Merge tag 'kgdb-4.21-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/danielt/linux

Pull kgdb updates from Daniel Thompson:
 "Mostly clean ups although while Doug's was chasing down a odd lockdep
  warning he also did some work to improved debugger resilience when
  some CPUs fail to respond to the round up request.

  The main changes are:

   - Fixing a lockdep warning on architectures that cannot use an NMI
     for the round up plus related changes to make CPU round up and all
     CPU backtrace more resilient.

   - Constify the arch ops tables

   - A couple of other small clean ups

  Two of the three patchsets here include changes that spill over into
  arch/. Changes in the arch space are relatively narrow in scope (and
  directly related to kgdb). Didn't get comprehensive acks but all
  impacted maintainers were Cc:ed in good time"

* tag 'kgdb-4.21-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/danielt/linux:
  kgdb/treewide: constify struct kgdb_arch arch_kgdb_ops
  mips/kgdb: prepare arch_kgdb_ops for constness
  kdb: use bool for binary state indicators
  kdb: Don't back trace on a cpu that didn't round up
  kgdb: Don't round up a CPU that failed rounding up before
  kgdb: Fix kgdb_roundup_cpus() for arches who used smp_call_function()
  kgdb: Remove irq flags from roundup

5 files changed, 82 insertions, 16 deletions

diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 65c0f1363788..5cc608de6883 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -55,6 +55,7 @@
 #include <linux/mm.h>
 #include <linux/vmacache.h>
 #include <linux/rcupdate.h>
+#include <linux/irq.h>
 
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
@@ -220,6 +221,62 @@ int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
 	return 0;
 }
 
+#ifdef CONFIG_SMP
+
+/*
+ * Default (weak) implementation for kgdb_roundup_cpus
+ */
+
+static DEFINE_PER_CPU(call_single_data_t, kgdb_roundup_csd);
+
+void __weak kgdb_call_nmi_hook(void *ignored)
+{
+	/*
+	 * NOTE: get_irq_regs() is supposed to get the registers from
+	 * before the IPI interrupt happened and so is supposed to
+	 * show where the processor was.  In some situations it's
+	 * possible we might be called without an IPI, so it might be
+	 * safer to figure out how to make kgdb_breakpoint() work
+	 * properly here.
+	 */
+	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void __weak kgdb_roundup_cpus(void)
+{
+	call_single_data_t *csd;
+	int this_cpu = raw_smp_processor_id();
+	int cpu;
+	int ret;
+
+	for_each_online_cpu(cpu) {
+		/* No need to roundup ourselves */
+		if (cpu == this_cpu)
+			continue;
+
+		csd = &per_cpu(kgdb_roundup_csd, cpu);
+
+		/*
+		 * If it didn't round up last time, don't try again
+		 * since smp_call_function_single_async() will block.
+		 *
+		 * If rounding_up is false then we know that the
+		 * previous call must have at least started and that
+		 * means smp_call_function_single_async() won't block.
+		 */
+		if (kgdb_info[cpu].rounding_up)
+			continue;
+		kgdb_info[cpu].rounding_up = true;
+
+		csd->func = kgdb_call_nmi_hook;
+		ret = smp_call_function_single_async(cpu, csd);
+		if (ret)
+			kgdb_info[cpu].rounding_up = false;
+	}
+}
+
+#endif
+
 /*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
@@ -535,6 +592,8 @@ return_normal:
 				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--;
@@ -593,7 +652,7 @@ return_normal:
 
 	/* Signal the other CPUs to enter kgdb_wait() */
 	else if ((!kgdb_single_step) && kgdb_do_roundup)
-		kgdb_roundup_cpus(flags);
+		kgdb_roundup_cpus();
 #endif
 
 	/*
@@ -667,6 +726,8 @@ kgdb_restore:
 	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--;
@@ -747,6 +808,8 @@ int kgdb_nmicallback(int cpu, void *regs)
 	struct kgdb_state kgdb_var;
 	struct kgdb_state *ks = &kgdb_var;
 
+	kgdb_info[cpu].rounding_up = false;
+
 	memset(ks, 0, sizeof(struct kgdb_state));
 	ks->cpu			= cpu;
 	ks->linux_regs		= regs;
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 127d9bc49fb4..b4a7c326d546 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -42,6 +42,7 @@ struct debuggerinfo_struct {
 	int			ret_state;
 	int			irq_depth;
 	int			enter_kgdb;
+	bool			rounding_up;
 };
 
 extern struct debuggerinfo_struct kgdb_info[];
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);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index d72b32c66f7d..82a3b32a7cfc 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -658,7 +658,7 @@ static void kdb_cmderror(int diag)
  */
 struct defcmd_set {
 	int count;
-	int usable;
+	bool usable;
 	char *name;
 	char *usage;
 	char *help;
@@ -666,7 +666,7 @@ struct defcmd_set {
 };
 static struct defcmd_set *defcmd_set;
 static int defcmd_set_count;
-static int defcmd_in_progress;
+static bool defcmd_in_progress;
 
 /* Forward references */
 static int kdb_exec_defcmd(int argc, const char **argv);
@@ -676,9 +676,9 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 	struct defcmd_set *s = defcmd_set + defcmd_set_count - 1;
 	char **save_command = s->command;
 	if (strcmp(argv0, "endefcmd") == 0) {
-		defcmd_in_progress = 0;
+		defcmd_in_progress = false;
 		if (!s->count)
-			s->usable = 0;
+			s->usable = false;
 		if (s->usable)
 			/* macros are always safe because when executed each
 			 * internal command re-enters kdb_parse() and is
@@ -695,7 +695,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 	if (!s->command) {
 		kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
 			   cmdstr);
-		s->usable = 0;
+		s->usable = false;
 		return KDB_NOTIMP;
 	}
 	memcpy(s->command, save_command, s->count * sizeof(*(s->command)));
@@ -737,7 +737,7 @@ static int kdb_defcmd(int argc, const char **argv)
 	       defcmd_set_count * sizeof(*defcmd_set));
 	s = defcmd_set + defcmd_set_count;
 	memset(s, 0, sizeof(*s));
-	s->usable = 1;
+	s->usable = true;
 	s->name = kdb_strdup(argv[1], GFP_KDB);
 	if (!s->name)
 		goto fail_name;
@@ -756,7 +756,7 @@ static int kdb_defcmd(int argc, const char **argv)
 		s->help[strlen(s->help)-1] = '\0';
 	}
 	++defcmd_set_count;
-	defcmd_in_progress = 1;
+	defcmd_in_progress = true;
 	kfree(save_defcmd_set);
 	return 0;
 fail_help: