This is the mail archive of the
gdb-patches@sourceware.org
mailing list for the GDB project.
Re: [non-stop] 08/10 linux native support
A Thursday 10 July 2008 20:58:55, Daniel Jacobowitz wrote:
> Right. Could you try this version?
Thanks!
> Basically the same as your previous posting, except that I moved the
> logic assuring we find the first thread when we find the first child
> into the thread-db layer.
Then, this patch cleaned it up a bit further. Basically, it gets
rid of the find_lwp_pid call in thread_db_find_new_threads. Instead
I'm using ALL_LWPS, which is already exported. This gets rid
of the find_lwp_pid -> linux_nat_lwp_pid rename throughout, and
removes the need for thread_db_find_new_threads_1. I then
reimported a couple of comments and cleanups that were on
the last patch, since you had picked up the previous-to-last.
Otherwise, the logic is the same.
Regtested on x86_64-unknown-linux-gnu.
OK?
--
Pedro Alves
2008-07-10 Pedro Alves <pedro@codesourcery.com>
Non-stop linux native.
* linux-nat.c (linux_test_for_tracefork): Block events while we're
here.
(find_lwp_pid): Rename to...
(linux_nat_find_lwp_pid): ... this. Make public. Update all
callers.
(get_pending_status): Implement non-stop mode.
(linux_nat_detach): Stop threads before detaching.
(linux_nat_resume): In non-stop mode, always resume only a single
PTID.
(linux_handle_extended_wait): On a clone event, in non-stop mode,
add new lwp to GDB's thread table, and mark as running, executing
and stopped appropriately.
(linux_nat_filter_event): Don't assume there are other running
threads when a thread exits.
(linux_nat_wait): Mark the main thread as running and executing.
In non-stop mode, don't stop all lwps.
(linux_nat_kill): Stop lwps before killing them.
(linux_nat_thread_alive): Use signal 0 to detect if a thread is
alive.
(send_sigint_callback): New.
(linux_nat_stop): New.
(linux_nat_add_target): Set to_stop to linux_nat_stop.
* linux-nat.h (thread_db_attach_lwp): Declare.
* linux-thread-db.c (thread_get_info_callback): Check for new
threads if we have none.
(thread_from_lwp, enable_thread_event): Set proc_handle.pid to the
stopped lwp. Check for new threads if we have none.
(thread_db_attach_lwp): New.
(thread_db_init): Set proc_handle.pid to inferior_ptid.
(check_event): Set proc_handle.pid to the stopped lwp.
(thread_db_find_new_threads): Set proc_handle.pid to any stopped
lwp available, bail out if there is none.
* linux-fork.c (linux_fork_killall): Use SIGKILL instead of
PTRACE_KILL.
---
gdb/linux-fork.c | 4
gdb/linux-nat.c | 246 ++++++++++++++++++++++++++++++++++++++++----------
gdb/linux-nat.h | 2
gdb/linux-thread-db.c | 77 +++++++++++++++
4 files changed, 282 insertions(+), 47 deletions(-)
Index: src/gdb/linux-nat.c
===================================================================
--- src.orig/gdb/linux-nat.c 2008-07-10 22:14:19.000000000 +0100
+++ src/gdb/linux-nat.c 2008-07-10 22:19:40.000000000 +0100
@@ -285,6 +285,9 @@ static void linux_nat_async (void (*call
static int linux_nat_async_mask (int mask);
static int kill_lwp (int lwpid, int signo);
+static int send_sigint_callback (struct lwp_info *lp, void *data);
+static int stop_callback (struct lwp_info *lp, void *data);
+
/* Captures the result of a successful waitpid call, along with the
options used in that call. */
struct waitpid_result
@@ -487,6 +490,9 @@ linux_test_for_tracefork (int original_p
{
int child_pid, ret, status;
long second_pid;
+ enum sigchld_state async_events_original_state;
+
+ async_events_original_state = linux_nat_async_events (sigchld_sync);
linux_supports_tracefork_flag = 0;
linux_supports_tracevforkdone_flag = 0;
@@ -517,6 +523,7 @@ linux_test_for_tracefork (int original_p
if (ret != 0)
{
warning (_("linux_test_for_tracefork: failed to kill child"));
+ linux_nat_async_events (async_events_original_state);
return;
}
@@ -527,6 +534,7 @@ linux_test_for_tracefork (int original_p
warning (_("linux_test_for_tracefork: unexpected wait status 0x%x from "
"killed child"), status);
+ linux_nat_async_events (async_events_original_state);
return;
}
@@ -566,6 +574,8 @@ linux_test_for_tracefork (int original_p
if (ret != 0)
warning (_("linux_test_for_tracefork: failed to kill child"));
my_waitpid (child_pid, &status, 0);
+
+ linux_nat_async_events (async_events_original_state);
}
/* Return non-zero iff we have tracefork functionality available.
