Merge remote-tracking branch 'upstream-ssh/scheduler-call-fastpath' into integration

# Conflicts:
#	esphome/core/application.h

esphome/core/application.h

@@ -392,7 +392,7 @@ class Application {
   void enable_component_loop_(Component *component);
   void enable_pending_loops_();
   void activate_looping_component_(uint16_t index);
-  inline uint32_t ESPHOME_ALWAYS_INLINE scheduler_tick_(uint32_t now);
+  inline Scheduler::CallResult ESPHOME_ALWAYS_INLINE scheduler_tick_(uint32_t now);
 
   // RAII guard for a component loop phase. Constructor processes any pending
   // enable_loop requests from ISRs and marks in_loop_ so reentrant
@@ -513,10 +513,11 @@ extern Application App;  // NOLINT(cppcoreguidelines-avoid-non-const-global-vari
 // Application::loop() tick regardless of whether a component phase runs, so
 // scheduler items fire at their requested cadence even when the caller has
 // raised loop_interval_ for power savings (see Application::loop()).
-// Returns the timestamp of the last scheduler item that ran (or `now`
-// unchanged if none ran), so the caller's WDT feed stays monotonic with the
-// per-item feeds inside scheduler.call() without an extra millis().
-inline uint32_t ESPHOME_ALWAYS_INLINE Application::scheduler_tick_(uint32_t now) {
+// Returns the advanced `now` (for monotonic wdt feed) alongside the Scheduler's
+// 64-bit `now_64` (or 0 if any item fired — then stale). The main loop forwards
+// now_64 to next_schedule_in() to avoid a second esp_timer_get_time() MMIO read
+// per iteration; 0 means "compute fresh".
+inline Scheduler::CallResult ESPHOME_ALWAYS_INLINE Application::scheduler_tick_(uint32_t now) {
 #ifdef USE_HOST
   // Drain wake notifications first to clear socket for next wake.
   wake_drain_notifications();
@@ -561,11 +562,12 @@ inline void ESPHOME_ALWAYS_INLINE Application::loop() {
   // Phase A: always service the scheduler. Decouples scheduler cadence from
   // loop_interval_ so raised intervals (for power savings) don't drag scheduled
   // items forward. A tick that only runs the scheduler is cheap.
-  // scheduler_tick_ returns the timestamp of the last scheduler item that ran
-  // (advanced by its per-item feeds) or `now` unchanged. We adopt it as `now`
-  // so the gate check and WDT feed both reflect actual elapsed time after
-  // scheduler dispatch, without an extra millis() call.
-  uint32_t now = this->scheduler_tick_(MillisInternal::get());
+  // scheduler_tick_ returns the advanced `now` (for wdt monotonicity) plus the
+  // 64-bit `now_64` Scheduler::call() already computed — forward that to the
+  // next_schedule_in() call below so we don't re-read esp_timer_get_time() a
+  // second time per iteration. 0 means "stale, recompute".
+  const Scheduler::CallResult sched_result = this->scheduler_tick_(MillisInternal::get());
+  uint32_t now = sched_result.now;
 #ifdef USE_RUNTIME_STATS
   // Capture immediately after scheduler_tick_ returns so the post-scheduler
   // feed_wdt_with_time slice can be separated from the scheduler slice in
@@ -685,7 +687,7 @@ inline void ESPHOME_ALWAYS_INLINE Application::loop() {
     const uint32_t elapsed_since_phase = now - this->last_loop_;
     const uint32_t until_phase =
         (elapsed_since_phase >= this->loop_interval_) ? 0 : (this->loop_interval_ - elapsed_since_phase);
-    const uint32_t until_sched = this->scheduler.next_schedule_in(now).value_or(until_phase);
+    const uint32_t until_sched = this->scheduler.next_schedule_in(now, sched_result.now_64).value_or(until_phase);
     delay_time = std::min(until_phase, until_sched);
   }
   // All platforms route loop yields through the platform wake primitive.

esphome/core/scheduler.cpp

@@ -412,7 +412,7 @@ bool HOT Scheduler::cancel_retry(Component *component, uint32_t id) {
 
 #pragma GCC diagnostic pop  // End suppression of deprecated RetryResult warnings
 
-optional<uint32_t> HOT Scheduler::next_schedule_in(uint32_t now) {
+optional<uint32_t> HOT Scheduler::next_schedule_in(uint32_t now, uint64_t now_64) {
   // IMPORTANT: This method should only be called from the main thread (loop task).
   // Accesses items_[0] and the fast-path empty checks without holding a lock, which
   // is only safe from the main thread. Other threads must not call this method.
@@ -455,7 +455,12 @@ optional<uint32_t> HOT Scheduler::next_schedule_in(uint32_t now) {
     return {};
 
