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, 12 insertions, 4 deletions

diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index b3a6943127bc..4432db6d0b99 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -10,6 +10,7 @@
 #include <linux/console.h>
 #include <linux/kvm_para.h>
 #include <linux/rcu_notifier.h>
+#include <linux/smp.h>
 
 //////////////////////////////////////////////////////////////////////////////
 //
@@ -371,6 +372,7 @@ static void rcu_dump_cpu_stacks(void)
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rnp) {
+		printk_deferred_enter();
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		for_each_leaf_node_possible_cpu(rnp, cpu)
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -380,6 +382,7 @@ static void rcu_dump_cpu_stacks(void)
 					dump_cpu_task(cpu);
 			}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		printk_deferred_exit();
 	}
 }
 
@@ -502,7 +505,7 @@ static void print_cpu_stall_info(int cpu)
 	}
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
 	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
-			rcu_dynticks_in_eqs(ct_dynticks_cpu(cpu));
+			rcu_watching_snap_in_eqs(ct_rcu_watching_cpu(cpu));
 	rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j);
 	if (rcuc_starved)
 		// Print signed value, as negative values indicate a probable bug.
@@ -516,8 +519,8 @@ static void print_cpu_stall_info(int cpu)
 			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
 				"!."[!delta],
 	       ticks_value, ticks_title,
-	       ct_dynticks_cpu(cpu) & 0xffff,
-	       ct_dynticks_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu),
+	       ct_rcu_watching_cpu(cpu) & 0xffff,
+	       ct_nesting_cpu(cpu), ct_nmi_nesting_cpu(cpu),
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
 	       rcuc_starved ? buf : "",
@@ -728,6 +731,9 @@ static void print_cpu_stall(unsigned long gps)
 	set_preempt_need_resched();
 }
 
+static bool csd_lock_suppress_rcu_stall;
+module_param(csd_lock_suppress_rcu_stall, bool, 0644);
+
 static void check_cpu_stall(struct rcu_data *rdp)
 {
 	bool self_detected;
@@ -800,7 +806,9 @@ static void check_cpu_stall(struct rcu_data *rdp)
 			return;
 
 		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
-		if (self_detected) {
+		if (READ_ONCE(csd_lock_suppress_rcu_stall) && csd_lock_is_stuck()) {
+			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);
+		} else if (self_detected) {
 			/* We haven't checked in, so go dump stack. */
 			print_cpu_stall(gps);
 		} else {