freebsd-skq/lib/libkse/thread/thr_info.c

246 lines
7.1 KiB
C
Raw Normal View History

/*
* Copyright (c) 1995-1998 John Birrell <jb@cimlogic.com.au>
* 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.
* 3. Neither the name of the author nor the names of any co-contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY JOHN BIRRELL 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 AUTHOR 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.
*
1999-08-28 00:22:10 +00:00
* $FreeBSD$
*/
2007-11-30 17:20:29 +00:00
#include "namespace.h"
#include <stdio.h>
Implement zero system call thread switching. Performance of thread switches should be on par with that under scheduler activations. o Timing is achieved through the use of a fixed interval timer (ITIMER_PROF) to count scheduling ticks instead of retrieving the time-of-day upon every thread switch and calculating elapsed real time. o Polling for I/O readiness is performed once for each scheduling tick instead of every thread switch. o The non-signal saving/restoring versions of setjmp/longjmp are used to save and restore thread contexts. This may allow the removal of _THREAD_SAFE macros from setjmp() and longjmp() - needs more investigation. Change signal handling so that signals are handled in the context of the thread that is receiving the signal. When signals are dispatched to a thread, a special signal handling frame is created on top of the target threads stack. The frame contains the threads saved state information and a new context in which the thread can run. The applications signal handler is invoked through a wrapper routine that knows how to restore the threads saved state and unwind to previous frames. Fix interruption of threads due to signals. Some states were being improperly interrupted while other states were not being interrupted. This should fix several PRs. Signal handlers, which are invoked as a result of a process signal (not by pthread_kill()), are now called with the code (or siginfo_t if SA_SIGINFO was set in sa_flags) and sigcontext_t as received from the process signal handler. Modify the search for a thread to which a signal is delivered. The search algorithm is now: o First thread found in sigwait() with signal in wait mask. o First thread found sigsuspend()'d on the signal. o Current thread if signal is unmasked. o First thread found with signal unmasked. Collapse machine dependent support into macros defined in pthread_private.h. These should probably eventually be moved into separate MD files. Change the range of settable priorities to be compliant with POSIX (0-31). The threads library uses higher priorities internally for real-time threads (not yet implemented) and threads executing signal handlers. Real-time threads and threads running signal handlers add 64 and 32, respectively, to a threads base priority. Some other small changes and cleanups. PR: 17757 18559 21943 Reviewed by: jasone
2000-10-13 22:12:32 +00:00
#include <stdlib.h>
#include <fcntl.h>
#include <string.h>
#include <unistd.h>
#include <pthread.h>
#include <errno.h>
2007-11-30 17:20:29 +00:00
#include "un-namespace.h"
#include "thr_private.h"
#ifndef NELEMENTS
#define NELEMENTS(arr) (sizeof(arr) / sizeof(arr[0]))
#endif
static void dump_thread(int fd, pthread_t pthread, int long_version);
2007-11-30 17:20:29 +00:00
void _pthread_set_name_np(pthread_t thread, char *name);
__weak_reference(_pthread_set_name_np, pthread_set_name_np);
struct s_thread_info {
enum pthread_state state;
2007-11-30 17:20:29 +00:00
const char *name;
};
/* Static variables: */
static const struct s_thread_info thread_info[] = {
{PS_RUNNING , "Running"},
{PS_LOCKWAIT , "Waiting on an internal lock"},
{PS_MUTEX_WAIT , "Waiting on a mutex"},
{PS_COND_WAIT , "Waiting on a condition variable"},
{PS_SLEEP_WAIT , "Sleeping"},
{PS_SIGSUSPEND , "Suspended, waiting for a signal"},
{PS_SIGWAIT , "Waiting for a signal"},
{PS_JOIN , "Waiting to join"},
{PS_SUSPENDED , "Suspended"},
{PS_DEAD , "Dead"},
[ The author's description... ] o Runnable threads are now maintained in priority queues. The implementation requires two things: 1.) The priority queues must be protected during insertion and removal of threads. Since the kernel scheduler must modify the priority queues, a spinlock for protection cannot be used. The functions _thread_kern_sched_defer() and _thread_kern_sched_undefer() were added to {un}defer kernel scheduler activation. 