From d6ad3e286d2c075a60b9f11075a2c55aeeeca2ad Mon Sep 17 00:00:00 2001
From: Jason Wessel <jason.wessel@windriver.com>
Date: Wed, 27 Jan 2010 16:25:22 -0600
Subject: softlockup: Add sched_clock_tick() to avoid kernel warning on kgdb
resume
When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, sched_clock() gets
the time from hardware such as the TSC on x86. In this
configuration kgdb will report a softlock warning message on
resuming or detaching from a debug session.
Sequence of events in the problem case:
1) "cpu sched clock" and "hardware time" are at 100 sec prior
to a call to kgdb_handle_exception()
2) Debugger waits in kgdb_handle_exception() for 80 sec and on
exit the following is called ... touch_softlockup_watchdog() -->
__raw_get_cpu_var(touch_timestamp) = 0;
3) "cpu sched clock" = 100s (it was not updated, because the
interrupt was disabled in kgdb) but the "hardware time" = 180 sec
4) The first timer interrupt after resuming from
kgdb_handle_exception updates the watchdog from the "cpu sched clock"
update_process_times() { ... run_local_timers() -->
softlockup_tick() --> check (touch_timestamp == 0) (it is "YES"
here, we have set "touch_timestamp = 0" at kgdb) -->
__touch_softlockup_watchdog() ***(A)--> reset "touch_timestamp"
to "get_timestamp()" (Here, the "touch_timestamp" will still be
set to 100s.) ...
scheduler_tick() ***(B)--> sched_clock_tick() (update "cpu sched
clock" to "hardware time" = 180s) ... }
5) The Second timer interrupt handler appears to have a large
jump and trips the softlockup warning.
update_process_times() { ... run_local_timers() -->
softlockup_tick() --> "cpu sched clock" - "touch_timestamp" =
180s-100s > 60s --> printk "soft lockup error messages" ... }
note: ***(A) reset "touch_timestamp" to
"get_timestamp(this_cpu)"
Why is "touch_timestamp" 100 sec, instead of 180 sec?
When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, the call trace of
get_timestamp() is:
get_timestamp(this_cpu)
-->cpu_clock(this_cpu)
-->sched_clock_cpu(this_cpu)
-->__update_sched_clock(sched_clock_data, now)
The __update_sched_clock() function uses the GTOD tick value to
create a window to normalize the "now" values. So if "now"
value is too big for sched_clock_data, it will be ignored.
The fix is to invoke sched_clock_tick() to update "cpu sched
clock" in order to recover from this state. This is done by
introducing the function touch_softlockup_watchdog_sync(). This
allows kgdb to request that the sched clock is updated when the
watchdog thread runs the first time after a resume from kgdb.
[yong.zhang0@gmail.com: Use per cpu instead of an array]
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Dongdong Deng <Dongdong.Deng@windriver.com>
Cc: kgdb-bugreport@lists.sourceforge.net
Cc: peterz@infradead.org
LKML-Reference: <1264631124-4837-2-git-send-email-jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
include/linux/sched.h | 4 ++++
1 file changed, 4 insertions(+)
(limited to 'include')
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6f7bba9..8923215 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -310,6 +310,7 @@ extern void sched_show_task(struct task_struct *p);
#ifdef CONFIG_DETECT_SOFTLOCKUP
extern void softlockup_tick(void);
extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
void __user *buffer,
@@ -323,6 +324,9 @@ static inline void softlockup_tick(void)
static inline void touch_softlockup_watchdog(void)
{
}
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
static inline void touch_all_softlockup_watchdogs(void)
{
}
--
cgit v1.1
From f98bfbd78c37c5946cc53089da32a5f741efdeb7 Mon Sep 17 00:00:00 2001
From: Evgeniy Polyakov <zbr@ioremap.net>
Date: Tue, 2 Feb 2010 15:58:48 -0800
Subject: connector: Delete buggy notification code.
On Tue, Feb 02, 2010 at 02:57:14PM -0800, Greg KH (gregkh@suse.de) wrote:
> > There are at least two ways to fix it: using a big cannon and a small
> > one. The former way is to disable notification registration, since it is
> > not used by anyone at all. Second way is to check whether calling
> > process is root and its destination group is -1 (kind of priveledged
> > one) before command is dispatched to workqueue.
>
> Well if no one is using it, removing it makes the most sense, right?
>
> No objection from me, care to make up a patch either way for this?
Getting it is not used, let's drop support for notifications about
(un)registered events from connector.
Another option was to check credentials on receiving, but we can always
restore it without bugs if needed, but genetlink has a wider code base
and none complained, that userspace can not get notification when some
other clients were (un)registered.
Kudos for Sebastian Krahmer <krahmer@suse.de>, who found a bug in the
code.
Signed-off-by: Evgeniy Polyakov <zbr@ioremap.net>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/connector.h | 32 --------------------------------
1 file changed, 32 deletions(-)
(limited to 'include')
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 72ba63e..3a779ff 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -24,9 +24,6 @@
#include <linux/types.h>
-#define CN_IDX_CONNECTOR 0xffffffff
-#define CN_VAL_CONNECTOR 0xffffffff
-
/*
* Process Events connector unique ids -- used for message routing
*/
@@ -75,30 +72,6 @@ struct cn_msg {
__u8 data[0];
};
-/*
- * Notify structure - requests notification about
- * registering/unregistering idx/val in range [first, first+range].
- */
-struct cn_notify_req {
- __u32 first;
- __u32 range;
-};
-
-/*
- * Main notification control message
- * *_notify_num - number of appropriate cn_notify_req structures after
- * this struct.
- * group - notification receiver's idx.
- * len - total length of the attached data.
- */
-struct cn_ctl_msg {
- __u32 idx_notify_num;
- __u32 val_notify_num;
- __u32 group;
- __u32 len;
- __u8 data[0];
-};
-
#ifdef __KERNEL__
#include <asm/atomic.h>
@@ -151,11 +124,6 @@ struct cn_callback_entry {
u32 seq, group;
};
-struct cn_ctl_entry {
- struct list_head notify_entry;
- struct cn_ctl_msg *msg;
-};
-
struct cn_dev {
struct cb_id id;
--
cgit v1.1