Mark Wielaard [Mon, 22 Jun 2009 14:48:30 +0000 (16:48 +0200)]
PR10307 beginning of statement check should be overridden in guru mode.
* tapsets.cxx (query_cu): When in guru mode just issue an warning (if not
suppressed) instead of an error when address isn't at the beginning of
a statement.
Masami Hiramatsu [Fri, 19 Jun 2009 22:19:52 +0000 (18:19 -0400)]
Fix various issues in initscript (bz506956)
* initscript/systemtap.in: Fix messages.
(clog): Don't strip spaces out.
(parse_args): Parse -y option.
(status): Show message if no scripts are running.
(restart): Don't try to stop scripts if no scripts are running.
Masami Hiramatsu [Fri, 19 Jun 2009 22:19:51 +0000 (18:19 -0400)]
Fix on-file flight recorder mode bugs on old kernel.
* runtime/staprun/common.c (make_outfile_name): Moved from relay.c, fix not to
open /dev/null.XXX output files, and add 'bulk' argument for bulkmode.
* runtime/staprun/relay.c (make_outfile_name): Moved to common.c.
* runtime/staprun/relay_old.c (open_oldoutfile): Fix to use fopen() and store
FILE * to percpu_tmpfile[cpu].
Stan Cox [Fri, 19 Jun 2009 20:13:21 +0000 (16:13 -0400)]
Correctly find probes for -m32 executables.
* sdt.h (STAP_PROBE_DATA_): Pad with 0 so final probe entry doesn't
pickup a stray word.
* sdt_misc.exp (static_user_markers.{c,d}): Add bstruct to test struct
type handling
Revise acquiring of pid and ppid in fork.return probe -- use returnval()
and pid() instead of pid() and ppid() respectively. Add pid removal on
exit syscall. Use dwarfless syscall probe aliases. Correct formatting.
Previous implementation was error-prone, because allowed returning empty
tokens (mimiced strsep()), which is fine if there is a NULL semantic.
Unfortunately SystemTap doesn't provide it in scripts and has only blank
string (""), therefore testing against it was misleading.
The solution is to return only non-empty tokens (mimic strtok()).
* tapset/string.stp: Fix tokenize.
* testsuite/systemtap.string/tokenize.stp: Improve and add case with
more than one delimiter in the delim string.
* testsuite/systemtap.string/tokenize.exp: Ditto.
* stapfuncs.3stap.in: Update tokenize description.
* doc/langref.tex: Ditto.
David Smith [Tue, 16 Jun 2009 17:17:35 +0000 (12:17 -0500)]
Moved time.c inclusion from runtime/transport/transport.c to runtime/runtime.h.
* runtime/runtime.h: Includes time.c.
* runtime/transport/transport.c: Removed time.c inclusion.
Mark Wielaard [Tue, 16 Jun 2009 14:13:25 +0000 (16:13 +0200)]
Add GCC version to testsuite run output and systemtap.sum file.
Prints the gcc being used and full version. Also adds short version
number to systemtap.sum file (plus full version string). Will make
comparing failures based on compiler version being used easier.
* testsuite/lib/systemtap.exp (print_systemtap_version): Also print
location and full version of gcc being used.
(get_system_info): Get gcc version number and long version string.
* testsuite/lib/stap_run.exp (print_system_info): Output GCC version.
Stan Cox [Mon, 15 Jun 2009 16:16:17 +0000 (12:16 -0400)]
Add experimental utrace/kprobe sdt support
* sdt.h (EXPERIMENTAL_UTRACE_SDT, EXPERIMENTAL_KPROBE_SDT): New probe
point macros.
* dtrace: Add support for creating type debug info, currently invoked
with --types.
* tapsets.cxx (probe_table::convert_probe): New.
(probe_table::convert_location): New.
(dwarf_builder::build): Use it to simplify probe point handling.
* sdt.exp (pbtype_flags, pbtype_mssgs): New to also test kprobe and utrace.
