mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-23 17:53:37 +08:00
c579f48edb
This patch remove the PID cache and usage in current GLIBC code. Current usage is mainly used a performance optimization to avoid the syscall, however it adds some issues: - The exposed clone syscall will try to set pid/tid to make the new thread somewhat compatible with current GLIBC assumptions. This cause a set of issue with new workloads and usecases (such as BZ#17214 and [1]) as well for new internal usage of clone to optimize other algorithms (such as clone plus CLONE_VM for posix_spawn, BZ#19957). - The caching complexity also added some bugs in the past [2] [3] and requires more effort of each port to handle such requirements (for both clone and vfork implementation). - Caching performance gain in mainly on getpid and some specific code paths. The getpid performance leverage is questionable [4], either by the idea of getpid being a hotspot as for the getpid implementation itself (if it is indeed a justifiable hotspot a vDSO symbol could let to a much more simpler solution). Other usage is mainly for non usual code paths, such as pthread cancellation signal and handling. For thread creation (on stack allocation) the code simplification in fact adds some performance gain due the no need of transverse the stack cache and invalidate each element pid. Other thread usages will require a direct getpid syscall, such as cancellation/setxid signal, thread cancellation, thread fail path (at create_thread), and thread signal (pthread_kill and pthread_sigqueue). However these are hardly usual hotspots and I think adding a syscall is justifiable. It also simplifies both the clone and vfork arch-specific implementation. And by review each fork implementation there are some discrepancies that this patch also solves: - microblaze clone/vfork does not set/reset the pid/tid field - hppa uses the default vfork implementation that fallback to fork. Since vfork is deprecated I do not think we should bother with it. The patch also removes the TID caching in clone. My understanding for such semantic is try provide some pthread usage after a user program issue clone directly (as done by thread creation with CLONE_PARENT_SETTID and pthread tid member). However, as stated before in multiple discussions threads, GLIBC provides clone syscalls without further supporting all this semantics. I ran a full make check on x86_64, x32, i686, armhf, aarch64, and powerpc64le. For sparc32, sparc64, and mips I ran the basic fork and vfork tests from posix/ folder (on a qemu system). So it would require further testing on alpha, hppa, ia64, m68k, nios2, s390, sh, and tile (I excluded microblaze because it is already implementing the patch semantic regarding clone/vfork). [1] https://codereview.chromium.org/800183004/ [2] https://sourceware.org/ml/libc-alpha/2006-07/msg00123.html [3] https://sourceware.org/bugzilla/show_bug.cgi?id=15368 [4] http://yarchive.net/comp/linux/getpid_caching.html * sysdeps/nptl/fork.c (__libc_fork): Remove pid cache setting. * nptl/allocatestack.c (allocate_stack): Likewise. (__reclaim_stacks): Likewise. (setxid_signal_thread): Obtain pid through syscall. * nptl/nptl-init.c (sigcancel_handler): Likewise. (sighandle_setxid): Likewise. * nptl/pthread_cancel.c (pthread_cancel): Likewise. * sysdeps/unix/sysv/linux/pthread_kill.c (__pthread_kill): Likewise. * sysdeps/unix/sysv/linux/pthread_sigqueue.c (pthread_sigqueue): Likewise. * sysdeps/unix/sysv/linux/createthread.c (create_thread): Likewise. * sysdeps/unix/sysv/linux/getpid.c: Remove file. * nptl/descr.h (struct pthread): Change comment about