction * sizeof (*froms)));
+ newtoidx = toidx++;
+ tos[newtoidx].here = &data[idx];
+ tos[newtoidx].link = froms[from_index];
+ froms[from_index] = newtoidx;
+ }
+
/* Turn on profiling. */
- param.state = GMON_PROF_ON;
+ state = GMON_PROF_ON;
}
void
_dl_mcount (ElfW(Addr) frompc, ElfW(Addr) selfpc)
{
- if (param.state != GMON_PROF_ON)
+ if (state != GMON_PROF_ON)
return;
- param.state = GMON_PROF_BUSY;
+ state = GMON_PROF_BUSY;
/* Compute relative addresses. The shared object can be loaded at
any address. The value of frompc could be anything. We cannot
restrict it in any way, just set to a fixed value (0) in case it
is outside the allowed range. These calls show up as calls from
<external> in the gprof output. */
- frompc -= param.lowpc;
- if (frompc >= param.textsize)
+ frompc -= lowpc;
+ if (frompc >= textsize)
frompc = 0;
- selfpc -= param.lowpc;
+ selfpc -= lowpc;
+ if (selfpc >= textsize)
+ goto done;
+
- param.state = GMON_PROF_ON;
+ done:
+ state = GMON_PROF_ON;
}