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/kgdb.c b/arch/x86/kernel/kgdb.c
index 7d651ad..8c7e555 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -370,6 +370,8 @@
ptr = &remcomInBuffer[1];
if (kgdb_hex2long(&ptr, &addr))
linux_regs->ip = addr;
+ case 'D':
+ case 'k':
newPC = linux_regs->ip;
/* clear the trace bit */
@@ -480,6 +482,8 @@
if (kgdb_handle_exception(args->trapnr, args->signr, args->err, regs))
return NOTIFY_DONE;
+ /* Must touch watchdog before return to normal operation */
+ touch_nmi_watchdog();
return NOTIFY_STOP;
}
