powerpc/setjmp: Add 64-bit support

Use 64-bit store/load instructions to save/restore the general-purpose
registers.

newlib/libc/include/machine/setjmp.h

@@ -173,11 +173,19 @@ _BEGIN_STD_C
 #endif
 
 #ifdef __PPC__
+#ifdef __powerpc64__
+#ifdef __ALTIVEC__
+#define _JBLEN 70
+#else
+#define _JBLEN 43
+#endif
+#else
 #ifdef __ALTIVEC__
 #define _JBLEN 64
 #else
 #define _JBLEN 32
 #endif
+#endif
 #define _JBTYPE double
 #endif
 

newlib/libc/machine/powerpc/setjmp.S

@@ -1,6 +1,7 @@
 /* This is a simple version of setjmp and longjmp for the PowerPC.
    Ian Lance Taylor, Cygnus Support, 9 Feb 1994.  
-   Modified by Jeff Johnston, Red Hat Inc. 2 Oct 2001. */
+   Modified by Jeff Johnston, Red Hat Inc. 2 Oct 2001.
+   Modified by Sebastian Huber, embedded brains GmbH. 22 Sep 2022.  */
 
 #include "ppc-asm.h"
 
@@ -40,6 +41,31 @@ FUNC_START(setjmp)
 	   stored.  Note that we are not adding 168 because the next
 	   store instruction uses an offset of 4.  */
 	addi	3,3,164
+#elif __powerpc64__
+	/* In the first store, add 16 to r3 so that the subsequent floating
+	   point stores are aligned on an 8 byte boundary and the Altivec
+	   stores are aligned on a 16 byte boundary.  */
+	stdu	1,16(3)		# offset 16
+	stdu	2,8(3)		# offset 24
+	stdu	13,8(3)		# offset 32
+	stdu	14,8(3)		# offset 40
+	stdu	15,8(3)		# offset 48
+	stdu	16,8(3)		# offset 56
+	stdu	17,8(3)		# offset 64
+	stdu	18,8(3)		# offset 72
+	stdu	19,8(3)		# offset 80
+	stdu	20,8(3)		# offset 88
+	stdu	21,8(3)		# offset 96
+	stdu	22,8(3)		# offset 104
+	stdu	23,8(3)		# offset 112
+	stdu	24,8(3)		# offset 120
+	stdu	25,8(3)		# offset 128
+	stdu	26,8(3)		# offset 136
+	stdu	27,8(3)		# offset 144
+	stdu	28,8(3)		# offset 152
+	stdu	29,8(3)		# offset 160
+	stdu	30,8(3)		# offset 168
+	stdu	31,8(3)		# offset 176
 #else
 	stw	1,0(3)		# offset 0
 	stwu	2,4(3)		# offset 4
@@ -64,10 +90,15 @@ FUNC_START(setjmp)
 	stwu	31,4(3)		# offset 80
 #endif
 
-	/* From this point on until the end of this function, add 84
+	/* If __SPE__, then add 84 to the offset shown from this point on until
-	   to the offset shown if __SPE__.  This difference comes from
+	   the end of this function.  This difference comes from the fact that
-	   the fact that we save 21 64-bit registers instead of 21
+	   we save 21 64-bit registers instead of 21 32-bit registers above.
-	   32-bit registers above.  */
+
+	   If __powerpc64__, then add 96 to the offset shown from this point on until
+	   the end of this function.  This difference comes from the fact that
+	   we save 21 64-bit registers instead of 21 32-bit registers above and
+	   we take alignement requirements of floating point and Altivec stores
+	   into account.  */
 	mflr	4
 	stwu	4,4(3)		# offset 84
 	mfcr	4
@@ -188,6 +219,31 @@ FUNC_START(longjmp)
 	   loaded.  Note that we are not adding 168 because the next
 	   load instruction uses an offset of 4.  */
 	addi	3,3,164
+#elif __powerpc64__
+	/* In the first load, add 16 to r3 so that the subsequent floating
+	   point loades are aligned on an 8 byte boundary and the Altivec
+	   loads are aligned on a 16 byte boundary.  */
+	ldu	1,16(3)		# offset 16
+	ldu	2,8(3)		# offset 24
+	ldu	13,8(3)		# offset 32
+	ldu	14,8(3)		# offset 40
+	ldu	15,8(3)		# offset 48
+	ldu	16,8(3)		# offset 56
+	ldu	17,8(3)		# offset 64
+	ldu	18,8(3)		# offset 72
+	ldu	19,8(3)		# offset 80
+	ldu	20,8(3)		# offset 88
+	ldu	21,8(3)		# offset 96
+	ldu	22,8(3)		# offset 104
+	ldu	23,8(3)		# offset 112
+	ldu	24,8(3)		# offset 120
+	ldu	25,8(3)		# offset 128
+	ldu	26,8(3)		# offset 136
+	ldu	27,8(3)		# offset 144
+	ldu	28,8(3)		# offset 152
+	ldu	29,8(3)		# offset 160
+	ldu	30,8(3)		# offset 168
+	ldu	31,8(3)		# offset 176
 #else
 	lwz	1,0(3)		# offset 0 
 	lwzu	2,4(3)		# offset 4 
@@ -211,10 +267,15 @@ FUNC_START(longjmp)
 	lwzu	30,4(3)		# offset 76
 	lwzu	31,4(3)		# offset 80
 #endif
-	/* From this point on until the end of this function, add 84
+	/* If __SPE__, then add 84 to the offset shown from this point on until
-	   to the offset shown if __SPE__.  This difference comes from
+	   the end of this function.  This difference comes from the fact that
-	   the fact that we restore 21 64-bit registers instead of 21
+	   we restore 21 64-bit registers instead of 21 32-bit registers above.
-	   32-bit registers above.  */
+
+	   If __powerpc64__, then add 96 to the offset shown from this point on until
+	   the end of this function.  This difference comes from the fact that
+	   we restore 21 64-bit registers instead of 21 32-bit registers above and
+	   we take alignement requirements of floating point and Altivec loads
+	   into account.  */
 	lwzu	5,4(3)		# offset 84
 	mtlr	5
 	lwzu	5,4(3)		# offset 88