Revision 9e2b7fa2df4365e99934901da4fb4af52d81e820 authored by Martin Willi on 06 November 2020, 07:30:30 UTC, committed by Jakub Kicinski on 12 November 2020, 15:47:06 UTC
VRF devices use an optimized direct path on output if a default qdisc
is involved, calling Netfilter hooks directly. This path, however, does
not consider Netfilter rules completing asynchronously, such as with
NFQUEUE. The Netfilter okfn() is called for asynchronously accepted
packets, but the VRF never passes that packet down the stack to send
it out over the slave device. Using the slower redirect path for this
seems not feasible, as we do not know beforehand if a Netfilter hook
has asynchronously completing rules.

Fix the use of asynchronously completing Netfilter rules in OUTPUT and
POSTROUTING by using a special completion function that additionally
calls dst_output() to pass the packet down the stack. Also, slightly
adjust the use of nf_reset_ct() so that is called in the asynchronous
case, too.

Fixes: dcdd43c41e60 ("net: vrf: performance improvements for IPv4")
Fixes: a9ec54d1b0cd ("net: vrf: performance improvements for IPv6")
Signed-off-by: Martin Willi <martin@strongswan.org>
Link: https://lore.kernel.org/r/20201106073030.3974927-1-martin@strongswan.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
1 parent 52755b6
Raw File
hweight.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/export.h>
#include <linux/bitops.h>
#include <asm/types.h>

/**
 * hweightN - returns the hamming weight of a N-bit word
 * @x: the word to weigh
 *
 * The Hamming Weight of a number is the total number of bits set in it.
 */

unsigned int __sw_hweight32(unsigned int w)
{
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
	w -= (w >> 1) & 0x55555555;
	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
	w =  (w + (w >> 4)) & 0x0f0f0f0f;
	return (w * 0x01010101) >> 24;
#else
	unsigned int res = w - ((w >> 1) & 0x55555555);
	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
	res = (res + (res >> 4)) & 0x0F0F0F0F;
	res = res + (res >> 8);
	return (res + (res >> 16)) & 0x000000FF;
#endif
}
EXPORT_SYMBOL(__sw_hweight32);

unsigned int __sw_hweight16(unsigned int w)
{
	unsigned int res = w - ((w >> 1) & 0x5555);
	res = (res & 0x3333) + ((res >> 2) & 0x3333);
	res = (res + (res >> 4)) & 0x0F0F;
	return (res + (res >> 8)) & 0x00FF;
}
EXPORT_SYMBOL(__sw_hweight16);

unsigned int __sw_hweight8(unsigned int w)
{
	unsigned int res = w - ((w >> 1) & 0x55);
	res = (res & 0x33) + ((res >> 2) & 0x33);
	return (res + (res >> 4)) & 0x0F;
}
EXPORT_SYMBOL(__sw_hweight8);

unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
	return __sw_hweight32((unsigned int)(w >> 32)) +
	       __sw_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
	w -= (w >> 1) & 0x5555555555555555ul;
	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
	return (w * 0x0101010101010101ul) >> 56;
#else
	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
	res = res + (res >> 8);
	res = res + (res >> 16);
	return (res + (res >> 32)) & 0x00000000000000FFul;
#endif
#endif
}
EXPORT_SYMBOL(__sw_hweight64);
back to top