* static_uprobes.exp (pbtype_flags, pbtype_mssgs): New to also test kprobe and utrace.
Mark Wielaard [Mon, 15 Jun 2009 15:47:36 +0000 (17:47 +0200)]
PR10285. User space PROBE marks aren't found with separate debuginfo.
The original logic was a little confused. It could end up searching the
separate debuginfo twice instead of falling back to the main elf file.
Now we explicitly search the main elf file first (where the .probes
section really should be) and only then fall back to the separate
debuginfo file.
* tapsets.cxx (dwarf_builder::probe_table::probe_table): Search main
elf file first, then fall back on separate debuginfo file if necessary.
* testsuite/systemtap.exelib/exelib.exp: Enable mark.tcl testcase.
main elf file or the debuginfo file, but would interpret
Mark Wielaard [Mon, 15 Jun 2009 11:37:39 +0000 (13:37 +0200)]
PR10274 Fix exelib -O3 testcase.
The testcase now uses noinline, an empty asm statement and a volatile
variable to prevent the function getting inlined, being totally unrolled
or the recursive call being replaced with an inner-iteration.
This does defeat part of the testcase though, which was testing unwinding
through an optimized recursive function. But it seems the best we can do.
* testsuite/systemtap.exelib/exelib.exp: Add -O3 to the mix.
* testsuite/systemtap.exelib/uprobes_exe.c: Use volatile bar and mark
main_func noinline.
* testsuite/systemtap.exelib/uprobes_lib.c: Use volatile foo and mark
lib_func noinline.
Frank Ch. Eigler [Sat, 13 Jun 2009 22:21:06 +0000 (18:21 -0400)]
PR10279: add -DKRETACTIVE=nnnn parameter
* tapsets.cxx (dwarf/kprobe_derived_...::emit_decl/init): Define
and use KRETPROBE instead of hard-coded max(...) values. Raise
the default 50%.
* testsuite/buildok/thirtytwo.stp: New test.
Mark Wielaard [Fri, 12 Jun 2009 20:37:11 +0000 (22:37 +0200)]
Add exelib uprobes test framework.
Tests uprobes placed in executables and shared libraries on different
arches (32-on-64 currently disabled), gcc/g++, optimizations (currently
disabled), prelinked libs (currently disabled), seperate libs/exe debuginfo
and pie executables.
* testsuite/systemtap.base/uprobes_exe.c: Moved to...
* testsuite/systemtap.exelib/uprobes_exe.c: From systemtap.base.
* testsuite/systemtap.base/uprobes_lib.c: Moved to...
* testsuite/systemtap.exelib/uprobes_lib.c: From systemtap.base.
* testsuite/systemtap.base/uprobes_lib.exp: Rewritten as...
* testsuite/systemtap.exelib/lib.tcl: From uprobes_lib.exp.
* testsuite/systemtap.base/uprobes_lib.stp: Rewritten as...
* testsuite/systemtap.exelib/lib.stp: From uprobes_lib.stp.
* testsuite/systemtap.base/uprobes_uname.exp: Rewritten as...
* testsuite/systemtap.exelib/uname.tcl: From uprobes_uname.exp.
* testsuite/systemtap.base/uprobes_uname.stp: Rewritten as...
* testsuite/systemtap.exelib/uname.stp: From uprobes_uname.stp.
* testsuite/systemtap.base/uprobes_ustack.exp: Rewritten as...
* testsuite/systemtap.exelib/ustack.tcl: From uprobes_ustack.exp.
* testsuite/systemtap.base/uprobes_ustack.stp: Rewritten as...
* testsuite/systemtap.exelib/ustack.stp: From uprobes_ustack.stp.
* testsuite/systemtap.exelib/exelib.exp: New exelib uprobes framework.
* testsuite/systemtap.exelib/cleanup.tcl: New file.
