Re: [PATCH v6 4/4] kdb: Don't back trace on a cpu that didn't round up

[Daniel Thompson]

On Tue, Nov 27, 2018 at 09:38:39AM -0800, Douglas Anderson wrote:
> If you have a CPU that fails to round up and then run 'btc' you'll end
> up crashing in kdb becaue we dereferenced NULL.  Let's add a check.
> It's wise to also set the task to NULL when leaving the debugger so
> that if we fail to round up on a later entry into the debugger we
> won't backtrace a stale task.
> 
> Signed-off-by: Douglas Anderson <dianders@xxxxxxxxxxxx>

Acked-by: Daniel Thompson <daniel.thompson@xxxxxxxxxx>

> ---
> 
> Changes in v6: None
> Changes in v5: None
> Changes in v4:
> - Also clear out .debuggerinfo.
> - Also clear out .debuggerinfo and .task for the master.
> - Remove clearing out in kdb_stub for offline CPUs; it's now redundant.
> 
> Changes in v3:
> - Don't back trace on a cpu that didn't round up new for v3.
> 
> Changes in v2: None
> 
>  kernel/debug/debug_core.c       |  4 ++++
>  kernel/debug/kdb/kdb_bt.c       | 11 ++++++++++-
>  kernel/debug/kdb/kdb_debugger.c |  7 -------
>  3 files changed, 14 insertions(+), 8 deletions(-)
> 
> diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
> index 1fb8b239e567..5cc608de6883 100644
> --- a/kernel/debug/debug_core.c
> +++ b/kernel/debug/debug_core.c
> @@ -592,6 +592,8 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
>  				arch_kgdb_ops.correct_hw_break();
>  			if (trace_on)
>  				tracing_on();
> +			kgdb_info[cpu].debuggerinfo = NULL;
> +			kgdb_info[cpu].task = NULL;
>  			kgdb_info[cpu].exception_state &=
>  				~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
>  			kgdb_info[cpu].enter_kgdb--;
> @@ -724,6 +726,8 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
>  	if (trace_on)
>  		tracing_on();
>  
> +	kgdb_info[cpu].debuggerinfo = NULL;
> +	kgdb_info[cpu].task = NULL;
>  	kgdb_info[cpu].exception_state &=
>  		~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
>  	kgdb_info[cpu].enter_kgdb--;
> diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
> index 7921ae4fca8d..7e2379aa0a1e 100644
> --- a/kernel/debug/kdb/kdb_bt.c
> +++ b/kernel/debug/kdb/kdb_bt.c
> @@ -186,7 +186,16 @@ kdb_bt(int argc, const char **argv)
>  		kdb_printf("btc: cpu status: ");
>  		kdb_parse("cpu\n");
>  		for_each_online_cpu(cpu) {
> -			sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
> +			void *kdb_tsk = KDB_TSK(cpu);
> +
> +			/* If a CPU failed to round up we could be here */
> +			if (!kdb_tsk) {
> +				kdb_printf("WARNING: no task for cpu %ld\n",
> +					   cpu);
> +				continue;
> +			}
> +
> +			sprintf(buf, "btt 0x%px\n", kdb_tsk);
>  			kdb_parse(buf);
>  			touch_nmi_watchdog();
>  		}
> diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
> index 15e1a7af5dd0..53a0df6e4d92 100644
> --- a/kernel/debug/kdb/kdb_debugger.c
> +++ b/kernel/debug/kdb/kdb_debugger.c
> @@ -118,13 +118,6 @@ int kdb_stub(struct kgdb_state *ks)
>  	kdb_bp_remove();
>  	KDB_STATE_CLEAR(DOING_SS);
>  	KDB_STATE_SET(PAGER);
> -	/* zero out any offline cpu data */
> -	for_each_present_cpu(i) {
> -		if (!cpu_online(i)) {
> -			kgdb_info[i].debuggerinfo = NULL;
> -			kgdb_info[i].task = NULL;
> -		}
> -	}
>  	if (ks->err_code == DIE_OOPS || reason == KDB_REASON_OOPS) {
>  		ks->pass_exception = 1;
>  		KDB_FLAG_SET(CATASTROPHIC);
> -- 
> 2.20.0.rc0.387.gc7a69e6b6c-goog
>