2.) A thread (active) priority change can be performed only when the thread is removed from the priority queue. The implementation uses a threads active priority when inserting it into the queue. A by-product is that thread switches are much faster. A separate queue is used for waiting and/or blocked threads, and it is searched at most 2 times in the kernel scheduler when there are active threads. It should be possible to reduce this to once by combining polling of threads waiting on I/O with the loop that looks for timed out threads and the minimum timeout value. o Functions to defer kernel scheduler activation were added. These are _thread_kern_sched_defer() and _thread_kern_sched_undefer() and may be called recursively. These routines do not block the scheduling signal, but latch its occurrence. The signal handler will not call the kernel scheduler when the running thread has deferred scheduling, but it will be called when running thread undefers scheduling. o Added support for _POSIX_THREAD_PRIORITY_SCHEDULING. All the POSIX routines required by this should now be implemented. One note, SCHED_OTHER, SCHED_FIFO, and SCHED_RR are required to be defined by including pthread.h. These defines are currently in sched.h. I modified pthread.h to include sched.h but don't know if this is the proper thing to do. o Added support for priority protection and inheritence mutexes. This allows definition of _POSIX_THREAD_PRIO_PROTECT and _POSIX_THREAD_PRIO_INHERIT. o Added additional error checks required by POSIX for mutexes and condition variables. o Provided a wrapper for sigpending which is marked as a hidden syscall. o Added a non-portable function as a debugging aid to allow an application to monitor thread context switches. An application can install a routine that gets called everytime a thread (explicitly created by the application) gets context switched. The routine gets passed the pthread IDs of the threads that are being switched in and out. Submitted by: Dan Eischen <eischen@vigrid.com> Changes by me: o Added a PS_SPINBLOCK state to deal with the priority inversion problem most often (I think) seen by threads calling malloc/free/realloc. o Dispatch signals to the running thread directly rather than at a context switch to avoid the situation where the switch never occurs.
1999-03-23 05:07:56 +00:00
{PS_DEADLOCK , "Deadlocked"},
{PS_STATE_MAX , "Not a real state!"}
};
void
_thread_dump_info(void)
{
2007-11-30 17:20:29 +00:00
char s[512], tempfile[128];
pthread_t pthread;
int fd, i;
for (i = 0; i < 100000; i++) {
2007-11-30 17:20:29 +00:00
snprintf(tempfile, sizeof(tempfile), "/tmp/pthread.dump.%u.%i",
getpid(), i);
/* Open the dump file for append and create it if necessary: */
2007-11-30 17:20:29 +00:00
if ((fd = __sys_open(tempfile, O_RDWR | O_CREAT | O_EXCL,
0666)) < 0) {
/* Can't open the dump file. */
if (errno == EEXIST)
continue;
/*
* We only need to continue in case of
* EEXIT error. Most other error
* codes means that we will fail all
* the times.
*/
return;
} else {
break;
}
}
if (i==100000) {
/* all 100000 possibilities are in use :( */
return;
} else {
/* Dump the active threads. */
strcpy(s, "\n\n========\nACTIVE THREADS\n\n");
__sys_write(fd, s, strlen(s));
/* Enter a loop to report each thread in the global list: */
In the words of the author: o The polling mechanism for I/O readiness was changed from select() to poll(). In additon, a wrapped version of poll() is now provided. o The wrapped select routine now converts each fd_set to a poll array so that the thread scheduler doesn't have to perform a bitwise search for selected fds each time file descriptors are polled for I/O readiness. o The thread scheduler was modified to use a new queue (_workq) for threads that need work. Threads waiting for I/O readiness and spinblocks are added to the work queue in addition to the waiting queue. This reduces the time spent forming/searching the array of file descriptors being polled. o The waiting queue (_waitingq) is now maintained in order of thread wakeup time. This allows the thread scheduler to find the nearest wakeup time by looking at the first thread in the queue instead of searching the entire queue. o Removed file descriptor locking for select/poll routines. An application should not rely on the threads library for providing this locking; if necessary, the application should use mutexes to protect selecting/polling of file descriptors. o Retrieve and use the kernel clock rate/resolution at startup instead of hardcoding the clock resolution to 10 msec (tested with kernel running at 1000 HZ). o All queues have been changed to use queue.h macros. These include the queues of all threads, dead threads, and threads waiting for file descriptor locks. o Added reinitialization of the GC mutex and condition variable after a fork. Also prevented reallocation of the ready queue after a fork. o Prevented the wrapped close routine from closing the thread kernel pipes. o Initialized file descriptor table for stdio entries at thread init. o Provided additional flags to indicate to what queues threads belong. o Moved TAILQ initialization for statically allocated mutex and condition variables to after the spinlock. o Added dispatching of signals to pthread_kill. Removing the dispatching of signals from thread activation broke sigsuspend when pthread_kill was used to send a signal to a thread. o Temporarily set the state of a thread to PS_SUSPENDED when it is first created and placed in the list of threads so that it will not be accidentally scheduled before becoming a member of one of the scheduling queues. o Change the signal handler to queue signals to the thread kernel pipe if