To test out the new utrace interface (I was using kernel
2.6.26-138.fc10.x86_64), I ported the crash-suspend.c example from the
old interface to the new interface. It is attached to this email. Feel
free to ignore/delete the extra debug printk's.
When run, it does what is is supposed to do, but triggers a BUG_ON
message when the crashed/suspended process is put back in the foreground.
Note that I don't have any real feel for whether the bug lies in my
crash-suspend.c translation or the new utrace itself.
The BUG details are in msg.txt.
--
David Smith
[EMAIL PROTECTED]
Red Hat
http://www.redhat.com
256.217.0141 (direct)
256.837.0057 (fax)
#include <linux/sched.h>
#include <linux/pid.h>
#include <linux/utrace.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/errno.h>
MODULE_DESCRIPTION("automatic suspend on crash");
MODULE_LICENSE("GPL");
static int target_pid;
static int verbose;
module_param_named(pid, target_pid, int, 0);
module_param(verbose, bool, 0);
#define MY_EVENTS (UTRACE_EVENT(CLONE) | UTRACE_EVENT(DEATH) \
| UTRACE_EVENT(SIGNAL_CORE) | UTRACE_EVENT(JCTL))
/*
* This is the interesting hook.
*/
static u32
crash_suspend_signal(u32 action,
struct utrace_attached_engine *engine,
struct task_struct *tsk, struct pt_regs *regs,
siginfo_t *info,
const struct k_sigaction *orig_ka,
struct k_sigaction *return_ka)
{
printk("%s:%d action = 0x%x\n", __FUNCTION__, __LINE__, action);
if (info->si_errno & 0x80000000) {
info->si_errno &= ~0x80000000;
printk("%s:%d\n", __FUNCTION__, __LINE__);
return UTRACE_RESUME;
}
/*
* If another engine is doing something, just get out of the way.
*/
if ((action & UTRACE_SIGNAL_MASK) != UTRACE_SIGNAL_CORE)
return UTRACE_RESUME;
printk("%s:%d\n", __FUNCTION__, __LINE__);
info->si_errno |= 0x80000000;
return UTRACE_SIGNAL_TSTP | UTRACE_SIGNAL_HOLD;
}
static u32
crash_suspend_jctl(enum utrace_resume_action action,
struct utrace_attached_engine *engine,
struct task_struct *tsk,
bool notify, int type)
{
printk("%s:%d type = 0x%x\n", __FUNCTION__, __LINE__, type);
if (type == CLD_STOPPED) {
int signr = tsk->exit_code;
pid_t pgid = task_pgrp_nr(tsk);
if (verbose)
printk("crash-suspend stopped"
" pgrp %d for pid %d signal %d\n",
pgid, tsk->pid, signr);
if (signr != SIGSTOP && signr != SIGTSTP
&& signr != SIGTTOU && signr != SIGTTIN)
/*
* This is an unnatural stop induced by us, above.
* Now that we have ourselves stopped with the
* proper weirdo status, stop the rest of the
* process group too in normal job control fashion.
*/
(void) kill_pgrp(find_pid(-pgid), SIGTTOU, 1);
}
return UTRACE_RESUME;
}
/*
* On clone, attach to the child.
*/
static u32
crash_suspend_clone(enum utrace_resume_action action,
struct utrace_attached_engine *engine,
struct task_struct *parent,
unsigned long clone_flags,
struct task_struct *child)
{
struct utrace_attached_engine *child_engine;
printk("%s:%d\n", __FUNCTION__, __LINE__);
child_engine = utrace_attach(child, UTRACE_ATTACH_CREATE,
engine->ops, 0);
if (IS_ERR(child_engine)) {
printk("attach to clone child %d (%lx) from 0x%p => %ld\n",
child->pid, clone_flags, engine, PTR_ERR(child_engine));
}
else
utrace_set_events(child, child_engine, MY_EVENTS);
return UTRACE_RESUME;
}
/*
* If we are still attached at task death, it didn't die by core dump signal.
* Just detach and let it go.