David Smith [Fri, 12 Jun 2009 18:20:57 +0000 (13:20 -0500)]
Fixed non-bulkmode output on smp systems using transport version 2.
* runtime/transport/relay_v2.c (__stp_relay_create_buf_file_callback): Set
the 'is_global' return parameter so that smp systems work correctly.
Dave Brolley [Thu, 11 Jun 2009 15:58:55 +0000 (11:58 -0400)]
Only sign modules if --unprivileged is specified.
Don't generate an error message for unsigned modules.
Make sure module signature exists before attempting to copy to the cache.
Allow timer p[robes for unprivileged users.
Josh Stone [Wed, 10 Jun 2009 22:50:04 +0000 (15:50 -0700)]
PR10260: Clean up all resources after init errors
When anything in systemtap_module_init fails, and we return non-zero,
then the module load is aborted. The normal module unload path
(systemtap_module_exit) is not even attempted, so we need to make sure
that all partially-allocated resources are returned.
Our timer callbacks for the gettimeofday subsystem are a classic example
of this error. If we don't unregister the timers before aborting init,
they will later be called and cause a kernel fault.
We also were neglecting to free the percpu context. A memory leak is
less harmful, but that's fixed now too.
Josh Stone [Wed, 10 Jun 2009 02:58:15 +0000 (19:58 -0700)]
Fix condition propagation across aliases
When an instance of an alias has a condition, that condition gets
propagated to each of the locations that the alias defines. However,
the copy of the location list was not a deep copy, and so all other
instances of the alias would also incorrectly receive the condition.
This patch makes the location list copy a little deeper, and adds a
test case which demonstrates the issue.
Josh Stone [Tue, 9 Jun 2009 23:37:14 +0000 (16:37 -0700)]
Remove the spurious sdt @cast expansion
The result of sdt's private @cast expansion was not being used, and it's
not really needed anyway. The global cast visitor is registered to run
as a post-processing step on ALL functions and probes, and so it will
pick up and expand sdt's casts too.
Stan Cox [Tue, 9 Jun 2009 21:05:53 +0000 (17:05 -0400)]
* tapsets.cxx (sdt_var_expanding_visitor::process_name): New.
(sdt_var_expanding_visitor::visit_target_symbol): Have @cast use
types from a dtrace built object instead of a dtrace supplied header.
(dwarf_builder::build): Use it.
David Smith [Mon, 1 Jun 2009 17:20:08 +0000 (12:20 -0500)]
Avoid holding semaphore while making mmap callbacks.
* runtime/task_finder.c (__stp_call_mmap_callbacks_for_task): Grabs the
'mmap_sem' sempaphore. Caches vma information, releases the semaphore,
then makes mmap callbacks.
(__stp_utrace_task_finder_target_quiesce): Calls
__stp_call_mmap_callbacks_for_task() to make mmap callbacks on initial
attach to a task.
David Smith [Thu, 28 May 2009 15:58:17 +0000 (10:58 -0500)]
Avoid 1 case of holding a semaphore while mmap callbacks are being made.
* runtime/task_finder.c (__stp_call_mmap_callbacks_with_addr): Renamed
from __stp_call_mmap_callbacks_with_vma(). Also added some code from
__stp_utrace_task_finder_target_syscall_exit() that locks the 'mmap_sem'
semaphore. This avoids holding the semaphore while the mmap callbacks
are made.
(__stp_utrace_task_finder_target_syscall_exit): Just calls
__stp_call_mmap_callbacks_with_addr() in the mmap case.
* tapsets.cxx (dwarf_builder::probe_table::probe_table): gcc 4.4
complains that shdr may be used uninitialized. I added returns to
ensure that it's ok, but gcc still complains. Set the thing to NULL
as well to silence the beast.
Stan Cox [Tue, 9 Jun 2009 01:57:44 +0000 (21:57 -0400)]
* tapsets.cxx (probe_table): Make mark_name and sess refs.