the scheduling queues are protected. When scheduling queues are unprotected, signals are then dequeued and handled. o Ensured that all installed signal handlers block the scheduling signal and that the scheduling signal handler blocks all other signals. This ensures that the signal handler is only interruptible for and by non-scheduling signals. An atomic lock is used to decide which instance of the signal handler will handle pending signals. o Removed _lock_thread_list and _unlock_thread_list as they are no longer used to protect the thread list. o Added missing RCS IDs to modified files. o Added checks for appropriate queue membership and activity when adding, removing, and searching the scheduling queues. These checks add very little overhead and are enabled when compiled with _PTHREADS_INVARIANTS defined. Suggested and implemented by Tor Egge with some modification by me. o Close a race condition in uthread_close. (Tor Egge) o Protect the scheduling queues while modifying them in pthread_cond_signal and _thread_fd_unlock. (Tor Egge) o Ensure that when a thread gets a mutex, the mutex is on that threads list of owned mutexes. (Tor Egge) o Set the kernel-in-scheduler flag in _thread_kern_sched_state and _thread_kern_sched_state_unlock to prevent a scheduling signal from calling the scheduler again. (Tor Egge) o Don't use TAILQ_FOREACH macro while searching the waiting queue for threads in a sigwait state, because a change of state destroys the TAILQ link. It is actually safe to do so, though, because once a sigwaiting thread is found, the loop ends and the function returns. (Tor Egge) o When dispatching signals to threads, make the thread inherit the signal deferral flag of the currently running thread. (Tor Egge) Submitted by: Daniel Eischen <eischen@vigrid.com> and Tor Egge <Tor.Egge@fast.no>
1999-06-20 08:28:48 +00:00
TAILQ_FOREACH(pthread, &_thread_list, tle) {
if (pthread->state != PS_DEAD)
dump_thread(fd, pthread, /*long_verson*/ 1);
}
/*
* Dump the ready threads.
* XXX - We can't easily do this because the run queues
* are per-KSEG.
*/
strcpy(s, "\n\n========\nREADY THREADS - unimplemented\n\n");
__sys_write(fd, s, strlen(s));
[ The author's description... ] o Runnable threads are now maintained in priority queues. The implementation requires two things: 1.) The priority queues must be protected during insertion and removal of threads. Since the kernel scheduler must modify the priority queues, a spinlock for protection cannot be used. The functions _thread_kern_sched_defer() and _thread_kern_sched_undefer() were added to {un}defer kernel scheduler activation. 2.) A thread (active) priority change can be performed only when the thread is removed from the priority queue. The implementation uses a threads active priority when inserting it into the queue. A by-product is that thread switches are much faster. A separate queue is used for waiting and/or blocked threads, and it is searched at most 2 times in the kernel scheduler when there are active threads. It should be possible to reduce this to once by combining polling of threads waiting on I/O with the loop that looks for timed out threads and the minimum timeout value. o Functions to defer kernel scheduler activation were added. These are _thread_kern_sched_defer() and _thread_kern_sched_undefer() and may be called recursively. These routines do not block the scheduling signal, but latch its occurrence. The signal handler will not call the kernel scheduler when the running thread has deferred scheduling, but it will be called when running thread undefers scheduling. o Added support for _POSIX_THREAD_PRIORITY_SCHEDULING. All the POSIX routines required by this should now be implemented. One note, SCHED_OTHER, SCHED_FIFO, and SCHED_RR are required to be defined by including pthread.h. These defines are currently in sched.h. I modified pthread.h to include sched.h but don't know if this is the proper thing to do. o Added support for priority protection and inheritence mutexes. This allows definition of _POSIX_THREAD_PRIO_PROTECT and _POSIX_THREAD_PRIO_INHERIT. o Added additional error checks required by POSIX for mutexes and condition variables. o Provided a wrapper for sigpending which is marked as a hidden syscall. o Added a non-portable function as a debugging aid to allow an application to monitor thread context switches. An application can install a routine that gets called everytime a thread (explicitly created by the application) gets context switched. The routine gets passed the pthread IDs of the threads that are being switched in and out. Submitted by: Dan Eischen <eischen@vigrid.com> Changes by me: o Added a PS_SPINBLOCK state to deal with the priority inversion problem most often (I think) seen by threads calling malloc/free/realloc. o Dispatch signals to the running thread directly rather than at a context switch to avoid the situation where the switch never occurs.
1999-03-23 05:07:56 +00:00
/*
* Dump the waiting threads.
* XXX - We can't easily do this because the wait queues
* are per-KSEG.