@@ -1376,16 +1386,80 @@ get_pending_status (struct lwp_info *lp,
events are always cached in waitpid_queue. */
*status = 0;
- if (GET_LWP (lp->ptid) == GET_LWP (last_ptid))
+
+ if (non_stop)
{
- if (stop_signal != TARGET_SIGNAL_0
- && signal_pass_state (stop_signal))
- *status = W_STOPCODE (target_signal_to_host (stop_signal));
+ enum target_signal signo = TARGET_SIGNAL_0;
+
+ if (is_executing (lp->ptid))
+ {
+ /* If the core thought this lwp was executing --- e.g., the
+ executing property hasn't been updated yet, but the
+ thread has been stopped with a stop_callback /
+ stop_wait_callback sequence (see linux_nat_detach for
+ example) --- we can only have pending events in the local
+ queue. */
+ if (queued_waitpid (GET_LWP (lp->ptid), status, __WALL) != -1)
+ {
+ if (WIFSTOPPED (status))
+ signo = target_signal_from_host (WSTOPSIG (status));
+
+ /* If not stopped, then the lwp is gone, no use in
+ resending a signal. */
+ }
+ }
+ else
+ {
+ /* If the core knows the thread is not executing, then we
+ have the last signal recorded in
+ thread_info->stop_signal, unless this is inferior_ptid,
+ in which case, it's in the global stop_signal, due to
+ context switching. */
+
+ if (ptid_equal (lp->ptid, inferior_ptid))
+ signo = stop_signal;
+ else
+ {
+ struct thread_info *tp = find_thread_pid (lp->ptid);
+ gdb_assert (tp);
+ signo = tp->stop_signal;
+ }
+ }
+
+ if (signo != TARGET_SIGNAL_0
+ && !signal_pass_state (signo))
+ {
+ if (debug_linux_nat)
+ fprintf_unfiltered (gdb_stdlog, "\
+GPT: lwp %s had signal %s, but it is in no pass state\n",
+ target_pid_to_str (lp->ptid),
+ target_signal_to_string (signo));
+ }
+ else
+ {
+ if (signo != TARGET_SIGNAL_0)
+ *status = W_STOPCODE (target_signal_to_host (signo));
+
+ if (debug_linux_nat)
+ fprintf_unfiltered (gdb_stdlog,
+ "GPT: lwp %s as pending signal %s\n",
+ target_pid_to_str (lp->ptid),
+ target_signal_to_string (signo));
+ }
}
- else if (target_can_async_p ())
- queued_waitpid (GET_LWP (lp->ptid), status, __WALL);
else
- *status = lp->status;
+ {
+ if (GET_LWP (lp->ptid) == GET_LWP (last_ptid))
+ {
+ if (stop_signal != TARGET_SIGNAL_0
+ && signal_pass_state (stop_signal))
+ *status = W_STOPCODE (target_signal_to_host (stop_signal));
+ }
+ else if (target_can_async_p ())
+ queued_waitpid (GET_LWP (lp->ptid), status, __WALL);
+ else
+ *status = lp->status;
+ }
return 0;
}
@@ -1449,6 +1523,13 @@ linux_nat_detach (char *args, int from_t
if (target_can_async_p ())
linux_nat_async (NULL, 0);
+ /* Stop all threads before detaching. ptrace requires that the
+ thread is stopped to sucessfully detach. */
+ iterate_over_lwps (stop_callback, NULL);
+ /* ... and wait until all of them have reported back that
+ they're no longer running. */
+ iterate_over_lwps (stop_wait_callback, NULL);
+
iterate_over_lwps (detach_callback, NULL);
/* Only the initial process should be left right now. */
@@ -1538,10 +1619,17 @@ linux_nat_resume (ptid_t ptid, int step,
/* A specific PTID means `step only this process id'. */
resume_all = (PIDGET (ptid) == -1);
- if (resume_all)
- iterate_over_lwps (resume_set_callback, NULL);
- else
- iterate_over_lwps (resume_clear_callback, NULL);
+ if (non_stop && resume_all)
+ internal_error (__FILE__, __LINE__,
+ "can't resume all in non-stop mode");
+
+ if (!non_stop)
+ {
+ if (resume_all)
+ iterate_over_lwps (resume_set_callback, NULL);
+ else
+ iterate_over_lwps (resume_clear_callback, NULL);
+ }
/* If PID is -1, it's the current inferior that should be
handled specially. */
@@ -1551,6 +1639,7 @@ linux_nat_resume (ptid_t ptid, int step,
lp = find_lwp_pid (ptid);
gdb_assert (lp != NULL);