(probe_table::get_next_probe): Dissect using struct probe_table.
(sdt_var_expanding_visitor): Use lex_cast.
(dwarf_builder::build): Copy probe and location for TOK_MARK cases.
Call derive_probes for kprobe and utrace cases.
Josh Stone [Mon, 8 Jun 2009 23:37:00 +0000 (16:37 -0700)]
Remove dwflpp::default_name
It was just a basic NULL check, but creating its string temporaries was
causing a fair slowdown. Removing this function and adjusting the
callers shaves ~5% off the syscall.* elaboration time.
Josh Stone [Mon, 8 Jun 2009 22:36:42 +0000 (15:36 -0700)]
Let query_module abort early for simple matches
query_module was already returning DW_CB_ABORT when a simple match was
found, but dwflpp::iterate_over_modules was ignoring that and instead
forcing the module loop to restart. The only way out of the loop was
with the pending_interrupts flag, which is only for signalled
interrupts.
Now iterate_over_modules will only attempt the dwfl_getmodules loop
once, since that loop will only abort if the CB returns DW_CB_ABORT.
Then query_module is also modified to return ABORT if pending_interrupts
is flagged.
My trusty test, stap -l syscall.*, is nearly 2x faster with this change.
Empirically, I found that the kernel object is always the first "module"
returned, so the syscall probepoints always gets to short-circuit the
loop right away.
Josh Stone [Thu, 4 Jun 2009 01:51:30 +0000 (18:51 -0700)]
Fix uninitialized shdr in probe_table
* tapsets.cxx (dwarf_builder::probe_table::probe_table): gcc 4.4
complains that shdr may be used uninitialized. I added returns to
ensure that it's ok, but gcc still complains. Set the thing to NULL
as well to silence the beast.
David Smith [Wed, 3 Jun 2009 20:20:46 +0000 (15:20 -0500)]
Make sure all DEBUG_TRANS output uses printk.
* runtime/transport/control.c (_stp_ctl_write_cmd): Calls dbug_trans2
instead of _dbug (so that printk is used instead of the transport
itself).
(_stp_ctl_write_dbug): Ditto.
* runtime/debug.h (dbug_trans2): New macro.
David Smith [Wed, 3 Jun 2009 18:04:54 +0000 (13:04 -0500)]
Fixed STP_TRANSPORT_VERSION 1 behavior.
* runtime/transport/control.c (_stp_ctl_write_dbug): Added support for
more messages.
* runtime/transport/relay_v2.c (_stp_transport_data_fs_start): New
function.
(_stp_transport_data_fs_stop): Ditto.
(_stp_transport_data_fs_close): Moved some functionality into
_stp_transport_data_fs_stop() and calls _stp_transport_data_fs_stop()
also.
(_stp_transport_data_fs_init): Moved some functionality into
_stp_transport_data_fs_start() and calls _stp_transport_data_fs_start()
also.
* runtime/transport/relayfs.c (_stp_transport_data_fs_start): New
function.
(_stp_transport_data_fs_stop): Ditto.
(_stp_transport_data_fs_close): Moved some functionality into
_stp_transport_data_fs_stop() and calls _stp_transport_data_fs_stop()
also.
(_stp_transport_data_fs_init): Moved some functionality into
_stp_transport_data_fs_start() and calls _stp_transport_data_fs_start()
also.
* runtime/transport/ring_buffer.c (_stp_transport_data_fs_start): New
empty function.
(_stp_transport_data_fs_stop): Ditto.
* runtime/transport/transport.h: Added _stp_transport_data_fs_start() and
_stp_transport_data_fs_stop() prototypes.
* runtime/transport/transport.c (_stp_cleanup_and_exit): Calls
_stp_transport_data_fs_stop().
(_stp_transport_close): Calls _stp_transport_fs_close() earlier.
(_stp_transport_init): Calls _stp_transport_data_fs_start().
git://sourceware.org / systemtap.git / log