This is the mail archive of the
gdb-patches@sourceware.org
mailing list for the GDB project.
[non-stop] 08/10 linux native support
- From: Pedro Alves <pedro at codesourcery dot com>
- To: gdb-patches at sourceware dot org
- Date: Sun, 15 Jun 2008 22:05:49 +0100
- Subject: [non-stop] 08/10 linux native support
This adds the linux native target non-stop mode support:
- Not stop all threads when a thread stops.
- Be sure we're not reading registers and memory from
running threads.
- Add threads to the thread table as soon as we detect
them.
- Avoid using ptrace on running threads.
- Implement target_stop_ptid to interrupt only
one thread
- Getting the last pending event of a thread is
different in nonstop due to the fact that
stop_signal is per-thread in non-stop mode.
--
Pedro Alves
2008-06-15 Pedro Alves <pedro@codesourcery.com>
* linux-fork.c (linux_fork_killall): Use SIGKILL instead of
PTRACE_KILL.
* linux-nat.c (find_lwp_pid): Make public.
(get_pending_status): Implement non-stop mode.
(sigint_clear_callback): New.
(linux_nat_resume): In non-stop mode, always resume only a single
PTID. Clear the sigint flag.
(linux_handle_extended_wait): On a clone event, add new lwp to
GDB's thread table, and mark as running, executing and stopped
appropriatelly.
(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.
(kill_callback): If lwp is not stopped, use SIGKILL.
(linux_nat_thread_alive): Use signal 0 to detect if a thread is
alive.
(send_sigint_callback): New.
(linux_nat_stop_ptid): New.
(linux_nat_add_target): Set to_stop_ptid to linux_nat_stop_ptid.
* linux-nat.h (struct lwp_info): Add sigint field.
(find_lwp_pid): Declare.
* linux-thread-db.c (thread_from_lwp, enable_thread_event)
(check_event): Set proc_handle.pid to the stopped lwp.
(thread_db_find_new_threads): If current lwp is executing, don't
try to read from it.
---
gdb/linux-fork.c | 4
gdb/linux-nat.c | 256 ++++++++++++++++++++++++++++++++++++++++----------
gdb/linux-nat.h | 6 +
gdb/linux-thread-db.c | 15 ++
4 files changed, 233 insertions(+), 48 deletions(-)
Index: src/gdb/linux-fork.c
===================================================================
--- src.orig/gdb/linux-fork.c 2008-06-15 20:25:42.000000000 +0100
+++ src/gdb/linux-fork.c 2008-06-15 20:56:56.000000000 +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
Index: src/gdb/linux-nat.c
===================================================================
--- src.orig/gdb/linux-nat.c 2008-06-15 20:25:42.000000000 +0100
+++ src/gdb/linux-nat.c 2008-06-15 20:57:27.000000000 +0100
@@ -212,6 +212,10 @@ 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
@@ -415,6 +419,8 @@ linux_test_for_tracefork (int original_p
int child_pid, ret, status;
long second_pid;
+ int events_enabled = linux_nat_async_events (0);
+
linux_supports_tracefork_flag = 0;
linux_supports_tracevforkdone_flag = 0;
@@ -454,6 +460,7 @@ 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 (events_enabled);
return;
}
@@ -493,6 +500,8 @@ 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 (events_enabled);
}
/* Return non-zero iff we have tracefork functionality available.
@@ -920,7 +929,7 @@ delete_lwp (ptid_t ptid)
/* Return a pointer to the structure describing the LWP corresponding
to PID. If no corresponding LWP could be found, return NULL. */
-static struct lwp_info *
+struct lwp_info *
find_lwp_pid (ptid_t ptid)
{
struct lwp_info *lp;
@@ -1306,16 +1315,76 @@ 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, 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 then 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;
}
@@ -1379,6 +1448,13 @@ 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. */
@@ -1445,6 +1521,13 @@ resume_set_callback (struct lwp_info *lp
return 0;
}
+static int
+sigint_clear_callback (struct lwp_info *lp, void *data)
+{
+ lp->sigint = 0;
+ return 0;
+}
+
static void
linux_nat_resume (ptid_t ptid, int step, enum target_signal signo)
{
@@ -1468,10 +1551,17 @@ 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. */
@@ -1481,6 +1571,7 @@ 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. */
@@ -1489,6 +1580,9 @@ linux_nat_resume (ptid_t ptid, int step,
/* Mark this LWP as resumed. */
lp->resumed = 1;
+ /* Remove the SIGINT mark. Used in non-stop mode. */
+ lp->sigint = 0;
+
/* If we have a pending wait status for this thread, there is no
point in resuming the process. But first make sure that
linux_nat_wait won't preemptively handle the event - we
