kgdb: fix several kgdb regressions
kgdb core fixes:
- Check to see that mm->mmap_cache is not null before calling
flush_cache_range(), else on arch=ARM it will cause a fatal
fault.
- Breakpoints should only be restored if they are in the BP_ACTIVE
state.
- Fix a typo in comments to "kgdb_register_io_module"
x86 kgdb fixes:
- Fix the x86 arch handler such that on a kill or detach that the
appropriate cleanup on the single stepping flags gets run.
- Add in the DIE_NMIWATCHDOG call for x86_64
- Touch the nmi watchdog before returning the system to normal
operation after performing any kind of kgdb operation, else
the possibility exists to trigger the watchdog.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 055b165..4e07332 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -600,8 +600,13 @@
void __kprobes die_nmi(char *str, struct pt_regs *regs, int do_panic)
{
- unsigned long flags = oops_begin();
+ unsigned long flags;
+ if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) ==
+ NOTIFY_STOP)
+ return;
+
+ flags = oops_begin();
/*
* We are in trouble anyway, lets at least try
* to get a message out.