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 <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>

3 files changed, 14 insertions, 3 deletions

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
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 8859ca34dcfe..15e1a7af5dd0 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -129,6 +129,10 @@ int kdb_stub(struct kgdb_state *ks)
                 ks->pass_exception = 1;
                 KDB_FLAG_SET(CATASTROPHIC);
         }
+        /* set CATASTROPHIC if the system contains unresponsive processors */
+        for_each_online_cpu(i)
+                if (!kgdb_info[i].enter_kgdb)
+                        KDB_FLAG_SET(CATASTROPHIC);
         if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
                 KDB_STATE_CLEAR(SSBPT);
                 KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 8d84979cbe05..f191bddf64b8 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2201,6 +2201,8 @@ static void kdb_cpu_status(void)
         for (start_cpu = -1, i = 0; i < NR_CPUS; i++) {
                 if (!cpu_online(i)) {
                         state = 'F';    /* cpu is offline */
+                } else if (!kgdb_info[i].enter_kgdb) {
+                        state = 'D';    /* cpu is online but unresponsive */
                 } else {
                         state = ' ';    /* cpu is responding to kdb */
                         if (kdb_task_state_char(KDB_TSK(i)) == 'I')
@@ -2254,7 +2256,7 @@ static int kdb_cpu(int argc, const char **argv)
         /*
          * Validate cpunum
          */
-        if ((cpunum > NR_CPUS) || !cpu_online(cpunum))
+        if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
                 return KDB_BADCPUNUM;
 
         dbg_switch_cpu = cpunum;