Merge pull request #160 from grooverdan/crc32_power_abi_fix

MDEV-9699: power8 crc32: Per the PPC64 ABI, v20-v31 are non-volatile registers

storage/innobase/ut/crc32_power8/crc32.S

@@ -67,14 +67,13 @@
 #define off96		 		 r30
 #define off112		 		 r31
 
-#define const1		 		 v25
-#define const2		 		 v26
+#define const1				 v24
+#define const2				 v25
 
-#define byteswap		 v27
-#define		 mask_32bit		 v28
-#define		 mask_64bit		 v29
-#define zeroes		 		 v30
-#define ones		 		 v31
+#define byteswap			 v26
+#define mask_32bit			 v27
+#define mask_64bit			 v28
+#define zeroes				 v29
 
 #ifdef BYTESWAP_DATA
 #define VPERM(A, B, C, D) vperm		 A, B, C, D
@@ -101,13 +100,28 @@ FUNC_START(__crc32_vpmsum)
 		 li		 off112,112
 		 li		 r0,0
 
+		 /* Enough room for saving 10 non volatile VMX registers */
+		 subi		 r6,r1,56+10*16
+		 subi		 r7,r1,56+2*16
+
+		 stvx		 v20,0,r6
+		 stvx		 v21,off16,r6
+		 stvx		 v22,off32,r6
+		 stvx		 v23,off48,r6
+		 stvx		 v24,off64,r6
+		 stvx		 v25,off80,r6
+		 stvx		 v26,off96,r6
+		 stvx		 v27,off112,r6
+		 stvx		 v28,0,r7
+		 stvx		 v29,off16,r7
+
 		 mr		 r10,r3
 
 		 vxor		 zeroes,zeroes,zeroes
-		 vspltisw ones,-1
+		 vspltisw 	 v0,-1
 
-		 vsldoi		 mask_32bit,zeroes,ones,4
-		 vsldoi		 mask_64bit,zeroes,ones,8
+		 vsldoi		 mask_32bit,zeroes,v0,4
+		 vsldoi		 mask_64bit,zeroes,v0,8
 
 		 /* Get the initial value into v8 */
 		 vxor		 v8,v8,v8
@@ -570,6 +584,21 @@ FUNC_START(__crc32_vpmsum)
 		 vsldoi		 v0,v0,zeroes,4		 		 /* shift result into top 64 bits of */
 #endif
 
+.Lout:
+		 subi	r6,r1,56+10*16
+		 subi	r7,r1,56+2*16
+
+		 lvx	v20,0,r6
+		 lvx	v21,off16,r6
+		 lvx	v22,off32,r6
+		 lvx	v23,off48,r6
+		 lvx	v24,off64,r6
+		 lvx	v25,off80,r6
+		 lvx	v26,off96,r6
+		 lvx	v27,off112,r6
+		 lvx	v28,0,r7
+		 lvx	v29,off16,r7
+
 		 /* Get it into r3 */
 		 MFVRD(r3, v0)
 
@@ -739,6 +768,8 @@ FUNC_START(__crc32_vpmsum)
 .Lzero:
 		 mr		 r3,r10
 		 blr
+		 b	.Lout
+
 FUNC_END(__crc32_vpmsum)
 
 #endif /* __powerpc__ */

storage/xtradb/ut/crc32_power8/crc32.S

@@ -67,14 +67,13 @@
 #define off96		 		 r30
 #define off112		 		 r31
 
-#define const1		 		 v25
-#define const2		 		 v26
+#define const1				 v24
+#define const2				 v25
 
-#define byteswap		 v27
-#define		 mask_32bit		 v28
-#define		 mask_64bit		 v29
-#define zeroes		 		 v30
-#define ones		 		 v31
+#define byteswap			 v26
+#define mask_32bit			 v27
+#define mask_64bit			 v28
+#define zeroes				 v29
 
 #ifdef BYTESWAP_DATA
 #define VPERM(A, B, C, D) vperm		 A, B, C, D
@@ -101,13 +100,28 @@ FUNC_START(__crc32_vpmsum)
 		 li		 off112,112
 		 li		 r0,0
 
+		 /* Enough room for saving 10 non volatile VMX registers */
+		 subi		 r6,r1,56+10*16
+		 subi		 r7,r1,56+2*16
+
+		 stvx		 v20,0,r6
+		 stvx		 v21,off16,r6
+		 stvx		 v22,off32,r6
+		 stvx		 v23,off48,r6
+		 stvx		 v24,off64,r6
+		 stvx		 v25,off80,r6
+		 stvx		 v26,off96,r6
+		 stvx		 v27,off112,r6
+		 stvx		 v28,0,r7
+		 stvx		 v29,off16,r7
+
 		 mr		 r10,r3
 
 		 vxor		 zeroes,zeroes,zeroes
-		 vspltisw ones,-1
+		 vspltisw 	 v0,-1
 
-		 vsldoi		 mask_32bit,zeroes,ones,4
-		 vsldoi		 mask_64bit,zeroes,ones,8
+		 vsldoi		 mask_32bit,zeroes,v0,4
+		 vsldoi		 mask_64bit,zeroes,v0,8
 
 		 /* Get the initial value into v8 */
 		 vxor		 v8,v8,v8
@@ -570,6 +584,21 @@ FUNC_START(__crc32_vpmsum)
 		 vsldoi		 v0,v0,zeroes,4		 		 /* shift result into top 64 bits of */
 #endif
 
+.Lout:
+		 subi	r6,r1,56+10*16
+		 subi	r7,r1,56+2*16
+
+		 lvx	v20,0,r6
+		 lvx	v21,off16,r6
+		 lvx	v22,off32,r6
+		 lvx	v23,off48,r6
+		 lvx	v24,off64,r6
+		 lvx	v25,off80,r6
+		 lvx	v26,off96,r6
+		 lvx	v27,off112,r6
+		 lvx	v28,0,r7
+		 lvx	v29,off16,r7
+
 		 /* Get it into r3 */
 		 MFVRD(r3, v0)
 
@@ -739,6 +768,8 @@ FUNC_START(__crc32_vpmsum)
 .Lzero:
 		 mr		 r3,r10
 		 blr
+		 b	.Lout
+
 FUNC_END(__crc32_vpmsum)
 
 #endif /* __powerpc__ */