Merge tag 'timers-urgent-2024-07-26' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull timer migration updates from Thomas Gleixner:
 "Fixes and minor updates for the timer migration code:

   - Stop testing the group->parent pointer as it is not guaranteed to
     be stable over a chain of operations by design.

     This includes a warning which would be nice to have but it produces
     false positives due to the racy nature of the check.

   - Plug a race between CPUs going in and out of idle and a CPU hotplug
     operation. The latter can create and connect a new hierarchy level
     which is missed in the concurrent updates of CPUs which go into
     idle. As a result the events of such a CPU might not be processed
     and timers go stale.

     Cure it by splitting the hotplug operation into a prepare and
     online callback. The prepare callback is guaranteed to run on an
     online and therefore active CPU. This CPU updates the hierarchy and
     being online ensures that there is always at least one migrator
     active which handles the modified hierarchy correctly when going
     idle. The online callback which runs on the incoming CPU then just
     marks the CPU active and brings it into operation.

   - Improve tracing and polish the code further so it is more obvious
     what's going on"

* tag 'timers-urgent-2024-07-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timers/migration: Fix grammar in comment
  timers/migration: Spare write when nothing changed
  timers/migration: Rename childmask by groupmask to make naming more obvious
  timers/migration: Read childmask and parent pointer in a single place
  timers/migration: Use a single struct for hierarchy walk data
  timers/migration: Improve tracing
  timers/migration: Move hierarchy setup into cpuhotplug prepare callback
  timers/migration: Do not rely always on group->parent

include/linux/cpuhotplug.h

@@ -122,6 +122,7 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
+	CPUHP_TMIGR_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,

include/trace/events/timer_migration.h

@@ -43,7 +43,7 @@ TRACE_EVENT(tmigr_connect_child_parent,
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
 		__field( unsigned int,	num_children	)
-		__field( u32,		childmask	)
+		__field( u32,		groupmask	)
 	),
 
 	TP_fast_assign(
@@ -52,11 +52,11 @@ TRACE_EVENT(tmigr_connect_child_parent,
 		__entry->lvl		= child->parent->level;
 		__entry->numa_node	= child->parent->numa_node;
 		__entry->num_children	= child->parent->num_children;
-		__entry->childmask	= child->childmask;
+		__entry->groupmask	= child->groupmask;
 	),
 
-	TP_printk("group=%p childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->child,  __entry->childmask, __entry->parent,
+	TP_printk("group=%p groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->child,  __entry->groupmask, __entry->parent,
 		  __entry->lvl, __entry->numa_node, __entry->num_children)
 );
 
@@ -72,7 +72,7 @@ TRACE_EVENT(tmigr_connect_cpu_parent,
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
 		__field( unsigned int,	num_children	)
-		__field( u32,		childmask	)
+		__field( u32,		groupmask	)
 	),
 
 	TP_fast_assign(
@@ -81,11 +81,11 @@ TRACE_EVENT(tmigr_connect_cpu_parent,
 		__entry->lvl		= tmc->tmgroup->level;
 		__entry->numa_node	= tmc->tmgroup->numa_node;
 		__entry->num_children	= tmc->tmgroup->num_children;
-		__entry->childmask	= tmc->childmask;
+		__entry->groupmask	= tmc->groupmask;
 	),
 
-	TP_printk("cpu=%d childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->cpu,	 __entry->childmask, __entry->parent,
+	TP_printk("cpu=%d groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->cpu,	 __entry->groupmask, __entry->parent,
 		  __entry->lvl, __entry->numa_node, __entry->num_children)
 );