The generic csum_ipv6_magic() generates a pretty bad result
00000000 <csum_ipv6_magic>: (PPC32)
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
0000000000000000 <.csum_ipv6_magic>: (PPC64)
0: 81 23 00 00 lwz r9,0(r3)
4: 80 03 00 04 lwz r0,4(r3)
8: 81 63 00 08 lwz r11,8(r3)
c: 7c e7 4a 14 add r7,r7,r9
10: 7f 89 38 40 cmplw cr7,r9,r7
14: 7d 47 02 14 add r10,r7,r0
18: 7d 30 10 26 mfocrf r9,1
1c: 55 29 f7 fe rlwinm r9,r9,30,31,31
20: 7d 4a 4a 14 add r10,r10,r9
24: 7f 80 50 40 cmplw cr7,r0,r10
28: 7d 2a 5a 14 add r9,r10,r11
2c: 80 03 00 0c lwz r0,12(r3)
30: 81 44 00 00 lwz r10,0(r4)
34: 7d 10 10 26 mfocrf r8,1
38: 55 08 f7 fe rlwinm r8,r8,30,31,31
3c: 7d 29 42 14 add r9,r9,r8
40: 81 04 00 04 lwz r8,4(r4)
44: 7f 8b 48 40 cmplw cr7,r11,r9
48: 7d 29 02 14 add r9,r9,r0
4c: 7d 70 10 26 mfocrf r11,1
50: 55 6b f7 fe rlwinm r11,r11,30,31,31
54: 7d 29 5a 14 add r9,r9,r11
58: 7f 80 48 40 cmplw cr7,r0,r9
5c: 7d 29 52 14 add r9,r9,r10
60: 7c 10 10 26 mfocrf r0,1
64: 54 00 f7 fe rlwinm r0,r0,30,31,31
68: 7d 69 02 14 add r11,r9,r0
6c: 7f 8a 58 40 cmplw cr7,r10,r11
70: 7c 0b 42 14 add r0,r11,r8
74: 81 44 00 08 lwz r10,8(r4)
78: 7c f0 10 26 mfocrf r7,1
7c: 54 e7 f7 fe rlwinm r7,r7,30,31,31
80: 7c 00 3a 14 add r0,r0,r7
84: 7f 88 00 40 cmplw cr7,r8,r0
88: 7d 20 52 14 add r9,r0,r10
8c: 80 04 00 0c lwz r0,12(r4)
90: 7d 70 10 26 mfocrf r11,1
94: 55 6b f7 fe rlwinm r11,r11,30,31,31
98: 7d 29 5a 14 add r9,r9,r11
9c: 7f 8a 48 40 cmplw cr7,r10,r9
a0: 7d 29 02 14 add r9,r9,r0
a4: 7d 70 10 26 mfocrf r11,1
a8: 55 6b f7 fe rlwinm r11,r11,30,31,31
ac: 7d 29 5a 14 add r9,r9,r11
b0: 7f 80 48 40 cmplw cr7,r0,r9
b4: 7d 29 2a 14 add r9,r9,r5
b8: 7c 10 10 26 mfocrf r0,1
bc: 54 00 f7 fe rlwinm r0,r0,30,31,31
c0: 7d 29 02 14 add r9,r9,r0
c4: 7f 85 48 40 cmplw cr7,r5,r9
c8: 7c 09 32 14 add r0,r9,r6
cc: 7d 50 10 26 mfocrf r10,1
d0: 55 4a f7 fe rlwinm r10,r10,30,31,31
d4: 7c 00 52 14 add r0,r0,r10
d8: 7f 80 30 40 cmplw cr7,r0,r6
dc: 7d 30 10 26 mfocrf r9,1
e0: 55 29 ef fe rlwinm r9,r9,29,31,31
e4: 7c 09 02 14 add r0,r9,r0
e8: 54 03 80 3e rotlwi r3,r0,16
ec: 7c 03 02 14 add r0,r3,r0
f0: 7c 03 00 f8 not r3,r0
f4: 78 63 84 22 rldicl r3,r3,48,48
f8: 4e 80 00 20 blr
This patch implements it in assembly for both PPC32 and PPC64
Link: https://github.com/linuxppc/linux/issues/9
Signed-off-by: Christophe Leroy <[email protected]>
---
v4: Interleaved loads and adds in PPC32. No performance change on 8xx, 15% improvment on 83xx
v3: Add support for PPC64 (please review, especially whether instructions order in optimal)
v2: Fix number of args in final addze
arch/powerpc/include/asm/checksum.h | 6 ++++++
arch/powerpc/lib/checksum_32.S | 33 +++++++++++++++++++++++++++++++++
arch/powerpc/lib/checksum_64.S | 28 ++++++++++++++++++++++++++++
3 files changed, 67 insertions(+)
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 54065caa40b3..a78a57e5058d 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 +212,11 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