@@ -1631,6 +1725,8 @@ 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;
@@ -1650,20 +1746,43 @@ linux_handle_extended_wait (struct lwp_i
else
status = 0;
+ /* Make thread_db aware of this thread. We do this this
+ early, so in non-stop mode, threads show up as they're
+ created, instead of on next stop. thread_db needs a
+ stopped inferior_ptid --- since we know LP is stopped,
+ use it this time. */
+ old_chain = save_inferior_ptid ();
+ inferior_ptid = lp->ptid;
+ lp->stopped = 1;
+ target_find_new_threads ();
+ do_cleanups (old_chain);
+ if (!in_thread_list (new_lp->ptid))
+ {
+ /* We're not using thread_db. Attach and add it to
+ GDB's list. */
+ lin_lwp_attach_lwp (new_lp->ptid);
+ target_post_attach (GET_LWP (new_lp->ptid));
+ add_thread (new_lp->ptid);
+ }
+
if (stopping)
new_lp->stopped = 1;
else
{
+ new_lp->stopped = 0;
new_lp->resumed = 1;
ptrace (PTRACE_CONT,
PIDGET (lp->waitstatus.value.related_pid), 0,
status ? WSTOPSIG (status) : 0);
+ set_running (new_lp->ptid, 1);
+ set_executing (new_lp->ptid, 1);
}
if (debug_linux_nat)
fprintf_unfiltered (gdb_stdlog,
"LHEW: Got clone event from LWP %ld, resuming\n",
GET_LWP (lp->ptid));
+ lp->stopped = 0;
ptrace (PTRACE_CONT, GET_LWP (lp->ptid), 0, 0);
return 1;
@@ -2383,13 +2502,7 @@ 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
@@ -2519,6 +2632,8 @@ 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);
@@ -2747,19 +2862,23 @@ 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
@@ -2796,13 +2915,26 @@ static int
kill_callback (struct lwp_info *lp, void *data)
{
errno = 0;
- ptrace (PTRACE_KILL, GET_LWP (lp->ptid), 0, 0);
- if (debug_linux_nat)
- fprintf_unfiltered (gdb_stdlog,
- "KC: PTRACE_KILL %s, 0, 0 (%s)\n",
- target_pid_to_str (lp->ptid),
- errno ? safe_strerror (errno) : "OK");
+ /* PTRACE_KILL doesn't work when the thread is running. */
+ if (!lp->stopped)
+ {
+ kill_lwp (GET_LWP (lp->ptid), SIGKILL);
+ if (debug_linux_nat)
+ fprintf_unfiltered (gdb_stdlog,
+ "KC: kill_lwp (SIGKILL) %s (%s)\n",
+ target_pid_to_str (lp->ptid),
+ errno ? safe_strerror (errno) : "OK");
+ }
+ else
+ {
+ ptrace (PTRACE_KILL, GET_LWP (lp->ptid), 0, 0);
+ if (debug_linux_nat)
+ fprintf_unfiltered (gdb_stdlog,
+ "KC: PTRACE_KILL %s, 0, 0 (%s)\n",
+ target_pid_to_str (lp->ptid),
+ errno ? safe_strerror (errno) : "OK");
+ }
return 0;
}
@@ -2943,22 +3075,22 @@ 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;
@@ -4140,6 +4272,33 @@ 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_stopped 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_stopped (lp->ptid) && !lp->sigint)
+ {
+ kill_lwp (GET_LWP (lp->ptid), SIGINT);
+ lp->sigint = 1;
+ }
+ return 0;
+}
+
+static void
+linux_nat_stop_ptid (ptid_t ptid)
+{
+ 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);
+ }
+}
+
void
linux_nat_add_target (struct target_ops *t)
{
@@ -4170,6 +4329,9 @@ 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_ptid = linux_nat_stop_ptid;
+
/* 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 2008-06-15 20:25:42.000000000 +0100
+++ src/gdb/linux-nat.h 2008-06-15 20:27:15.000000000 +0100
@@ -37,6 +37,10 @@ struct lwp_info
SIGCHLD. */
int cloned;
+ /* Non-zero if we sent this LWP a SIGINT (but the LWP didn't report
+ it back yet). */
+ int sigint;
+
/* Non-zero if we sent this LWP a SIGSTOP (but the LWP didn't report
it back yet). */
int signalled;
@@ -88,6 +92,8 @@ extern struct lwp_info *lwp_list;
#define is_lwp(ptid) (GET_LWP (ptid) != 0)
#define BUILD_LWP(lwp, pid) ptid_build (pid, lwp, 0)
+struct lwp_info *find_lwp_pid (ptid_t ptid);
+
/* Attempt to initialize libthread_db. */
void check_for_thread_db (void);
Index: src/gdb/linux-thread-db.c
===================================================================
--- src.orig/gdb/linux-thread-db.c 2008-06-15 20:25:41.000000000 +0100
+++ src/gdb/linux-thread-db.c 2008-06-15 20:27:15.000000000 +0100
@@ -308,6 +308,8 @@ 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"),
@@ -418,6 +420,9 @@ 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 +766,9 @@ 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 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
@@ -955,7 +963,14 @@ static void
thread_db_find_new_threads (void)
{
td_err_e err;
+ struct lwp_info *lp = find_lwp_pid (inferior_ptid);
+
+ if (!lp || !lp->stopped)
+ /* In linux, we can only read memory through a stopped lwp. */
+ return;
+ /* Access an lwp we know is stopped. */
+ proc_handle.pid = GET_LWP (inferior_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,