pid value. * nptl/pthread_getattr_np.c (pthread_getattr_np): Remove thread pid assert. * sysdeps/unix/sysv/linux/pthread-pids.h (__pthread_initialize_pids): Do not set pid value. * nptl_db/td_ta_thr_iter.c (iterate_thread_list): Remove thread pid cache check. * nptl_db/td_thr_validate.c (td_thr_validate): Likewise. * sysdeps/aarch64/nptl/tcb-offsets.sym: Remove pid offset. * sysdeps/alpha/nptl/tcb-offsets.sym: Likewise. * sysdeps/arm/nptl/tcb-offsets.sym: Likewise. * sysdeps/hppa/nptl/tcb-offsets.sym: Likewise. * sysdeps/i386/nptl/tcb-offsets.sym: Likewise. * sysdeps/ia64/nptl/tcb-offsets.sym: Likewise. * sysdeps/m68k/nptl/tcb-offsets.sym: Likewise. * sysdeps/microblaze/nptl/tcb-offsets.sym: Likewise. * sysdeps/mips/nptl/tcb-offsets.sym: Likewise. * sysdeps/nios2/nptl/tcb-offsets.sym: Likewise. * sysdeps/powerpc/nptl/tcb-offsets.sym: Likewise. * sysdeps/s390/nptl/tcb-offsets.sym: Likewise. * sysdeps/sh/nptl/tcb-offsets.sym: Likewise. * sysdeps/sparc/nptl/tcb-offsets.sym: Likewise. * sysdeps/tile/nptl/tcb-offsets.sym: Likewise. * sysdeps/x86_64/nptl/tcb-offsets.sym: Likewise. * sysdeps/unix/sysv/linux/aarch64/clone.S: Remove pid and tid caching. * sysdeps/unix/sysv/linux/alpha/clone.S: Likewise. * sysdeps/unix/sysv/linux/arm/clone.S: Likewise. * sysdeps/unix/sysv/linux/hppa/clone.S: Likewise. * sysdeps/unix/sysv/linux/i386/clone.S: Likewise. * sysdeps/unix/sysv/linux/ia64/clone2.S: Likewise. * sysdeps/unix/sysv/linux/mips/clone.S: Likewise. * sysdeps/unix/sysv/linux/nios2/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/clone.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/clone.S: Likewise. * sysdeps/unix/sysv/linux/sh/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/clone.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/clone.S: Likewise. * sysdeps/unix/sysv/linux/tile/clone.S: Likewise. * sysdeps/unix/sysv/linux/x86_64/clone.S: Likewise. * sysdeps/unix/sysv/linux/aarch64/vfork.S: Remove pid set and reset. * sysdeps/unix/sysv/linux/alpha/vfork.S: Likewise. * sysdeps/unix/sysv/linux/arm/vfork.S: Likewise. * sysdeps/unix/sysv/linux/i386/vfork.S: Likewise. * sysdeps/unix/sysv/linux/ia64/vfork.S: Likewise. * sysdeps/unix/sysv/linux/m68k/clone.S: Likewise. * sysdeps/unix/sysv/linux/m68k/vfork.S: Likewise. * sysdeps/unix/sysv/linux/mips/vfork.S: Likewise. * sysdeps/unix/sysv/linux/nios2/vfork.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/vfork.S: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/vfork.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/vfork.S: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/vfork.S: Likewise. * sysdeps/unix/sysv/linux/sh/vfork.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/vfork.S: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/vfork.S: Likewise. * sysdeps/unix/sysv/linux/tile/vfork.S: Likewise. * sysdeps/unix/sysv/linux/x86_64/vfork.S: Likewise. * sysdeps/unix/sysv/linux/tst-clone2.c (f): Remove direct pthread struct access. (clone_test): Remove function. (do_test): Rewrite to take in consideration pid is not cached anymore.
151 lines
4.8 KiB
C
151 lines
4.8 KiB
C
/* Iterate over a process's threads.
|
|
Copyright (C) 1999-2016 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Ulrich Drepper <drepper@redhat.com>, 1999.
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include "thread_dbP.h"
|
|
|
|
|
|
static td_err_e
|
|
iterate_thread_list (td_thragent_t *ta, td_thr_iter_f *callback,
|
|
void *cbdata_p, td_thr_state_e state, int ti_pri,
|
|
psaddr_t head, bool fake_empty, pid_t match_pid)
|
|
{
|
|
td_err_e err;
|
|
psaddr_t next, ofs;
|
|
void *copy;
|
|
|
|
/* Test the state.