*/
static u32
crash_suspend_death(struct utrace_attached_engine *engine,
struct task_struct *tsk,
bool group_dead, int signal)
{
printk("%s:%d\n", __FUNCTION__, __LINE__);
return UTRACE_DETACH;
}
static const struct utrace_engine_ops crash_suspend_ops =
{
.report_clone = crash_suspend_clone,
.report_death = crash_suspend_death,
.report_signal = crash_suspend_signal,
.report_jctl = crash_suspend_jctl,
};
static int __init init_crash_suspend(void)
{
struct task_struct *target;
struct utrace_attached_engine *engine;
rcu_read_lock();
target = find_task_by_pid(target_pid);
if (target)
get_task_struct(target);
rcu_read_unlock();
if (target == NULL) {
printk("cannot find PID %d\n", target_pid);
return -ESRCH;
}
engine = utrace_attach(target, UTRACE_ATTACH_CREATE,
&crash_suspend_ops, 0);
if (IS_ERR(engine))
printk("utrace_attach: %ld\n", PTR_ERR(engine));
else if (engine == NULL)
printk("utrace_attach => null!\n");
else
printk("attached to %d => 0x%p\n", target->pid, engine);
utrace_set_events(target, engine, MY_EVENTS);
WARN_ON(atomic_dec_and_test(&target->usage));
return 0;
}
static void __exit exit_crash_suspend(void)
{
struct task_struct *t;
struct utrace_attached_engine *engine;
int n = 0;
rcu_read_lock();
for_each_process(t) {
engine = utrace_attach(t, UTRACE_ATTACH_MATCH_OPS,
&crash_suspend_ops, 0);
if (IS_ERR(engine)) {
int error = -PTR_ERR(engine);
if (error != ENOENT)
printk("!!! utrace_attach returned %d on %d\n",
error, t->pid);
}
else {
utrace_control(t, engine, UTRACE_DETACH);
++n;
}
}
rcu_read_unlock();
printk("detached from %d threads, unloading\n", n);
}
module_init(init_crash_suspend);
module_exit(exit_crash_suspend);
Jul 23 14:52:16 dhcp-148 kernel:<4>attached to 3132 => 0xffff81000a46d000
Jul 23 14:52:28 dhcp-148 kernel:<4>crash_suspend_clone:90
Jul 23 14:52:31 dhcp-148 kernel:<4>crash_suspend_signal:32 action = 0x35
Jul 23 14:52:31 dhcp-148 kernel:<4>crash_suspend_signal:45
Jul 23 14:52:31 dhcp-148 kernel:<4>crash_suspend_jctl:56 type = 0x40005
Jul 23 14:52:31 dhcp-148 kernel:<4>crash-suspend stopped pgrp 4327 for pid 4327
signal 3
Jul 23 14:52:34 dhcp-148 kernel:<0>------------[ cut here ]------------
Jul 23 14:52:34 dhcp-148 kernel:<2>kernel BUG at kernel/utrace.c:1188!
Jul 23 14:52:34 dhcp-148 kernel:<0>invalid opcode: 0000 [4] SMP DEBUG_PAGEALLOC
Jul 23 14:52:34 dhcp-148 kernel:<4>CPU 0
Jul 23 14:52:34 dhcp-148 kernel:<4>Modules linked in: crash_suspend nfs lockd
nfs_acl rfcomm l2cap bluetooth autofs4 fuse sunrpc ipt_REJECT nf_conntrack_ipv4
iptable_filter ip_tables ip6t_REJECT xt_tcpudp nf_conntrack_ipv6 xt_state
nf_conntrack ip6table_filter ip6_tables x_tables ipv6 loop floppy pcspkr
8139too 8139cp mii i2c_piix4 i2c_core sr_mod cdrom dm_snapshot dm_zero
dm_mirror dm_log dm_mod pata_acpi ata_piix ata_generic ext3 jbd mbcache
uhci_hcd ohci_hcd ehci_hcd [last unloaded: crash_suspend]
Jul 23 14:52:34 dhcp-148 kernel:<4>Pid: 4327, comm: cat Tainted: G D
2.6.26-138.fc10.x86_64 #1
Jul 23 14:52:34 dhcp-148 kernel:<4>RIP: 0010:[<ffffffff81072a54>]
[<ffffffff81072a54>] start_report+0x11/0x38
