Merge tag 'rcu.release.v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux

Pull RCU updates from Neeraj Upadhyay:
 "Context tracking:
   - rename context tracking state related symbols and remove references
     to "dynticks" in various context tracking state variables and
     related helpers
   - force context_tracking_enabled_this_cpu() to be inlined to avoid
     leaving a noinstr section

  CSD lock:
   - enhance CSD-lock diagnostic reports
   - add an API to provide an indication of ongoing CSD-lock stall

  nocb:
   - update and simplify RCU nocb code to handle (de-)offloading of
     callbacks only for offline CPUs
   - fix RT throttling hrtimer being armed from offline CPU

  rcutorture:
   - remove redundant rcu_torture_ops get_gp_completed fields
   - add SRCU ->same_gp_state and ->get_comp_state functions
   - add generic test for NUM_ACTIVE_*RCU_POLL* for testing RCU and SRCU
     polled grace periods
   - add CFcommon.arch for arch-specific Kconfig options
   - print number of update types in rcu_torture_write_types()
   - add rcutree.nohz_full_patience_delay testing to the TREE07 scenario
   - add a stall_cpu_repeat module parameter to test repeated CPU stalls
   - add argument to limit number of CPUs a guest OS can use in
     torture.sh

  rcustall:
   - abbreviate RCU CPU stall warnings during CSD-lock stalls
   - Allow dump_cpu_task() to be called without disabling preemption
   - defer printing stall-warning backtrace when holding rcu_node lock

  srcu:
   - make SRCU gp seq wrap-around faster
   - add KCSAN checks for concurrent updates to ->srcu_n_exp_nodelay and
     ->reschedule_count which are used in heuristics governing
     auto-expediting of normal SRCU grace periods and
     grace-period-state-machine delays
   - mark idle SRCU-barrier callbacks to help identify stuck
     SRCU-barrier callback

  rcu tasks:
   - remove RCU Tasks Rude asynchronous APIs as they are no longer used
   - stop testing RCU Tasks Rude asynchronous APIs
   - fix access to non-existent percpu regions
   - check processor-ID assumptions during chosen CPU calculation for
     callback enqueuing
   - update description of rtp->tasks_gp_seq grace-period sequence
     number
   - add rcu_barrier_cb_is_done() to identify whether a given
     rcu_barrier callback is stuck
   - mark idle Tasks-RCU-barrier callbacks
   - add *torture_stats_print() functions to print detailed diagnostics
     for Tasks-RCU variants
   - capture start time of rcu_barrier_tasks*() operation to help
     distinguish a hung barrier operation from a long series of barrier
     operations

  refscale:
   - add a TINY scenario to support tests of Tiny RCU and Tiny
     SRCU
   - optimize process_durations() operation

  rcuscale:
   - dump stacks of stalled rcu_scale_writer() instances and
     grace-period statistics when rcu_scale_writer() stalls
   - mark idle RCU-barrier callbacks to identify stuck RCU-barrier
     callbacks
   - print detailed grace-period and barrier diagnostics on
     rcu_scale_writer() hangs for Tasks-RCU variants
   - warn if async module parameter is specified for RCU implementations
     that do not have async primitives such as RCU Tasks Rude
   - make all writer tasks report upon hang
   - tolerate repeated GFP_KERNEL failure in rcu_scale_writer()
   - use special allocator for rcu_scale_writer()
   - NULL out top-level pointers to heap memory to avoid double-free
     bugs on modprobe failures
   - maintain per-task instead of per-CPU callbacks count to avoid any
     issues with migration of either tasks or callbacks
   - constify struct ref_scale_ops

  Fixes:
   - use system_unbound_wq for kfree_rcu work to avoid disturbing
     isolated CPUs

  Misc:
   - warn on unexpected rcu_state.srs_done_tail state
   - better define "atomic" for list_replace_rcu() and
     hlist_replace_rcu() routines
   - annotate struct kvfree_rcu_bulk_data with __counted_by()"

* tag 'rcu.release.v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux: (90 commits)
  rcu: Defer printing stall-warning backtrace when holding rcu_node lock
  rcu/nocb: Remove superfluous memory barrier after bypass enqueue
  rcu/nocb: Conditionally wake up rcuo if not already waiting on GP
  rcu/nocb: Fix RT throttling hrtimer armed from offline CPU
  rcu/nocb: Simplify (de-)offloading state machine
  context_tracking: Tag context_tracking_enabled_this_cpu() __always_inline
  context_tracking, rcu: Rename rcu_dyntick trace event into rcu_watching
  rcu: Update stray documentation references to rcu_dynticks_eqs_{enter, exit}()
  rcu: Rename rcu_momentary_dyntick_idle() into rcu_momentary_eqs()
  rcu: Rename rcu_implicit_dynticks_qs() into rcu_watching_snap_recheck()
  rcu: Rename dyntick_save_progress_counter() into rcu_watching_snap_save()
  rcu: Rename struct rcu_data .exp_dynticks_snap into .exp_watching_snap
  rcu: Rename struct rcu_data .dynticks_snap into .watching_snap
  rcu: Rename rcu_dynticks_zero_in_eqs() into rcu_watching_zero_in_eqs()
  rcu: Rename rcu_dynticks_in_eqs_since() into rcu_watching_snap_stopped_since()
  rcu: Rename rcu_dynticks_in_eqs() into rcu_watching_snap_in_eqs()
  rcu: Rename rcu_dynticks_eqs_online() into rcu_watching_online()
  context_tracking, rcu: Rename rcu_dynticks_curr_cpu_in_eqs() into rcu_is_watching_curr_cpu()
  context_tracking, rcu: Rename rcu_dynticks_task*() into rcu_task*()
  refscale: Constify struct ref_scale_ops
  ...

1 files changed, 33 insertions, 5 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index aaffecdad319..f25e20617b7e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -208,12 +208,25 @@ 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,
  * so waiting on other types gets much less information.
  */
-static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id)
+static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages)
 {
 	int cpu = -1;
 	int cpux;
@@ -229,15 +242,26 @@ 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;
 	}
 
 	ts2 = sched_clock();
 	/* How long since we last checked for a stuck CSD lock.*/
 	ts_delta = ts2 - *ts1;
-	if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0))
+	if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) *
+			       (!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) ||
+		   csd_lock_timeout_ns == 0))
 		return false;
 
+	if (ts0 > ts2) {
+		/* Our own sched_clock went backward; don't blame another CPU. */
+		ts_delta = ts0 - ts2;
+		pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta);
+		*ts1 = ts2;
+		return false;
+	}
+
 	firsttime = !*bug_id;
 	if (firsttime)
 		*bug_id = atomic_inc_return(&csd_bug_count);
@@ -249,9 +273,12 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
 	cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
 	/* How long since this CSD lock was stuck. */
 	ts_delta = ts2 - ts0;
-	pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n",
-		 firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta,
+	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);
+	(*nmessages)++;
+	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
@@ -290,12 +317,13 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
  */
 static void __csd_lock_wait(call_single_data_t *csd)
 {
+	unsigned long nmessages = 0;
 	int bug_id = 0;
 	u64 ts0, ts1;
 
 	ts1 = ts0 = sched_clock();
 	for (;;) {
-		if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id))
+		if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages))
 			break;
 		cpu_relax();
 	}