+ /* Convert to something the lower layer understands. */
ptid = pid_to_ptid (GET_LWP (lp->ptid));
/* Remember if we're stepping. */
@@ -1701,9 +1790,12 @@ linux_handle_extended_wait (struct lwp_i
ourstatus->kind = TARGET_WAITKIND_VFORKED;
else
{
+ struct cleanup *old_chain;
+
ourstatus->kind = TARGET_WAITKIND_IGNORE;
new_lp = add_lwp (BUILD_LWP (new_pid, GET_PID (inferior_ptid)));
new_lp->cloned = 1;
+ new_lp->stopped = 1;
if (WSTOPSIG (status) != SIGSTOP)
{
@@ -1720,13 +1812,38 @@ linux_handle_extended_wait (struct lwp_i
else
status = 0;
- if (stopping)
- new_lp->stopped = 1;
- else
+ if (non_stop)
+ {
+ /* Add the new thread to GDB's lists as soon as possible
+ so that:
+
+ 1) the frontend doesn't have to wait for a stop to
+ display them, and,
+
+ 2) we tag it with the correct running state. */
+
+ /* If the thread_db layer is active, let it know about
+ this new thread, and add it to GDB's list. */
+ if (!thread_db_attach_lwp (new_lp->ptid))
+ {
+ /* We're not using thread_db. Add it to GDB's
+ list. */
+ target_post_attach (GET_LWP (new_lp->ptid));
+ add_thread (new_lp->ptid);
+ }
+
+ if (!stopping)
+ {
+ set_running (new_lp->ptid, 1);
+ set_executing (new_lp->ptid, 1);
+ }
+ }
+
+ if (!stopping)
{
+ new_lp->stopped = 0;
new_lp->resumed = 1;
- ptrace (PTRACE_CONT,
- PIDGET (lp->waitstatus.value.related_pid), 0,
+ ptrace (PTRACE_CONT, new_pid, 0,
status ? WSTOPSIG (status) : 0);
}
@@ -2463,13 +2580,7 @@ linux_nat_filter_event (int lwpid, int s
not the end of the debugged application and should be
ignored. */
if (num_lwps > 0)
- {
- /* Make sure there is at least one thread running. */
- gdb_assert (iterate_over_lwps (running_callback, NULL));
-
- /* Discard the event. */
- return NULL;
- }
+ return NULL;
}
/* Check if the current LWP has previously exited. In the nptl
@@ -2599,6 +2710,8 @@ linux_nat_wait (ptid_t ptid, struct targ
lp->resumed = 1;
/* Add the main thread to GDB's thread list. */
add_thread_silent (lp->ptid);
+ set_running (lp->ptid, 1);
+ set_executing (lp->ptid, 1);
}
sigemptyset (&flush_mask);
@@ -2826,19 +2939,23 @@ retry:
fprintf_unfiltered (gdb_stdlog, "LLW: Candidate event %s in %s.\n",
status_to_str (status), target_pid_to_str (lp->ptid));
- /* Now stop all other LWP's ... */
- iterate_over_lwps (stop_callback, NULL);
+ if (!non_stop)
+ {
+ /* Now stop all other LWP's ... */
+ iterate_over_lwps (stop_callback, NULL);
- /* ... and wait until all of them have reported back that they're no
- longer running. */
- iterate_over_lwps (stop_wait_callback, &flush_mask);
- iterate_over_lwps (flush_callback, &flush_mask);
-
- /* If we're not waiting for a specific LWP, choose an event LWP from
- among those that have had events. Giving equal priority to all
- LWPs that have had events helps prevent starvation. */
- if (pid == -1)
- select_event_lwp (&lp, &status);
+ /* ... and wait until all of them have reported back that
+ they're no longer running. */
+ iterate_over_lwps (stop_wait_callback, &flush_mask);
+ iterate_over_lwps (flush_callback, &flush_mask);
+
+ /* If we're not waiting for a specific LWP, choose an event LWP
+ from among those that have had events. Giving equal priority
+ to all LWPs that have had events helps prevent
+ starvation. */
+ if (pid == -1)
+ select_event_lwp (&lp, &status);
+ }
/* Now that we've selected our final event LWP, cancel any
breakpoints in other LWPs that have hit a GDB breakpoint. See
@@ -2970,6 +3087,13 @@ linux_nat_kill (void)
}
else
{
+ /* Stop all threads before killing them, since ptrace requires
+ that the thread is stopped to sucessfully PTRACE_KILL. */
+ iterate_over_lwps (stop_callback, NULL);
+ /* ... and wait until all of them have reported back that
