Skip to main content

Browse the archive

Staging
v0.6.0
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 
r8169: disable TSO on a single version of RTL8168c to fix performance
 
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
percpu_test.c 
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>

/* validate @native and @pcp counter values match @expected */
#define CHECK(native, pcp, expected)                                    \
	do {                                                            \
		WARN((native) != (expected),                            \
		     "raw %ld (0x%lx) != expected %lld (0x%llx)",	\
		     (native), (native),				\
		     (long long)(expected), (long long)(expected));	\
		WARN(__this_cpu_read(pcp) != (expected),                \
		     "pcp %ld (0x%lx) != expected %lld (0x%llx)",	\
		     __this_cpu_read(pcp), __this_cpu_read(pcp),	\
		     (long long)(expected), (long long)(expected));	\
	} while (0)

static DEFINE_PER_CPU(long, long_counter);
static DEFINE_PER_CPU(unsigned long, ulong_counter);

static int __init percpu_test_init(void)
{
	/*
	 * volatile prevents compiler from optimizing it uses, otherwise the
	 * +ul_one/-ul_one below would replace with inc/dec instructions.
	 */
	volatile unsigned int ui_one = 1;
	long l = 0;
	unsigned long ul = 0;

	pr_info("percpu test start\n");

	preempt_disable();

	l += -1;
	__this_cpu_add(long_counter, -1);
	CHECK(l, long_counter, -1);

	l += 1;
	__this_cpu_add(long_counter, 1);
	CHECK(l, long_counter, 0);

	ul = 0;
	__this_cpu_write(ulong_counter, 0);

	ul += 1UL;
	__this_cpu_add(ulong_counter, 1UL);
	CHECK(ul, ulong_counter, 1);

	ul += -1UL;
	__this_cpu_add(ulong_counter, -1UL);
	CHECK(ul, ulong_counter, 0);

	ul += -(unsigned long)1;
	__this_cpu_add(ulong_counter, -(unsigned long)1);
	CHECK(ul, ulong_counter, -1);

	ul = 0;
	__this_cpu_write(ulong_counter, 0);

	ul -= 1;
	__this_cpu_dec(ulong_counter);
	CHECK(ul, ulong_counter, -1);
	CHECK(ul, ulong_counter, ULONG_MAX);

	l += -ui_one;
	__this_cpu_add(long_counter, -ui_one);
	CHECK(l, long_counter, 0xffffffff);

	l += ui_one;
	__this_cpu_add(long_counter, ui_one);
	CHECK(l, long_counter, (long)0x100000000LL);


	l = 0;
	__this_cpu_write(long_counter, 0);

	l -= ui_one;
	__this_cpu_sub(long_counter, ui_one);
	CHECK(l, long_counter, -1);

	l = 0;
	__this_cpu_write(long_counter, 0);

	l += ui_one;
	__this_cpu_add(long_counter, ui_one);
	CHECK(l, long_counter, 1);

	l += -ui_one;
	__this_cpu_add(long_counter, -ui_one);
	CHECK(l, long_counter, (long)0x100000000LL);

	l = 0;
	__this_cpu_write(long_counter, 0);

	l -= ui_one;
	this_cpu_sub(long_counter, ui_one);
	CHECK(l, long_counter, -1);
	CHECK(l, long_counter, ULONG_MAX);

	ul = 0;
	__this_cpu_write(ulong_counter, 0);

	ul += ui_one;
	__this_cpu_add(ulong_counter, ui_one);
	CHECK(ul, ulong_counter, 1);

	ul = 0;
	__this_cpu_write(ulong_counter, 0);

	ul -= ui_one;
	__this_cpu_sub(ulong_counter, ui_one);
	CHECK(ul, ulong_counter, -1);
	CHECK(ul, ulong_counter, ULONG_MAX);

	ul = 3;
	__this_cpu_write(ulong_counter, 3);

	ul = this_cpu_sub_return(ulong_counter, ui_one);
	CHECK(ul, ulong_counter, 2);

	ul = __this_cpu_sub_return(ulong_counter, ui_one);
	CHECK(ul, ulong_counter, 1);

	preempt_enable();

	pr_info("percpu test done\n");
	return -EAGAIN;  /* Fail will directly unload the module */
}

static void __exit percpu_test_exit(void)
{
}

module_init(percpu_test_init)
module_exit(percpu_test_exit)

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Greg Thelen");
MODULE_DESCRIPTION("percpu operations test");
back to top