return csum_fold(csum_partial(buff, len, 0));
}
+#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 /* __KERNEL__ */
#endif
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 9a671c774b22..d2238ea82209 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)
+
+/*
+ * __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)
+ addc r0, r7, r8
+ lwz r10, 8(r3)
+ adde r0, r0, r9
+ lwz r11, 12(r3)
+ adde r0, r0, r10
+ lwz r8, 0(r4)
+ adde r0, r0, r11
+ lwz r9, 4(r4)
+ adde r0, r0, r8
+ lwz r10, 8(r4)
+ adde r0, r0, r9
+ lwz r11, 12(r4)
+ adde r0, r0, r10
+ add r5, r5, r6 /* assumption: len + proto doesn't carry */
+ adde r0, r0, r11
+ adde r0, r0, r5
+ 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)
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index d7f1a966136e..bf0546e546fc 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -429,3 +429,31 @@ dstnr; stb r6,0(r4)
stw r6,0(r8)
blr
EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ * const struct in6_addr *daddr,
+ * __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+ ld r8, 0(r3)
+ ld r9, 8(r3)
+ add r5, r5, r6
+ addc r0, r8, r9
+ ld r10, 0(r4)
+ ld r11, 8(r4)
+ adde r0, r0, r10
+ add r5, r5, r7
+ adde r0, r0, r11
+ adde r0, r0, r5
+ addze r0, r0
+ rotldi r3 ,r0, 32 /* fold two 32 bit halves together */
+ add r3, r0, r3
+ srdi r0, r3, 32
+ rotlwi r3, r0, 16 /* fold two 16 bit halves together */
+ add r3, r0, r3
+ not r3, r3
+ rlwinm r3, r3, 16, 16, 31
+ blr
+EXPORT_SYMBOL(csum_ipv6_magic)
--
2.13.3
Looks fine to me (one comment below):
Reviewed-by: Segher Boessenkool <[email protected]>
On Thu, May 24, 2018 at 11:33:18AM +0000, Christophe Leroy wrote:
> +_GLOBAL(csum_ipv6_magic)
> + lwz r8, 0(r3)
> + lwz r9, 4(r3)
> + addc r0, r7, r8
> + lwz r10, 8(r3)
> + adde r0, r0, r9
> + lwz r11, 12(r3)
> + adde r0, r0, r10
> + lwz r8, 0(r4)
> + adde r0, r0, r11
> + lwz r9, 4(r4)
> + adde r0, r0, r8
> + lwz r10, 8(r4)
> + adde r0, r0, r9
> + lwz r11, 12(r4)
> + adde r0, r0, r10
> + add r5, r5, r6 /* assumption: len + proto doesn't carry */
> + adde r0, r0, r11
> + adde r0, r0, r5
> + 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)
> diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
> index d7f1a966136e..bf0546e546fc 100644
> --- a/arch/powerpc/lib/checksum_64.S
> +++ b/arch/powerpc/lib/checksum_64.S
> @@ -429,3 +429,31 @@ dstnr; stb r6,0(r4)
> stw r6,0(r8)
> blr
> EXPORT_SYMBOL(csum_partial_copy_generic)
> +
> +/*
> + * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
> + * const struct in6_addr *daddr,
> + * __u32 len, __u8 proto, __wsum sum)
> + */
> +
> +_GLOBAL(csum_ipv6_magic)
> + ld r8, 0(r3)
> + ld r9, 8(r3)
> + add r5, r5, r6
> + addc r0, r8, r9
> + ld r10, 0(r4)
> + ld r11, 8(r4)
> + adde r0, r0, r10
> + add r5, r5, r7
> + adde r0, r0, r11
> + adde r0, r0, r5
> + addze r0, r0
> + rotldi r3 ,r0, 32 /* fold two 32 bit halves together */
Typo (s/ ,/, /).