+ they're no longer running. */
+ iterate_over_lwps (stop_wait_callback, NULL);
+
/* Kill all LWP's ... */
iterate_over_lwps (kill_callback, NULL);
@@ -3022,22 +3146,22 @@ linux_nat_xfer_partial (struct target_op
static int
linux_nat_thread_alive (ptid_t ptid)
{
+ int err;
+
gdb_assert (is_lwp (ptid));
- errno = 0;
- ptrace (PTRACE_PEEKUSER, GET_LWP (ptid), 0, 0);
+ /* Send signal 0 instead of anything ptrace, because ptracing a
+ running thread errors out claiming that the thread doesn't
+ exist. */
+ err = kill_lwp (GET_LWP (ptid), 0);
+
if (debug_linux_nat)
fprintf_unfiltered (gdb_stdlog,
- "LLTA: PTRACE_PEEKUSER %s, 0, 0 (%s)\n",
+ "LLTA: KILL(SIG0) %s (%s)\n",
target_pid_to_str (ptid),
- errno ? safe_strerror (errno) : "OK");
+ err ? safe_strerror (err) : "OK");
- /* Not every Linux kernel implements PTRACE_PEEKUSER. But we can
- handle that case gracefully since ptrace will first do a lookup
- for the process based upon the passed-in pid. If that fails we
- will get either -ESRCH or -EPERM, otherwise the child exists and
- is alive. */
- if (errno == ESRCH || errno == EPERM)
+ if (err != 0)
return 0;
return 1;
@@ -4239,6 +4363,35 @@ linux_nat_set_async_mode (int on)
linux_nat_async_enabled = on;
}
+static int
+send_sigint_callback (struct lwp_info *lp, void *data)
+{
+ /* Use is_running instead of !lp->stopped, because the lwp may be
+ stopped due to an internal event, and we want to interrupt it in
+ that case too. What we want is to check if the thread is stopped
+ from the point of view of the user. */
+ if (is_running (lp->ptid))
+ kill_lwp (GET_LWP (lp->ptid), SIGINT);
+ return 0;
+}
+
+static void
+linux_nat_stop (ptid_t ptid)
+{
+ if (non_stop)
+ {
+ if (ptid_equal (ptid, minus_one_ptid))
+ iterate_over_lwps (send_sigint_callback, &ptid);
+ else
+ {
+ struct lwp_info *lp = find_lwp_pid (ptid);
+ send_sigint_callback (lp, NULL);
+ }
+ }
+ else
+ linux_ops->to_stop (ptid);
+}
+
void
linux_nat_add_target (struct target_ops *t)
{
@@ -4269,6 +4422,9 @@ linux_nat_add_target (struct target_ops
t->to_terminal_inferior = linux_nat_terminal_inferior;
t->to_terminal_ours = linux_nat_terminal_ours;
+ /* Methods for non-stop support. */
+ t->to_stop = linux_nat_stop;
+
/* We don't change the stratum; this target will sit at
process_stratum and thread_db will set at thread_stratum. This
is a little strange, since this is a multi-threaded-capable
Index: src/gdb/linux-nat.h
===================================================================
--- src.orig/gdb/linux-nat.h 2008-07-10 22:14:19.000000000 +0100
+++ src/gdb/linux-nat.h 2008-07-10 22:14:30.000000000 +0100
@@ -94,6 +94,8 @@ void check_for_thread_db (void);
/* Tell the thread_db layer what native target operations to use. */
void thread_db_init (struct target_ops *);
+int thread_db_attach_lwp (ptid_t ptid);
+
/* Find process PID's pending signal set from /proc/pid/status. */
void linux_proc_pending_signals (int pid, sigset_t *pending, sigset_t *blocked, sigset_t *ignored);
Index: src/gdb/linux-thread-db.c
===================================================================
--- src.orig/gdb/linux-thread-db.c 2008-07-10 22:14:19.000000000 +0100
+++ src/gdb/linux-thread-db.c 2008-07-10 22:15:05.000000000 +0100
@@ -283,7 +283,10 @@ thread_get_info_callback (const td_thrha
if (thread_info == NULL)
{
/* New thread. Attach to it now (why wait?). */
- attach_thread (thread_ptid, thp, &ti);
+ if (!have_threads ())
+ thread_db_find_new_threads ();
+ else
+ attach_thread (thread_ptid, thp, &ti);
thread_info = find_thread_pid (thread_ptid);
gdb_assert (thread_info != NULL);
}
@@ -308,6 +311,8 @@ thread_from_lwp (ptid_t ptid)
