diff mbox series

[2/4] locking/csd_lock: Provide an indication of ongoing CSD-lock stall

Message ID 20240816043917.26537-2-neeraj.upadhyay@kernel.org (mailing list archive)
State New, archived
Headers show
Series CSD-lock diagnostics updates for v6.12 | expand

Commit Message

Neeraj Upadhyay Aug. 16, 2024, 4:39 a.m. UTC 
From: "Paul E. McKenney" <paulmck@kernel.org>

If a CSD-lock stall goes on long enough, it will cause an RCU CPU
stall warning.  This additional warning provides much additional
console-log traffic and little additional information.  Therefore,
provide a new csd_lock_is_stuck() function that returns true if there
is an ongoing CSD-lock stall.  This function will be used by the RCU
CPU stall warnings to provide a one-line indication of the stall when
this function returns true.

[ neeraj.upadhyay: Apply Rik van Riel feedback. ]
[ neeraj.upadhyay: Apply kernel test robot feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Imran Khan <imran.f.khan@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leonardo Bras <leobras@redhat.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
---
 include/linux/smp.h |  6 ++++++
 kernel/smp.c        | 16 ++++++++++++++++
 lib/Kconfig.debug   |  1 +
 3 files changed, 23 insertions(+)
diff mbox series

Patch

diff --git a/include/linux/smp.h b/include/linux/smp.h
index fcd61dfe2af3..3871bd32018f 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -294,4 +294,10 @@  int smpcfd_prepare_cpu(unsigned int cpu);
 int smpcfd_dead_cpu(unsigned int cpu);
 int smpcfd_dying_cpu(unsigned int cpu);
 
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+bool csd_lock_is_stuck(void);
+#else
+static inline bool csd_lock_is_stuck(void) { return false; }
+#endif
+
 #endif /* __LINUX_SMP_H */
diff --git a/kernel/smp.c b/kernel/smp.c
index e87953729230..202cda4d2a55 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -208,6 +208,19 @@  static int csd_lock_wait_getcpu(call_single_data_t *csd)
 	return -1;
 }
 
+static atomic_t n_csd_lock_stuck;
+
+/**
+ * csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long?
+ *
+ * Returns @true if a CSD-lock acquisition is stuck and has been stuck
+ * long enough for a "non-responsive CSD lock" message to be printed.
+ */
+bool csd_lock_is_stuck(void)
+{
+	return !!atomic_read(&n_csd_lock_stuck);
+}
+
 /*
  * Complain if too much time spent waiting.  Note that only
  * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
@@ -229,6 +242,7 @@  static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
 		cpu = csd_lock_wait_getcpu(csd);
 		pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n",
 			 *bug_id, raw_smp_processor_id(), cpu);
+		atomic_dec(&n_csd_lock_stuck);
 		return true;
 	}
 
@@ -252,6 +266,8 @@  static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
 	pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n",
 		 firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta,
 		 cpu, csd->func, csd->info);
+	if (firsttime)
+		atomic_inc(&n_csd_lock_stuck);
 	/*
 	 * If the CSD lock is still stuck after 5 minutes, it is unlikely
 	 * to become unstuck. Use a signed comparison to avoid triggering
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a30c03a66172..4e5f61cba8e4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1614,6 +1614,7 @@  config SCF_TORTURE_TEST
 config CSD_LOCK_WAIT_DEBUG
 	bool "Debugging for csd_lock_wait(), called from smp_call_function*()"
 	depends on DEBUG_KERNEL
+	depends on SMP
 	depends on 64BIT
 	default n
 	help