[PATCH v2] powerpc/32: Implement csum_ipv6_magic in assembly

From: Christophe Leroy
Date: Tue May 22 2018 - 00:38:49 EST


The generic csum_ipv6_magic() generates a pretty bad result

00000000 <csum_ipv6_magic>:
0: 81 23 00 00 lwz r9,0(r3)
4: 81 03 00 04 lwz r8,4(r3)
8: 7c e7 4a 14 add r7,r7,r9
c: 7d 29 38 10 subfc r9,r9,r7
10: 7d 4a 51 10 subfe r10,r10,r10
14: 7d 27 42 14 add r9,r7,r8
18: 7d 2a 48 50 subf r9,r10,r9
1c: 80 e3 00 08 lwz r7,8(r3)
20: 7d 08 48 10 subfc r8,r8,r9
24: 7d 4a 51 10 subfe r10,r10,r10
28: 7d 29 3a 14 add r9,r9,r7
2c: 81 03 00 0c lwz r8,12(r3)
30: 7d 2a 48 50 subf r9,r10,r9
34: 7c e7 48 10 subfc r7,r7,r9
38: 7d 4a 51 10 subfe r10,r10,r10
3c: 7d 29 42 14 add r9,r9,r8
40: 7d 2a 48 50 subf r9,r10,r9
44: 80 e4 00 00 lwz r7,0(r4)
48: 7d 08 48 10 subfc r8,r8,r9
4c: 7d 4a 51 10 subfe r10,r10,r10
50: 7d 29 3a 14 add r9,r9,r7
54: 7d 2a 48 50 subf r9,r10,r9
58: 81 04 00 04 lwz r8,4(r4)
5c: 7c e7 48 10 subfc r7,r7,r9
60: 7d 4a 51 10 subfe r10,r10,r10
64: 7d 29 42 14 add r9,r9,r8
68: 7d 2a 48 50 subf r9,r10,r9
6c: 80 e4 00 08 lwz r7,8(r4)
70: 7d 08 48 10 subfc r8,r8,r9
74: 7d 4a 51 10 subfe r10,r10,r10
78: 7d 29 3a 14 add r9,r9,r7
7c: 7d 2a 48 50 subf r9,r10,r9
80: 81 04 00 0c lwz r8,12(r4)
84: 7c e7 48 10 subfc r7,r7,r9
88: 7d 4a 51 10 subfe r10,r10,r10
8c: 7d 29 42 14 add r9,r9,r8
90: 7d 2a 48 50 subf r9,r10,r9
94: 7d 08 48 10 subfc r8,r8,r9
98: 7d 4a 51 10 subfe r10,r10,r10
9c: 7d 29 2a 14 add r9,r9,r5
a0: 7d 2a 48 50 subf r9,r10,r9
a4: 7c a5 48 10 subfc r5,r5,r9
a8: 7c 63 19 10 subfe r3,r3,r3
ac: 7d 29 32 14 add r9,r9,r6
b0: 7d 23 48 50 subf r9,r3,r9
b4: 7c c6 48 10 subfc r6,r6,r9
b8: 7c 63 19 10 subfe r3,r3,r3
bc: 7c 63 48 50 subf r3,r3,r9
c0: 54 6a 80 3e rotlwi r10,r3,16
c4: 7c 63 52 14 add r3,r3,r10
c8: 7c 63 18 f8 not r3,r3
cc: 54 63 84 3e rlwinm r3,r3,16,16,31
d0: 4e 80 00 20 blr

This patch implements it in assembly for PPC32

Link: https://github.com/linuxppc/linux/issues/9
Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
---
v2: Fix number of args in final addze

arch/powerpc/include/asm/checksum.h | 8 ++++++++
arch/powerpc/lib/checksum_32.S | 33 +++++++++++++++++++++++++++++++++
2 files changed, 41 insertions(+)

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 54065caa40b3..c41c280c252f 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -13,6 +13,7 @@
#include <asm-generic/checksum.h>
#else
#include <linux/bitops.h>
+#include <linux/in6.h>
/*
* Computes the checksum of a memory block at src, length len,
* and adds in "sum" (32-bit), while copying the block to dst.
@@ -211,6 +212,13 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
return csum_fold(csum_partial(buff, len, 0));
}

+#ifdef CONFIG_PPC32
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum sum);
+#endif
+
#endif
#endif /* __KERNEL__ */
#endif
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 9a671c774b22..9167ab088f04 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -293,3 +293,36 @@ dst_error:
EX_TABLE(51b, dst_error);

EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ * const struct in6_addr *daddr,
+ * __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+ lwz r8, 0(r3)
+ lwz r9, 4(r3)
+ lwz r10, 8(r3)
+ lwz r11, 12(r3)
+ addc r0, r5, r6
+ adde r0, r0, r7
+ adde r0, r0, r8
+ adde r0, r0, r9
+ adde r0, r0, r10
+ adde r0, r0, r11
+ lwz r8, 0(r4)
+ lwz r9, 4(r4)
+ lwz r10, 8(r4)
+ lwz r11, 12(r4)
+ adde r0, r0, r8
+ adde r0, r0, r9
+ adde r0, r0, r10
+ adde r0, r0, r11
+ addze r0, r0
+ rotlwi r3, r0, 16
+ add r3, r0, r3
+ not r3, r3
+ rlwinm r3, r3, 16, 16, 31
+ blr
+EXPORT_SYMBOL(csum_ipv6_magic)
--
2.13.3