Staging
v0.8.1
Revision a0783cd0c810504427777e8aae20d5f4f8b652a0 authored by Corinna Vinschen on 19 November 2019, 09:09:39 UTC, committed by David S. Miller on 20 November 2019, 00:41:11 UTC
During performance testing, I found that one of my r8169 NICs suffered
a major performance loss, a 8168c model.

Running netperf's TCP_STREAM test didn't return the expected
throughput of > 900 Mb/s, but rather only about 22 Mb/s.  Strange
enough, running the TCP_MAERTS and UDP_STREAM tests all returned with
throughput > 900 Mb/s, as did TCP_STREAM with the other r8169 NICs I can
test (either one of 8169s, 8168e, 8168f).

Bisecting turned up commit 93681cd7d94f83903cb3f0f95433d10c28a7e9a5,
"r8169: enable HW csum and TSO" as the culprit.

I added my 8168c version, RTL_GIGA_MAC_VER_22, to the code
special-casing the 8168evl as per the patch below.  This fixed the
performance problem for me.

Fixes: 93681cd7d94f ("r8169: enable HW csum and TSO")
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent c9d55b6
Raw File
generic_mpih-lshift.c
// SPDX-License-Identifier: GPL-2.0-or-later
/* mpihelp-lshift.c  -	MPI helper functions
 * Copyright (C) 1994, 1996, 1998, 2001 Free Software Foundation, Inc.
 *
 * This file is part of GnuPG.
 *
 * Note: This code is heavily based on the GNU MP Library.
 *	 Actually it's the same code with only minor changes in the
 *	 way the data is stored; this is to support the abstraction
 *	 of an optional secure memory allocation which may be used
 *	 to avoid revealing of sensitive data due to paging etc.
 *	 The GNU MP Library itself is published under the LGPL;
 *	 however I decided to publish this code under the plain GPL.
 */

#include "mpi-internal.h"

/* Shift U (pointed to by UP and USIZE digits long) CNT bits to the left
 * and store the USIZE least significant digits of the result at WP.
 * Return the bits shifted out from the most significant digit.
 *
 * Argument constraints:
 * 1. 0 < CNT < BITS_PER_MP_LIMB
 * 2. If the result is to be written over the input, WP must be >= UP.
 */

mpi_limb_t
mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize, unsigned int cnt)
{
	mpi_limb_t high_limb, low_limb;
	unsigned sh_1, sh_2;
	mpi_size_t i;
	mpi_limb_t retval;

	sh_1 = cnt;
	wp += 1;
	sh_2 = BITS_PER_MPI_LIMB - sh_1;
	i = usize - 1;
	low_limb = up[i];
	retval = low_limb >> sh_2;
	high_limb = low_limb;
	while (--i >= 0) {
		low_limb = up[i];
		wp[i] = (high_limb << sh_1) | (low_limb >> sh_2);
		high_limb = low_limb;
	}
	wp[i] = high_limb << sh_1;

	return retval;
}
back to top