> + add r3, r0, r3
> + srdi r0, r3, 32
> + rotlwi r3, r0, 16 /* fold two 16 bit halves together */
> + add r3, r0, r3
> + not r3, r3
> + rlwinm r3, r3, 16, 16, 31
> + blr
> +EXPORT_SYMBOL(csum_ipv6_magic)
> --
> 2.13.3
On Thu, 2018-05-24 at 11:33:18 UTC, Christophe Leroy wrote:
> The generic csum_ipv6_magic() generates a pretty bad result
>
> 00000000 <csum_ipv6_magic>: (PPC32)
> 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
>
> 0000000000000000 <.csum_ipv6_magic>: (PPC64)
> 0: 81 23 00 00 lwz r9,0(r3)
> 4: 80 03 00 04 lwz r0,4(r3)
> 8: 81 63 00 08 lwz r11,8(r3)
> c: 7c e7 4a 14 add r7,r7,r9
> 10: 7f 89 38 40 cmplw cr7,r9,r7
> 14: 7d 47 02 14 add r10,r7,r0
> 18: 7d 30 10 26 mfocrf r9,1
> 1c: 55 29 f7 fe rlwinm r9,r9,30,31,31
> 20: 7d 4a 4a 14 add r10,r10,r9
> 24: 7f 80 50 40 cmplw cr7,r0,r10
> 28: 7d 2a 5a 14 add r9,r10,r11
> 2c: 80 03 00 0c lwz r0,12(r3)
> 30: 81 44 00 00 lwz r10,0(r4)
> 34: 7d 10 10 26 mfocrf r8,1
> 38: 55 08 f7 fe rlwinm r8,r8,30,31,31
> 3c: 7d 29 42 14 add r9,r9,r8
> 40: 81 04 00 04 lwz r8,4(r4)
> 44: 7f 8b 48 40 cmplw cr7,r11,r9
> 48: 7d 29 02 14 add r9,r9,r0
> 4c: 7d 70 10 26 mfocrf r11,1
> 50: 55 6b f7 fe rlwinm r11,r11,30,31,31
> 54: 7d 29 5a 14 add r9,r9,r11
> 58: 7f 80 48 40 cmplw cr7,r0,r9
> 5c: 7d 29 52 14 add r9,r9,r10
> 60: 7c 10 10 26 mfocrf r0,1
> 64: 54 00 f7 fe rlwinm r0,r0,30,31,31
> 68: 7d 69 02 14 add r11,r9,r0
> 6c: 7f 8a 58 40 cmplw cr7,r10,r11
> 70: 7c 0b 42 14 add r0,r11,r8
> 74: 81 44 00 08 lwz r10,8(r4)
> 78: 7c f0 10 26 mfocrf r7,1
> 7c: 54 e7 f7 fe rlwinm r7,r7,30,31,31
> 80: 7c 00 3a 14 add r0,r0,r7
> 84: 7f 88 00 40 cmplw cr7,r8,r0
> 88: 7d 20 52 14 add r9,r0,r10
> 8c: 80 04 00 0c lwz r0,12(r4)
> 90: 7d 70 10 26 mfocrf r11,1
> 94: 55 6b f7 fe rlwinm r11,r11,30,31,31
> 98: 7d 29 5a 14 add r9,r9,r11
> 9c: 7f 8a 48 40 cmplw cr7,r10,r9
> a0: 7d 29 02 14 add r9,r9,r0
> a4: 7d 70 10 26 mfocrf r11,1
> a8: 55 6b f7 fe rlwinm r11,r11,30,31,31
> ac: 7d 29 5a 14 add r9,r9,r11
> b0: 7f 80 48 40 cmplw cr7,r0,r9
> b4: 7d 29 2a 14 add r9,r9,r5
> b8: 7c 10 10 26 mfocrf r0,1
> bc: 54 00 f7 fe rlwinm r0,r0,30,31,31
> c0: 7d 29 02 14 add r9,r9,r0
> c4: 7f 85 48 40 cmplw cr7,r5,r9
> c8: 7c 09 32 14 add r0,r9,r6
> cc: 7d 50 10 26 mfocrf r10,1
> d0: 55 4a f7 fe rlwinm r10,r10,30,31,31
> d4: 7c 00 52 14 add r0,r0,r10
> d8: 7f 80 30 40 cmplw cr7,r0,r6
> dc: 7d 30 10 26 mfocrf r9,1
> e0: 55 29 ef fe rlwinm r9,r9,29,31,31
> e4: 7c 09 02 14 add r0,r9,r0
> e8: 54 03 80 3e rotlwi r3,r0,16
> ec: 7c 03 02 14 add r0,r3,r0
> f0: 7c 03 00 f8 not r3,r0
> f4: 78 63 84 22 rldicl r3,r3,48,48
> f8: 4e 80 00 20 blr
>
> This patch implements it in assembly for both PPC32 and PPC64
>
> Link: https://github.com/linuxppc/linux/issues/9
> Signed-off-by: Christophe Leroy <[email protected]>
> Reviewed-by: Segher Boessenkool <[email protected]>
Applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/e9c4943a107b56696e4872cdffdba6
cheers