x86/lib: Inline csum_ipv6_magic()

x86/lib: Inline csum_ipv6_magic()

Inline this small helper. It has been observed to consume up
to 0.75%, which is significant for such a small function.

This should reduce register pressure, as saddr and daddr are often
back to back in memory.

For instance code inlined in tcp6_gro_receive() will look like:

 55a:	48 03 73 28          	add    0x28(%rbx),%rsi
 55e:	8b 43 70             	mov    0x70(%rbx),%eax
 561:	29 f8                	sub    %edi,%eax
 563:	0f c8                	bswap  %eax
 565:	89 c0                	mov    %eax,%eax
 567:	48 05 00 06 00 00    	add    $0x600,%rax
 56d:	48 03 46 08          	add    0x8(%rsi),%rax
 571:	48 13 46 10          	adc    0x10(%rsi),%rax
 575:	48 13 46 18          	adc    0x18(%rsi),%rax
 579:	48 13 46 20          	adc    0x20(%rsi),%rax
 57d:	48 83 d0 00          	adc    $0x0,%rax
 581:	48 89 c6             	mov    %rax,%rsi
 584:	48 c1 ee 20          	shr    $0x20,%rsi
 588:	01 f0                	add    %esi,%eax
 58a:	83 d0 00             	adc    $0x0,%eax
 58d:	89 c6                	mov    %eax,%esi
 58f:	66 31 c0             	xor    %ax,%ax

Surprisingly, this inlining does not seem to bloat kernel text size.
It at least two cases[1], it either has no effect or results in a
slightly smaller kernel.

1. https://lore.kernel.org/all/CANn89iJzcb_XO9oCApKYfRxsMMmg7BHukRDqWTca3ZLQ8HT0iQ@mail.gmail.com/

[ dhansen: add justification and note about lack of kernel bloat ]

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://patch.msgid.link/20251113154545.594580-1-edumazet@google.com