netdev - Re: [PATCH net-next 1/2] net/smc: Introduce a specific sysctl for TEST

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20220920045520.GC108825@linux.alibaba.com>
Date:   Tue, 20 Sep 2022 12:55:20 +0800
From:   "dust.li" <dust.li@...ux.alibaba.com>
To:     Wen Gu <guwen@...ux.alibaba.com>, kgraul@...ux.ibm.com,
        wenjia@...ux.ibm.com, davem@...emloft.net, edumazet@...gle.com,
        kuba@...nel.org, pabeni@...hat.com
Cc:     linux-s390@...r.kernel.org, netdev@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next 1/2] net/smc: Introduce a specific sysctl for
 TEST_LINK time

On Tue, Sep 20, 2022 at 10:53:54AM +0800, Wen Gu wrote:
>SMC-R tests the viability of link by sending out TEST_LINK LLC
>messages over RoCE fabric when connections on link have been
>idle for a time longer than keepalive interval (testlink time).
>
>But using tcp_keepalive_time as testlink time maybe not quite
>suitable because it is default no less than two hours[1], which
>is too long for single link to find peer dead. The active host
>will still use peer-dead link (QP) sending messages, and can't
>find out until get IB_WC_RETRY_EXC_ERR error CQEs, which takes
>more time than TEST_LINK timeout (SMC_LLC_WAIT_TIME) normally.
>
>So this patch introduces a independent sysctl for SMC-R to set
>link keepalive time, in order to detect link down in time. The
>default value is 30 seconds.
>
>[1] https://www.rfc-editor.org/rfc/rfc1122#page-101
>
>Signed-off-by: Wen Gu <guwen@...ux.alibaba.com>
>---
> Documentation/networking/smc-sysctl.rst |  7 +++++++
> include/net/netns/smc.h                 |  1 +
> net/smc/smc_llc.c                       |  2 +-
> net/smc/smc_llc.h                       |  1 +
> net/smc/smc_sysctl.c                    | 14 ++++++++++++++
> 5 files changed, 24 insertions(+), 1 deletion(-)
>
>diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst
>index 742e90e..f8c3d59 100644
>--- a/Documentation/networking/smc-sysctl.rst
>+++ b/Documentation/networking/smc-sysctl.rst
>@@ -34,3 +34,10 @@ smcr_buf_type - INTEGER
>         - 1 - Use virtually contiguous buffers
>         - 2 - Mixed use of the two types. Try physically contiguous buffers first.
>           If not available, use virtually contiguous buffers then.
>+
>+smcr_testlink_time - INTEGER
>+	How frequently SMC-R link sends out TEST_LINK LLC messages to confirm
>+	viability, after the last activity of connections on it. The maximum
>+	value is (INT_MAX / HZ) seconds, the minimum value is 1 second.
>+
>+	Default: 30 seconds.
>diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h
>index 2adbe2b..d295e2c 100644
>--- a/include/net/netns/smc.h
>+++ b/include/net/netns/smc.h
>@@ -19,5 +19,6 @@ struct netns_smc {
> #endif
> 	unsigned int			sysctl_autocorking_size;
> 	unsigned int			sysctl_smcr_buf_type;
>+	int				sysctl_smcr_testlink_time;
> };
> #endif
>diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
>index 175026a..388bd2e 100644
>--- a/net/smc/smc_llc.c
>+++ b/net/smc/smc_llc.c
>@@ -2127,7 +2127,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc)
> 	init_waitqueue_head(&lgr->llc_flow_waiter);
> 	init_waitqueue_head(&lgr->llc_msg_waiter);
> 	mutex_init(&lgr->llc_conf_mutex);
>-	lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
>+	lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time) * HZ;
> }
> 
> /* called after lgr was removed from lgr_list */
>diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
>index 4404e52..1de9a29 100644
>--- a/net/smc/smc_llc.h
>+++ b/net/smc/smc_llc.h
>@@ -19,6 +19,7 @@
> 
> #define SMC_LLC_WAIT_FIRST_TIME		(5 * HZ)
> #define SMC_LLC_WAIT_TIME		(2 * HZ)
>+#define SMC_LLC_TESTLINK_DEFAULT_TIME	30

I'm wondering why we don't follow the upper to macros using (30 * HZ) ?


> 
> enum smc_llc_reqresp {
> 	SMC_LLC_REQ,
>diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
>index 0613868..7f68520 100644
>--- a/net/smc/smc_sysctl.c
>+++ b/net/smc/smc_sysctl.c
>@@ -16,8 +16,12 @@
> 
> #include "smc.h"
> #include "smc_core.h"
>+#include "smc_llc.h"
> #include "smc_sysctl.h"
> 
>+static int smcr_testlink_time_min = 1;
>+static int smcr_testlink_time_max = (INT_MAX / HZ);
>+
> static struct ctl_table smc_table[] = {
> 	{
> 		.procname       = "autocorking_size",
>@@ -35,6 +39,15 @@
> 		.extra1		= SYSCTL_ZERO,
> 		.extra2		= SYSCTL_TWO,
> 	},
>+	{
>+		.procname	= "smcr_testlink_time",
>+		.data		= &init_net.smc.sysctl_smcr_testlink_time,
>+		.maxlen		= sizeof(int),
>+		.mode		= 0644,
>+		.proc_handler	= proc_dointvec_minmax,
>+		.extra1		= &smcr_testlink_time_min,
>+		.extra2		= &smcr_testlink_time_max,
>+	},
> 	{  }
> };
> 
>@@ -60,6 +73,7 @@ int __net_init smc_sysctl_net_init(struct net *net)
> 
> 	net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
> 	net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS;
>+	net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME;
> 
> 	return 0;
> 
>-- 
>1.8.3.1