From 3241912ee8dcb1416ef9d2109a733507c6ef0fd5 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 11 Nov 2025 01:18:25 +0000
Subject: [PATCH 1/3] Initial plan


From 4dc072c04c70f88fa7fcb3cd4558cb06e51b66c9 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 11 Nov 2025 01:24:47 +0000
Subject: [PATCH 2/3] [libcpu][cortex-a] Improve FPU stack initialization
 implementation

Co-authored-by: BernardXiong <1241087+BernardXiong@users.noreply.github.com>
---
 libcpu/arm/cortex-a/cpuport.h |  5 +++++
 libcpu/arm/cortex-a/stack.c   | 13 ++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/libcpu/arm/cortex-a/cpuport.h b/libcpu/arm/cortex-a/cpuport.h
index 5fb067999cc..c18ae246b20 100644
--- a/libcpu/arm/cortex-a/cpuport.h
+++ b/libcpu/arm/cortex-a/cpuport.h
@@ -72,6 +72,11 @@ struct rt_hw_stack
 #define E_Bit       (1<<9)
 #define J_Bit       (1<<24)
 
+/* VFP/NEON register count for FPU context */
+#ifndef VFP_DATA_NR
+#define VFP_DATA_NR 64  /* 32 double-precision registers = 64 words */
+#endif
+
 #ifdef RT_USING_SMP
 typedef union {
     unsigned long slock;
diff --git a/libcpu/arm/cortex-a/stack.c b/libcpu/arm/cortex-a/stack.c
index 4c955677f87..0117514c617 100644
--- a/libcpu/arm/cortex-a/stack.c
+++ b/libcpu/arm/cortex-a/stack.c
@@ -31,6 +31,9 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
                              rt_uint8_t *stack_addr, void *texit)
 {
     rt_uint32_t *stk;
+#ifdef RT_USING_FPU
+    rt_uint32_t i;
+#endif
 
     stack_addr += sizeof(rt_uint32_t);
     stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
@@ -61,7 +64,15 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
     *(--stk) = 0;       /* user sp*/
 #endif
 #ifdef RT_USING_FPU
-    *(--stk) = 0;       /* not use fpu*/
+    /* FPU context initialization matches context_gcc.S restore order:
+     * Stack layout (high to low): FPEXC -> FPSCR -> D16-D31 -> D0-D15
+     */
+    for (i = 0; i < VFP_DATA_NR; i++)
+    {
+        *(--stk) = 0;   /* Initialize D0-D31 (64 words for 32 double regs) */
+    }
+    *(--stk) = 0;       /* FPSCR: Floating-Point Status and Control Register */
+    *(--stk) = 0x40000000;  /* FPEXC: Enable FPU (bit 30 = EN) */
 #endif
 
     /* return task's current stack address */

From 06eae477b8b83774e32814cfa7bc87e65c53a439 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 11 Nov 2025 01:31:53 +0000
Subject: [PATCH 3/3] [libcpu][cortex-a] Replace FPU init loop with rt_memset

Co-authored-by: BernardXiong <1241087+BernardXiong@users.noreply.github.com>
---
 libcpu/arm/cortex-a/stack.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/libcpu/arm/cortex-a/stack.c b/libcpu/arm/cortex-a/stack.c
index 0117514c617..5bb57ca4dd4 100644
--- a/libcpu/arm/cortex-a/stack.c
+++ b/libcpu/arm/cortex-a/stack.c
@@ -31,9 +31,6 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
                              rt_uint8_t *stack_addr, void *texit)
 {
     rt_uint32_t *stk;
-#ifdef RT_USING_FPU
-    rt_uint32_t i;
-#endif
 
     stack_addr += sizeof(rt_uint32_t);
     stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
@@ -67,10 +64,8 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
     /* FPU context initialization matches context_gcc.S restore order:
      * Stack layout (high to low): FPEXC -> FPSCR -> D16-D31 -> D0-D15
      */
-    for (i = 0; i < VFP_DATA_NR; i++)
-    {
-        *(--stk) = 0;   /* Initialize D0-D31 (64 words for 32 double regs) */
-    }
+    stk -= VFP_DATA_NR;
+    rt_memset(stk, 0, VFP_DATA_NR * sizeof(rt_uint32_t));  /* Initialize D0-D31 (64 words for 32 double regs) */
     *(--stk) = 0;       /* FPSCR: Floating-Point Status and Control Register */
     *(--stk) = 0x40000000;  /* FPEXC: Enable FPU (bit 30 = EN) */
 #endif