|
|
XXX This is incomplete. Normally this test should be in the loop. */
|
|
if (state != TD_THR_ANY_STATE)
|
|
return TD_OK;
|
|
|
|
err = DB_GET_FIELD (next, ta, head, list_t, next, 0);
|
|
if (err != TD_OK)
|
|
return err;
|
|
|
|
if (next == 0 && fake_empty)
|
|
{
|
|
/* __pthread_initialize_minimal has not run. There is just the main
|
|
thread to return. We cannot rely on its thread register. They
|
|
sometimes contain garbage that would confuse us, left by the
|
|
kernel at exec. So if it looks like initialization is incomplete,
|
|
we only fake a special descriptor for the initial thread. */
|
|
td_thrhandle_t th = { ta, 0 };
|
|
return callback (&th, cbdata_p) != 0 ? TD_DBERR : TD_OK;
|
|
}
|
|
|
|
/* Cache the offset from struct pthread to its list_t member. */
|
|
err = DB_GET_FIELD_ADDRESS (ofs, ta, 0, pthread, list, 0);
|
|
if (err != TD_OK)
|
|
return err;
|
|
|
|
if (ta->ta_sizeof_pthread == 0)
|
|
{
|
|
err = _td_check_sizeof (ta, &ta->ta_sizeof_pthread, SYM_SIZEOF_pthread);
|
|
if (err != TD_OK)
|
|
return err;
|
|
}
|
|
copy = __alloca (ta->ta_sizeof_pthread);
|
|
|
|
while (next != head)
|
|
{
|
|
psaddr_t addr, schedpolicy, schedprio;
|
|
|
|
addr = next - (ofs - (psaddr_t) 0);
|
|
if (next == 0 || addr == 0) /* Sanity check. */
|
|
return TD_DBERR;
|
|
|
|
/* Copy the whole descriptor in once so we can access the several
|
|
fields locally. Excess copying in one go is much better than
|
|
multiple ps_pdread calls. */
|
|
if (ps_pdread (ta->ph, addr, copy, ta->ta_sizeof_pthread) != PS_OK)
|
|
return TD_ERR;
|
|
|
|
err = DB_GET_FIELD_LOCAL (schedpolicy, ta, copy, pthread,
|
|
schedpolicy, 0);
|
|
if (err != TD_OK)
|
|
break;
|
|
err = DB_GET_FIELD_LOCAL (schedprio, ta, copy, pthread,
|
|
schedparam_sched_priority, 0);
|
|
if (err != TD_OK)
|
|
break;
|
|
|
|
/* Now test whether this thread matches the specified conditions. */
|
|
|
|
/* Only if the priority level is as high or higher. */
|
|
int descr_pri = ((uintptr_t) schedpolicy == SCHED_OTHER
|
|
? 0 : (uintptr_t) schedprio);
|
|
if (descr_pri >= ti_pri)
|
|
{
|
|
/* Yep, it matches. Call the callback function. */
|
|
td_thrhandle_t th;
|
|
th.th_ta_p = (td_thragent_t *) ta;
|
|
th.th_unique = addr;
|
|
if (callback (&th, cbdata_p) != 0)
|
|
return TD_DBERR;
|
|
}
|
|
|
|
/* Get the pointer to the next element. */
|
|
err = DB_GET_FIELD_LOCAL (next, ta, copy + (ofs - (psaddr_t) 0), list_t,
|
|
next, 0);
|
|
if (err != TD_OK)
|
|
break;
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
|
|
td_err_e
|
|
td_ta_thr_iter (const td_thragent_t *ta_arg, td_thr_iter_f *callback,
|
|
void *cbdata_p, td_thr_state_e state, int ti_pri,
|
|
sigset_t *ti_sigmask_p, unsigned int ti_user_flags)
|
|
{
|
|
td_thragent_t *const ta = (td_thragent_t *) ta_arg;
|
|
td_err_e err;
|
|
psaddr_t list = 0;
|
|
|
|
LOG ("td_ta_thr_iter");
|
|
|
|
/* Test whether the TA parameter is ok. */
|
|
if (! ta_ok (ta))
|
|
return TD_BADTA;
|
|
|
|
/* The thread library keeps two lists for the running threads. One
|
|
list contains the thread which are using user-provided stacks
|
|
(this includes the main thread) and the other includes the
|
|
threads for which the thread library allocated the stacks. We
|
|
have to iterate over both lists separately. We start with the
|
|
list of threads with user-defined stacks. */
|
|
|
|
pid_t pid = ps_getpid (ta->ph);
|
|
err = DB_GET_SYMBOL (list, ta, __stack_user);
|
|
if (err == TD_OK)
|
|
err = iterate_thread_list (ta, callback, cbdata_p, state, ti_pri,
|
|
list, true, pid);
|
|
|
|
/* And the threads with stacks allocated by the implementation. */
|
|
if (err == TD_OK)
|
|
err = DB_GET_SYMBOL (list, ta, stack_used);
|
|
if (err == TD_OK)
|
|
err = iterate_thread_list (ta, callback, cbdata_p, state, ti_pri,
|
|
list, false, pid);
|
|
|
|
return err;
|
|
}
|