*/
strcpy(s, "\n\n========\nWAITING THREADS - unimplemented\n\n");
__sys_write(fd, s, strlen(s));
In the words of the author: o The polling mechanism for I/O readiness was changed from select() to poll(). In additon, a wrapped version of poll() is now provided. o The wrapped select routine now converts each fd_set to a poll array so that the thread scheduler doesn't have to perform a bitwise search for selected fds each time file descriptors are polled for I/O readiness. o The thread scheduler was modified to use a new queue (_workq) for threads that need work. Threads waiting for I/O readiness and spinblocks are added to the work queue in addition to the waiting queue. This reduces the time spent forming/searching the array of file descriptors being polled. o The waiting queue (_waitingq) is now maintained in order of thread wakeup time. This allows the thread scheduler to find the nearest wakeup time by looking at the first thread in the queue instead of searching the entire queue. o Removed file descriptor locking for select/poll routines. An application should not rely on the threads library for providing this locking; if necessary, the application should use mutexes to protect selecting/polling of file descriptors. o Retrieve and use the kernel clock rate/resolution at startup instead of hardcoding the clock resolution to 10 msec (tested with kernel running at 1000 HZ). o All queues have been changed to use queue.h macros. These include the queues of all threads, dead threads, and threads waiting for file descriptor locks. o Added reinitialization of the GC mutex and condition variable after a fork. Also prevented reallocation of the ready queue after a fork. o Prevented the wrapped close routine from closing the thread kernel pipes. o Initialized file descriptor table for stdio entries at thread init. o Provided additional flags to indicate to what queues threads belong. o Moved TAILQ initialization for statically allocated mutex and condition variables to after the spinlock. o Added dispatching of signals to pthread_kill. Removing the dispatching of signals from thread activation broke sigsuspend when pthread_kill was used to send a signal to a thread. o Temporarily set the state of a thread to PS_SUSPENDED when it is first created and placed in the list of threads so that it will not be accidentally scheduled before becoming a member of one of the scheduling queues. o Change the signal handler to queue signals to the thread kernel pipe if the scheduling queues are protected. When scheduling queues are unprotected, signals are then dequeued and handled. o Ensured that all installed signal handlers block the scheduling signal and that the scheduling signal handler blocks all other signals. This ensures that the signal handler is only interruptible for and by non-scheduling signals. An atomic lock is used to decide which instance of the signal handler will handle pending signals. o Removed _lock_thread_list and _unlock_thread_list as they are no longer used to protect the thread list. o Added missing RCS IDs to modified files. o Added checks for appropriate queue membership and activity when adding, removing, and searching the scheduling queues. These checks add very little overhead and are enabled when compiled with _PTHREADS_INVARIANTS defined. Suggested and implemented by Tor Egge with some modification by me. o Close a race condition in uthread_close. (Tor Egge) o Protect the scheduling queues while modifying them in pthread_cond_signal and _thread_fd_unlock. (Tor Egge) o Ensure that when a thread gets a mutex, the mutex is on that threads list of owned mutexes. (Tor Egge) o Set the kernel-in-scheduler flag in _thread_kern_sched_state and _thread_kern_sched_state_unlock to prevent a scheduling signal from calling the scheduler again. (Tor Egge) o Don't use TAILQ_FOREACH macro while searching the waiting queue for threads in a sigwait state, because a change of state destroys the TAILQ link. It is actually safe to do so, though, because once a sigwaiting thread is found, the loop ends and the function returns. (Tor Egge) o When dispatching signals to threads, make the thread inherit the signal deferral flag of the currently running thread. (Tor Egge) Submitted by: Daniel Eischen <eischen@vigrid.com> and Tor Egge <Tor.Egge@fast.no>
1999-06-20 08:28:48 +00:00
/* Close the dump file. */
__sys_close(fd);
}
}
static void
dump_thread(int fd, pthread_t pthread, int long_version)
{
struct pthread *curthread = _get_curthread();
char s[512];
int i;
/* Find the state: */
2007-11-30 17:20:29 +00:00
for (i = 0; i < (int)NELEMENTS(thread_info) - 1; i++)
if (thread_info[i].state == pthread->state)
break;