LWP. */
gdb_assert (GET_LWP (ptid) != 0);
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (ptid);
err = td_ta_map_lwp2thr_p (thread_agent, GET_LWP (ptid), &th);
if (err != TD_OK)
error (_("Cannot find user-level thread for LWP %ld: %s"),
@@ -332,6 +337,48 @@ thread_from_lwp (ptid_t ptid)
}
+/* Attach to lwp PTID, doing whatever else is required to have this
+ LWP under the debugger's control --- e.g., enabling event
+ reporting. Returns true on success. */
+int
+thread_db_attach_lwp (ptid_t ptid)
+{
+ td_thrhandle_t th;
+ td_thrinfo_t ti;
+ td_err_e err;
+
+ if (!using_thread_db)
+ return 0;
+
+ /* This ptid comes from linux-nat.c, which should always fill in the
+ LWP. */
+ gdb_assert (GET_LWP (ptid) != 0);
+
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (ptid);
+
+ /* If we have only looked at the first thread before libpthread was
+ initialized, we may not know its thread ID yet. Make sure we do
+ before we add another thread to the list. */
+ if (!have_threads ())
+ thread_db_find_new_threads ();
+
+ err = td_ta_map_lwp2thr_p (thread_agent, GET_LWP (ptid), &th);
+ if (err != TD_OK)
+ /* Cannot find user-level thread. */
+ return 0;
+
+ err = td_thr_get_info_p (&th, &ti);
+ if (err != TD_OK)
+ {
+ warning (_("Cannot get thread info: %s"), thread_db_err_str (err));
+ return 0;
+ }
+
+ attach_thread (ptid, &th, &ti);
+ return 1;
+}
+
void
thread_db_init (struct target_ops *target)
{
@@ -418,6 +465,9 @@ enable_thread_event (td_thragent_t *thre
td_notify_t notify;
td_err_e err;
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (inferior_ptid);
+
/* Get the breakpoint address for thread EVENT. */
err = td_ta_event_addr_p (thread_agent, event, ¬ify);
if (err != TD_OK)
@@ -761,6 +811,15 @@ check_event (ptid_t ptid)
if (stop_pc != td_create_bp_addr && stop_pc != td_death_bp_addr)
return;
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (ptid);
+
+ /* If we have only looked at the first thread before libpthread was
+ initialized, we may not know its thread ID yet. Make sure we do
+ before we add another thread to the list. */
+ if (!have_threads ())
+ thread_db_find_new_threads ();
+
/* If we are at a create breakpoint, we do not know what new lwp
was created and cannot specifically locate the event message for it.
We have to call td_ta_event_getmsg() to get
@@ -951,11 +1010,27 @@ find_new_threads_callback (const td_thrh
return 0;
}
+/* Search for new threads, accessing memory through stopped thread
+ PTID. */
+
static void
thread_db_find_new_threads (void)
{
td_err_e err;
+ struct lwp_info *lp;
+ ptid_t ptid;
+
+ /* In linux, we can only read memory through a stopped lwp. */
+ ALL_LWPS (lp, ptid)
+ if (lp->stopped)
+ break;
+
+ if (!lp)
+ /* There is no stopped thread. Bail out. */
+ return;
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (ptid);
/* Iterate over all user-space threads to discover new threads. */
err = td_ta_thr_iter_p (thread_agent, find_new_threads_callback, NULL,
TD_THR_ANY_STATE, TD_THR_LOWEST_PRIORITY,
Index: src/gdb/linux-fork.c
===================================================================
--- src.orig/gdb/linux-fork.c 2008-07-10 22:14:19.000000000 +0100
+++ src/gdb/linux-fork.c 2008-07-10 22:14:30.000000000 +0100
@@ -337,7 +337,9 @@ linux_fork_killall (void)
{
pid = PIDGET (fp->ptid);
do {
- ptrace (PT_KILL, pid, 0, 0);
+ /* Use SIGKILL instead of PTRACE_KILL because the former works even
+ if the thread is running, while the later doesn't. */
+ kill (pid, SIGKILL);
ret = waitpid (pid, &status, 0);
/* We might get a SIGCHLD instead of an exit status. This is
aggravated by the first kill above - a child has just