[arm64] add hw thread self (#8942)

* [libcpu] arm64: Add hardware thread_self support

This patch introduces hardware-based thread self-identification
for the AArch64 architecture. It optimizes thread management by
using hardware registers to store and access the current thread's
pointer, reducing overhead and improving overall performance.

Changes include:
- Added `ARCH_USING_HW_THREAD_SELF` configuration option.
- Modified `rtdef.h`, `rtsched.h` to conditionally include
  `critical_switch_flag` based on the new config.
- Updated context management in `context_gcc.S`, `cpuport.h`
  to support hardware-based thread self.
- Enhanced `scheduler_mp.c` and `thread.c` to leverage the new
  hardware thread self feature.

These modifications ensure better scheduling and thread handling,
particularly in multi-core environments, by minimizing the
software overhead associated with thread management.

Signed-off-by: Shell <[email protected]>

* fixup: address suggestion

* fixup: rt_current_thread as global

* scheduler: add cpu object for UP scheduler

Also, maintain the rt_current_thread in cpu object on UP scheduler.

---------

Signed-off-by: Shell <[email protected]>

3 files changed, 24 insertions, 5 deletions

diff --git a/include/rtdef.h b/include/rtdef.h
index f0918d5dd6..72b61de7aa 100644
--- a/include/rtdef.h
+++ b/include/rtdef.h
@@ -740,8 +740,10 @@ struct rt_cpu
         struct rt_thread        *current_thread;
 
         rt_uint8_t              irq_switch_flag:1;
-        rt_uint8_t              critical_switch_flag:1;
         rt_uint8_t              sched_lock_flag:1;
+#ifndef ARCH_USING_HW_THREAD_SELF
+        rt_uint8_t              critical_switch_flag:1;
+#endif /* ARCH_USING_HW_THREAD_SELF */
 
         rt_uint8_t              current_priority;
         rt_list_t               priority_table[RT_THREAD_PRIORITY_MAX];
@@ -763,10 +765,19 @@ struct rt_cpu
     struct rt_cpu_usage_stats   cpu_stat;
 #endif
 };
-typedef struct rt_cpu *rt_cpu_t;
+
+#else /* !RT_USING_SMP */
+struct rt_cpu
+{
+    struct rt_thread            *current_thread;
+};
 
 #endif /* RT_USING_SMP */
 
+typedef struct rt_cpu *rt_cpu_t;
+/* Noted: As API to reject writing to this variable from application codes */
+#define rt_current_thread rt_thread_self()
+
 struct rt_thread;
 
 #ifdef RT_USING_SMART
diff --git a/include/rtsched.h b/include/rtsched.h
index 9e31320095..786ca8b54e 100644
--- a/include/rtsched.h
+++ b/include/rtsched.h
@@ -56,6 +56,10 @@ struct rt_sched_thread_ctx
     rt_uint8_t                  sched_flag_locked:1;    /**< calling thread have the scheduler locked */
     rt_uint8_t                  sched_flag_ttmr_set:1;  /**< thread timer is start */
 
+#ifdef ARCH_USING_HW_THREAD_SELF
+    rt_uint8_t                  critical_switch_flag:1; /**< critical switch pending */
+#endif /* ARCH_USING_HW_THREAD_SELF */
+
 #ifdef RT_USING_SMP
     rt_uint8_t                  bind_cpu;               /**< thread is bind to cpu */
     rt_uint8_t                  oncpu;                  /**< process on cpu */
@@ -170,6 +174,7 @@ rt_err_t rt_sched_thread_timer_stop(struct rt_thread *thread);
 rt_err_t rt_sched_thread_timer_start(struct rt_thread *thread);
 void rt_sched_insert_thread(struct rt_thread *thread);
 void rt_sched_remove_thread(struct rt_thread *thread);
+struct rt_thread *rt_sched_thread_self(void);
 
 #endif /* defined(__RT_KERNEL_SOURCE__) || defined(__RT_IPC_SOURCE__) */
 
diff --git a/include/rtthread.h b/include/rtthread.h
index 1cad47931a..386fbaf47e 100644
--- a/include/rtthread.h
+++ b/include/rtthread.h
@@ -669,6 +669,12 @@ rt_err_t  rt_device_control(rt_device_t dev, int cmd, void *arg);
 void rt_interrupt_enter(void);
 void rt_interrupt_leave(void);
 
+/**
+ * CPU object
+ */
+struct rt_cpu *rt_cpu_self(void);
+struct rt_cpu *rt_cpu_index(int index);
+
 #ifdef RT_USING_SMP
 
 /*
@@ -679,9 +685,6 @@ rt_base_t rt_cpus_lock(void);
 void rt_cpus_unlock(rt_base_t level);
 void rt_cpus_lock_status_restore(struct rt_thread *thread);
 
-struct rt_cpu *rt_cpu_self(void);
-struct rt_cpu *rt_cpu_index(int index);
-
 #ifdef RT_USING_DEBUG
     rt_base_t rt_cpu_get_id(void);
 #else /* !RT_USING_DEBUG */