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, 8 insertions, 3 deletions

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b24db425f16d..31706e3293bc 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -137,6 +137,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 		sdp->srcu_cblist_invoking = false;
 		sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq;
 		sdp->srcu_gp_seq_needed_exp = ssp->srcu_sup->srcu_gp_seq;
+		sdp->srcu_barrier_head.next = &sdp->srcu_barrier_head;
 		sdp->mynode = NULL;
 		sdp->cpu = cpu;
 		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
@@ -247,7 +248,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_sup->srcu_cb_mutex);
 	mutex_init(&ssp->srcu_sup->srcu_gp_mutex);
 	ssp->srcu_idx = 0;
-	ssp->srcu_sup->srcu_gp_seq = 0;
+	ssp->srcu_sup->srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_barrier_seq = 0;
 	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
@@ -258,7 +259,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	if (!ssp->sda)
 		goto err_free_sup;
 	init_srcu_struct_data(ssp);
-	ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
+	ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
 		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC))
@@ -266,7 +267,8 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 		WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
 	}
 	ssp->srcu_sup->srcu_ssp = ssp;
-	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
+	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed,
+			SRCU_GP_SEQ_INITIAL_VAL); /* Init done. */
 	return 0;
 
 err_free_sda:
@@ -628,6 +630,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 		if (time_after(j, gpstart))
 			jbase += j - gpstart;
 		if (!jbase) {
+			ASSERT_EXCLUSIVE_WRITER(sup->srcu_n_exp_nodelay);
 			WRITE_ONCE(sup->srcu_n_exp_nodelay, READ_ONCE(sup->srcu_n_exp_nodelay) + 1);
 			if (READ_ONCE(sup->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
 				jbase = 1;
@@ -1560,6 +1563,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 	struct srcu_data *sdp;
 	struct srcu_struct *ssp;
 
+	rhp->next = rhp; // Mark the callback as having been invoked.
 	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
 	ssp = sdp->ssp;
 	if (atomic_dec_and_test(&ssp->srcu_sup->srcu_barrier_cpu_cnt))
@@ -1818,6 +1822,7 @@ static void process_srcu(struct work_struct *work)
 	} else {
 		j = jiffies;
 		if (READ_ONCE(sup->reschedule_jiffies) == j) {
+			ASSERT_EXCLUSIVE_WRITER(sup->reschedule_count);
 			WRITE_ONCE(sup->reschedule_count, READ_ONCE(sup->reschedule_count) + 1);
 			if (READ_ONCE(sup->reschedule_count) > srcu_max_nodelay)
 				curdelay = 1;