/* Output a record for the thread: */
snprintf(s, sizeof(s),
"--------------------\n"
"Thread %p (%s), scope %s, prio %3d, blocked %s, state %s [%s:%d]\n",
pthread, (pthread->name == NULL) ? "" : pthread->name,
pthread->attr.flags & PTHREAD_SCOPE_SYSTEM ? "system" : "process",
pthread->active_priority, (pthread->blocked != 0) ? "yes" : "no",
thread_info[i].name, pthread->fname, pthread->lineno);
__sys_write(fd, s, strlen(s));
if (long_version != 0) {
/* Check if this is the running thread: */
if (pthread == curthread) {
/* Output a record for the running thread: */
strcpy(s, "This is the running thread\n");
__sys_write(fd, s, strlen(s));
}
/* Check if this is the initial thread: */
if (pthread == _thr_initial) {
/* Output a record for the initial thread: */
strcpy(s, "This is the initial thread\n");
__sys_write(fd, s, strlen(s));
}
/* Process according to thread state: */
switch (pthread->state) {
case PS_SIGWAIT:
snprintf(s, sizeof(s), "sigmask (hi) ");
__sys_write(fd, s, strlen(s));
for (i = _SIG_WORDS - 1; i >= 0; i--) {
snprintf(s, sizeof(s), "%08x ",
pthread->sigmask.__bits[i]);
__sys_write(fd, s, strlen(s));
}
snprintf(s, sizeof(s), "(lo)\n");
__sys_write(fd, s, strlen(s));
snprintf(s, sizeof(s), "waitset (hi) ");
o Use a daemon thread to monitor signal events in kernel, if pending signals were changed in kernel, it will retrieve the pending set and try to find a thread to dispatch the signal. The dispatching process can be rolled back if the signal is no longer in kernel. o Create two functions _thr_signal_init() and _thr_signal_deinit(), all signal action settings are retrieved from kernel when threading mode is turned on, after a fork(), child process will reset them to user settings by calling _thr_signal_deinit(). when threading mode is not turned on, all signal operations are direct past to kernel. o When a thread generated a synchoronous signals and its context returned from completed list, UTS will retrieve the signal from its mailbox and try to deliver the signal to thread. o Context signal mask is now only used when delivering signals, thread's current signal mask is always the one in pthread structure. o Remove have_signals field in pthread structure, replace it with psf_valid in pthread_signal_frame. when psf_valid is true, in context switch time, thread will backout itself from some mutex/condition internal queues, then begin to process signals. when a thread is not at blocked state and running, check_pending indicates there are signals for the thread, after preempted and then resumed time, UTS will try to deliver signals to the thread. o At signal delivering time, not only pending signals in thread will be scanned, process's pending signals will be scanned too. o Change sigwait code a bit, remove field sigwait in pthread_wait_data, replace it with oldsigmask in pthread structure, when a thread calls sigwait(), its current signal mask is backuped to oldsigmask, and waitset is copied to its signal mask and when the thread gets a signal in the waitset range, its current signal mask is restored from oldsigmask, these are done in atomic fashion. o Two additional POSIX APIs are implemented, sigwaitinfo() and sigtimedwait(). o Signal code locking is better than previous, there is fewer race conditions. o Temporary disable most of code in _kse_single_thread as it is not safe after fork().
2003-06-28 09:55:02 +00:00
__sys_write(fd, s, strlen(s));
for (i = _SIG_WORDS - 1; i >= 0; i--) {
snprintf(s, sizeof(s), "%08x ",
2003-09-22 00:40:23 +00:00
pthread->data.sigwait->waitset->__bits[i]);
__sys_write(fd, s, strlen(s));
}
snprintf(s, sizeof(s), "(lo)\n");
__sys_write(fd, s, strlen(s));
break;
/*
* Trap other states that are not explicitly
* coded to dump information:
*/
default:
snprintf(s, sizeof(s), "sigmask (hi) ");
__sys_write(fd, s, strlen(s));
for (i = _SIG_WORDS - 1; i >= 0; i--) {
snprintf(s, sizeof(s), "%08x ",
pthread->sigmask.__bits[i]);
__sys_write(fd, s, strlen(s));
}
snprintf(s, sizeof(s), "(lo)\n");
__sys_write(fd, s, strlen(s));
break;
}
}
}
/* Set the thread name for debug: */
void
_pthread_set_name_np(pthread_t thread, char *name)
{
struct pthread *curthread = _get_curthread();
char *new_name;
char *prev_name;
int ret;
new_name = strdup(name);
/* Add a reference to the target thread. */
if (_thr_ref_add(curthread, thread, 0) != 0) {
free(new_name);
ret = ESRCH;
}
else {
THR_THREAD_LOCK(curthread, thread);
prev_name = thread->name;
thread->name = new_name;
THR_THREAD_UNLOCK(curthread, thread);
_thr_ref_delete(curthread, thread);
if (prev_name != NULL) {
/* Free space for previous name. */
free(prev_name);
}
ret = 0;
}
#if 0
/* XXX - Should return error code. */
return (ret);
#endif
}