From a1465d2f396e416a0049332b20fca5977384b9f5 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Tue, 11 Nov 2014 09:31:53 -0600 Subject: kgdb: timeout if secondary CPUs ignore the roundup Currently if an active CPU fails to respond to a roundup request the CPU that requested the roundup will become stuck. This needlessly reduces the robustness of the debugger. This patch introduces a timeout allowing the system state to be examined even when the system contains unresponsive processors. It also modifies kdb's cpu command to make it censor attempts to switch to unresponsive processors and to report their state as (D)ead. Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Andrew Morton Signed-off-by: Jason Wessel --- kernel/debug/debug_core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel/debug/debug_core.c') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 1adf62b39b96..acd749736822 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -471,6 +471,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, int cpu; int trace_on = 0; int online_cpus = num_online_cpus(); + u64 time_left; kgdb_info[ks->cpu].enter_kgdb++; kgdb_info[ks->cpu].exception_state |= exception_state; @@ -595,9 +596,13 @@ return_normal: /* * Wait for the other CPUs to be notified and be waiting for us: */ - while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) + - atomic_read(&slaves_in_kgdb)) != online_cpus) + time_left = loops_per_jiffy * HZ; + while (kgdb_do_roundup && --time_left && + (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) != + online_cpus) cpu_relax(); + if (!time_left) + pr_crit("KGDB: Timed out waiting for secondary CPUs.\n"); /* * At this point the primary processor is completely -- cgit v1.2.3-55-g7522