xtensa: move saved FPU and HIFI registers to end of BSA

This moves the block of FPU and HIFI registers in the Base Save
Area (BSA), used during interrupts and exceptions, to the end of
the block. This is done to minimize code usage in the vector
text section. During interrupt entrance, the code stores a small
set of registers first before jumping to the long handler. When
the offset to these registers from the beginning of BSA is small
enough, the compiler will emit S32I.N instead of S32I. This
saves us one byte per store (2 vs 3 bytes). This is mainly done
to avoid overflowing the vector text area.

Signed-off-by: Daniel Leung <daniel.leung@intel.com>

Author: dcpleung

arch/xtensa/include/xtensa_asm2_context.h

@@ -152,6 +152,31 @@
  * are saved after the BSA.
  */
 struct xtensa_irq_base_save_area {
+#if XCHAL_HAVE_THREADPTR
+	uintptr_t threadptr;
+#endif
+
+#if XCHAL_HAVE_S32C1I
+	uintptr_t scompare1;
+#endif
+
+	uintptr_t exccause;
+	uintptr_t excvaddr;
+
+#if XCHAL_HAVE_LOOPS
+	uintptr_t lcount;
+	uintptr_t lend;
+	uintptr_t lbeg;
+#endif
+
+	uintptr_t sar;
+	uintptr_t ps;
+	uintptr_t pc;
+	uintptr_t a0;
+	uintptr_t scratch;
+	uintptr_t a2;
+	uintptr_t a3;
+
 #if XCHAL_HAVE_FP && defined(CONFIG_CPU_HAS_FPU) && defined(CONFIG_FPU_SHARING)
 	uintptr_t fcr;
 	uintptr_t fsr;
@@ -185,31 +210,6 @@ struct xtensa_irq_base_save_area {
 	uint8_t  hifi[XCHAL_CP1_SA_SIZE + XCHAL_CP1_SA_ALIGN];
 #endif
 
-#if XCHAL_HAVE_THREADPTR
-	uintptr_t threadptr;
-#endif
-
-#if XCHAL_HAVE_S32C1I
-	uintptr_t scompare1;
-#endif
-
-	uintptr_t exccause;
-	uintptr_t excvaddr;
-
-#if XCHAL_HAVE_LOOPS
-	uintptr_t lcount;
-	uintptr_t lend;
-	uintptr_t lbeg;
-#endif
-
-	uintptr_t sar;
-	uintptr_t ps;
-	uintptr_t pc;
-	uintptr_t a0;
-	uintptr_t scratch;
-	uintptr_t a2;
-	uintptr_t a3;
-
 	uintptr_t padding[_BSA_PADDING_NEEDED / sizeof(uintptr_t)];
 
 	uintptr_t caller_a0;