   SchedulerItem *item = this->items_[0];
-  const auto now_64 = this->millis_64_from_(now);
+  // If the caller did not pass a pre-computed now_64 (or passed the 0
+  // sentinel, meaning call() advanced past it by firing items), read the
+  // clock fresh. Otherwise reuse the passed value to avoid a second
+  // esp_timer_get_time() MMIO read per main-loop iteration.
+  if (now_64 == 0)
+    now_64 = this->millis_64_from_(now);
   const uint64_t next_exec = item->get_next_execution();
   if (next_exec < now_64)
     return 0;
@@ -566,7 +571,7 @@ void HOT Scheduler::process_defer_queue_slow_path_(uint32_t &now) {
 }
 #endif /* not ESPHOME_THREAD_SINGLE */
 
-uint32_t HOT Scheduler::call(uint32_t now) {
+Scheduler::CallResult HOT Scheduler::call(uint32_t now) {
 #ifndef ESPHOME_THREAD_SINGLE
   this->process_defer_queue_(now);
 #endif /* not ESPHOME_THREAD_SINGLE */
@@ -577,6 +582,10 @@ uint32_t HOT Scheduler::call(uint32_t now) {
 
   // Track if any items were added to to_add_ during callbacks
   bool has_added_items = false;
+  // Track whether we advanced `now` via execute_item_(). If we did, `now_64`
+  // is stale by the time we return and next_schedule_in() must recompute —
+  // signal that by writing 0 to *now_64_out.
+  bool executed_any_item = false;
 
 #ifdef ESPHOME_DEBUG_SCHEDULER
   static uint64_t last_print = 0;
@@ -689,6 +698,7 @@ uint32_t HOT Scheduler::call(uint32_t now) {
     //  - timeouts/intervals get added, potentially invalidating vector pointers
     //  - timeouts/intervals get cancelled
     now = this->execute_item_(item, now);
+    executed_any_item = true;
 
     LockGuard guard{this->lock_};
 
@@ -745,7 +755,10 @@ uint32_t HOT Scheduler::call(uint32_t now) {
 #endif
   // execute_item_() advances `now` as items fire; return it so the caller
   // stays monotonic with last_wdt_feed_.
-  return now;
+  // The returned now_64 is only usable if NO items fired — execute_item_ only
+  // advances the uint32 `now`, leaving our local now_64 stale. Signal stale
+  // with the 0 sentinel so next_schedule_in() reads the clock fresh.
+  return CallResult{now, executed_any_item ? 0 : now_64};
 }
 void HOT Scheduler::process_to_add_slow_path_() {
   LockGuard guard{this->lock_};

esphome/core/scheduler.h

@@ -122,15 +122,32 @@ class Scheduler {
 
   // Calculate when the next scheduled item should run.
   // @param now On ESP32, unused for 64-bit extension (native); on other platforms, extended to 64-bit via rollover.
+  // @param now_64 Optional pre-computed 64-bit timestamp from a recent call() (see CallResult).
+  //        Pass 0 (sentinel) to have this method compute now_64 freshly. Non-zero values are trusted and
+  //        used directly, saving a millis_64() / esp_timer_get_time() MMIO read when the caller already
+  //        has a fresh value from the same loop iteration.
   // Returns the time in milliseconds until the next scheduled item, or nullopt if no items.
   // This method performs cleanup of removed items before checking the schedule.
   // IMPORTANT: This method should only be called from the main thread (loop task).
-  optional<uint32_t> next_schedule_in(uint32_t now);
+  optional<uint32_t> next_schedule_in(uint32_t now, uint64_t now_64 = 0);
+
+  // Result of Scheduler::call().
+  //   now    – advanced uint32 millis timestamp (monotonic with the caller's wdt feed).
+  //   now_64 – 64-bit millis value Scheduler used for item dispatch, OR 0 if any item
+  //            fired (in that case now_64 is stale because execute_item_ only advances
+  //            the uint32 `now`). A subsequent next_schedule_in() treats 0 as "compute
+  //            fresh" and non-zero as "reuse this value", saving a second millis_64()
+  //            / esp_timer_get_time() call per main-loop iteration.
+  struct CallResult {
+    uint32_t now;
+    uint64_t now_64;
+  };
 
   // Execute all scheduled items that are ready
   // @param now Fresh timestamp from millis() - must not be stale/cached
-  // @return Timestamp of the last item that ran, or `now` unchanged if none ran.
-  uint32_t call(uint32_t now);
+  // @return Both advanced `now` (for wdt monotonicity) and `now_64` (for pipe-through
+  //         to next_schedule_in()). See CallResult.
+  CallResult call(uint32_t now);
 
   // Move items from to_add_ into the main heap.
   // IMPORTANT: This method should only be called from the main thread (loop task).