Jul 23 14:52:34 dhcp-148 kernel:<4>RSP: 0018:ffff81000a4afd18 EFLAGS: 00010202
Jul 23 14:52:34 dhcp-148 kernel:<4>RAX: 0000000000000063 RBX: 0000000000040006
RCX: 0000000000004601
Jul 23 14:52:34 dhcp-148 kernel:<4>RDX: 0000000000004600 RSI: 0000000000040006
RDI: ffff81001950d1f8
Jul 23 14:52:34 dhcp-148 kernel:<4>RBP: ffff81000a4afd28 R08: 0000000000000002
R09: 0000000000000001
Jul 23 14:52:34 dhcp-148 kernel:<4>R10: ffff81001d993e08 R11: ffff810010818048
R12: ffff81001950d1f8
Jul 23 14:52:34 dhcp-148 kernel:<4>R13: ffff810010818000 R14: ffff81001d950000
R15: ffff81000a4afd58
Jul 23 14:52:34 dhcp-148 kernel:<4>FS: 00007f627e0446f0(0000)
GS:ffffffff81492000(0000) knlGS:0000000000000000
Jul 23 14:52:34 dhcp-148 kernel:<4>CS: 0010 DS: 0000 ES: 0000 CR0:
000000008005003b
Jul 23 14:52:34 dhcp-148 kernel:<4>CR2: 00000000006bd4b4 CR3: 000000001e0f0000
CR4: 00000000000006e0
Jul 23 14:52:34 dhcp-148 kernel:<4>DR0: 0000000000000000 DR1: 0000000000000000
DR2: 0000000000000000
Jul 23 14:52:34 dhcp-148 kernel:<4>DR3: 0000000000000000 DR6: 00000000ffff0ff0
DR7: 0000000000000400
Jul 23 14:52:34 dhcp-148 kernel:<4>Process cat (pid: 4327, threadinfo
ffff81000a4ae000, task ffff810010818000)
Jul 23 14:52:34 dhcp-148 kernel:<4>Stack: 0000000000040006 ffff81001950d1f8
ffff81000a4afd98 ffffffff810730d9
Jul 23 14:52:34 dhcp-148 kernel:<4> ffffffff810461c9 0000000100040006
ffff81001d993e20 0000000000000046
Jul 23 14:52:34 dhcp-148 kernel:<4> 0000000000000005 ffff81000a000000
ffff81001d993e08 0000000000040006
Jul 23 14:52:34 dhcp-148 kernel:<4>Call Trace:
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff810730d9>]
utrace_report_jctl+0xeb/0x1f1
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff810461c9>] ?
get_signal_to_deliver+0x61/0x2c3
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff81046215>]
get_signal_to_deliver+0xad/0x2c3
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff8100b377>]
do_notify_resume+0x90/0x90a
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff8107c09c>] ?
audit_syscall_exit+0x331/0x353
Jul 23 14:52:34 dhcp-148 kernel:<4> [<ffffffff8100c402>] int_signal+0x12/0x17
Jul 23 14:52:34 dhcp-148 kernel:<4>
Jul 23 14:52:34 dhcp-148 kernel:<4>
Jul 23 14:52:34 dhcp-148 kernel:<0>Code: 48 85 c0 49 89 45 08 74 04 31 c0 eb 05
b8 f5 ff ff ff 5e 5b 41 5c 41 5d c9 c3 55 48 89 e5 41 54 49 89 fc 53 8a 47 5c
a8 01 74 04 <0f> 0b eb fe a8 02 74 1a 48 8d 5f 20 48 89 df e8 a5 d7 26 00 41
Jul 23 14:52:34 dhcp-148 kernel:<1>RIP [<ffffffff81072a54>]
start_report+0x11/0x38
Jul 23 14:52:34 dhcp-148 kernel:<4> RSP <ffff81000a4afd18>
Jul 23 14:52:34 dhcp-148 kernel:<4>---[ end trace 04166b488c6df96e ]---
Jul 23 14:52:34 dhcp-148 kernel:<4>crash_suspend_death:112
Jul 23 15:05:15 dhcp-148 kernel:<4>crash_suspend_clone:90
Jul 23 15:05:15 dhcp-148 kernel:<4>crash_suspend_death:112
Jul 23 16:06:57 dhcp-148 kernel:<4>crash_suspend_clone:90
Jul 23 16:06:57 dhcp-148 kernel:<4>crash_suspend_death:112
Jul 23 16:07:04 dhcp-148 kernel:<4>crash_suspend_clone:90
Jul 23 16:07:04 dhcp-148 kernel:<4>detached from 2 threads, unloading
