From: Elad Nachman <eladv6@gmail.com>
To: ferruh.yigit@intel.com
Cc: iryzhov@nfware.com, stephen@networkplumber.org, dev@dpdk.org,
eladv6@gmail.com
Subject: [dpdk-dev] [PATCH 1/2] kni: fix kernel deadlock when using mlx devices
Date: Thu, 25 Feb 2021 16:32:38 +0200 [thread overview]
Message-ID: <20210225143239.14220-1-eladv6@gmail.com> (raw)
In-Reply-To: <20201126144613.4986-1-eladv6@gmail.com>
This first part of v4 of the patch re-introduces Stephen Hemminger's
patch 64106 . This part changes the parameter kni_net_process_request()
gets and introduces the initial rtnl unlocking mechanism.
Signed-off-by: Elad Nachman <eladv6@gmail.com>
---
v4:
* for if down case, send asynchronously with rtnl locked and without
wait, returning immediately to avoid both kernel race conditions
and deadlock in user-space
v3:
* Include original patch and new patch as a series of patch, added a
comment to the new patch
v2:
* rebuild the patch as increment from patch 64106
* fix comment and blank lines
---
kernel/linux/kni/kni_net.c | 34 ++++++++++++++++++----------------
1 file changed, 18 insertions(+), 16 deletions(-)
diff --git a/kernel/linux/kni/kni_net.c b/kernel/linux/kni/kni_net.c
index 4b752083d..f0b6e9a8d 100644
--- a/kernel/linux/kni/kni_net.c
+++ b/kernel/linux/kni/kni_net.c
@@ -17,6 +17,7 @@
#include <linux/skbuff.h>
#include <linux/kthread.h>
#include <linux/delay.h>
+#include <linux/rtnetlink.h>
#include <rte_kni_common.h>
#include <kni_fifo.h>
@@ -102,17 +103,15 @@ get_data_kva(struct kni_dev *kni, void *pkt_kva)
* It can be called to process the request.
*/
static int
-kni_net_process_request(struct kni_dev *kni, struct rte_kni_request *req)
+kni_net_process_request(struct net_device *dev, struct rte_kni_request *req)
{
+ struct kni_dev *kni = netdev_priv(dev);
int ret = -1;
void *resp_va;
uint32_t num;
int ret_val;
- if (!kni || !req) {
- pr_err("No kni instance or request\n");
- return -EINVAL;
- }
+ ASSERT_RTNL();
mutex_lock(&kni->sync_lock);
@@ -125,8 +124,17 @@ kni_net_process_request(struct kni_dev *kni, struct rte_kni_request *req)
goto fail;
}
+ /* Since we need to wait and RTNL mutex is held
+ * drop the mutex and hold reference to keep device
+ */
+ dev_hold(dev);
+ rtnl_unlock();
+
ret_val = wait_event_interruptible_timeout(kni->wq,
kni_fifo_count(kni->resp_q), 3 * HZ);
+ rtnl_lock();
+ dev_put(dev);
+
if (signal_pending(current) || ret_val <= 0) {
ret = -ETIME;
goto fail;
@@ -155,7 +163,6 @@ kni_net_open(struct net_device *dev)
{
int ret;
struct rte_kni_request req;
- struct kni_dev *kni = netdev_priv(dev);
netif_start_queue(dev);
if (kni_dflt_carrier == 1)
@@ -168,7 +175,7 @@ kni_net_open(struct net_device *dev)
/* Setting if_up to non-zero means up */
req.if_up = 1;
- ret = kni_net_process_request(kni, &req);
+ ret = kni_net_process_request(dev, &req);
return (ret == 0) ? req.result : ret;
}
@@ -178,7 +185,6 @@ kni_net_release(struct net_device *dev)
{
int ret;
struct rte_kni_request req;
- struct kni_dev *kni = netdev_priv(dev);
netif_stop_queue(dev); /* can't transmit any more */
netif_carrier_off(dev);
@@ -188,7 +194,7 @@ kni_net_release(struct net_device *dev)
/* Setting if_up to 0 means down */
req.if_up = 0;
- ret = kni_net_process_request(kni, &req);
+ ret = kni_net_process_request(dev, &req);
return (ret == 0) ? req.result : ret;
}
@@ -643,14 +649,13 @@ kni_net_change_mtu(struct net_device *dev, int new_mtu)
{
int ret;
struct rte_kni_request req;
- struct kni_dev *kni = netdev_priv(dev);
pr_debug("kni_net_change_mtu new mtu %d to be set\n", new_mtu);
memset(&req, 0, sizeof(req));
req.req_id = RTE_KNI_REQ_CHANGE_MTU;
req.new_mtu = new_mtu;
- ret = kni_net_process_request(kni, &req);
+ ret = kni_net_process_request(dev, &req);
if (ret == 0 && req.result == 0)
dev->mtu = new_mtu;
@@ -661,7 +666,6 @@ static void
kni_net_change_rx_flags(struct net_device *netdev, int flags)
{
struct rte_kni_request req;
- struct kni_dev *kni = netdev_priv(netdev);
memset(&req, 0, sizeof(req));
@@ -683,7 +687,7 @@ kni_net_change_rx_flags(struct net_device *netdev, int flags)
req.promiscusity = 0;
}
- kni_net_process_request(kni, &req);
+ kni_net_process_request(netdev, &req);
}
/*
@@ -742,7 +746,6 @@ kni_net_set_mac(struct net_device *netdev, void *p)
{
int ret;
struct rte_kni_request req;
- struct kni_dev *kni;
struct sockaddr *addr = p;
memset(&req, 0, sizeof(req));
@@ -754,8 +757,7 @@ kni_net_set_mac(struct net_device *netdev, void *p)
memcpy(req.mac_addr, addr->sa_data, netdev->addr_len);
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
- kni = netdev_priv(netdev);
- ret = kni_net_process_request(kni, &req);
+ ret = kni_net_process_request(netdev, &req);
return (ret == 0 ? req.result : ret);
}
--
2.17.1
next prev parent reply other threads:[~2021-02-25 14:32 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-26 14:46 [dpdk-dev] [PATCH] kni: fix rtnl deadlocks and race conditions Elad Nachman
2021-02-19 18:41 ` Ferruh Yigit
2021-02-21 8:03 ` Elad Nachman
2021-02-22 15:58 ` Ferruh Yigit
2021-02-23 12:05 ` [dpdk-dev] [PATCH V2] kni: fix rtnl deadlocks and race conditions v2 Elad Nachman
2021-02-23 12:53 ` Ferruh Yigit
2021-02-23 13:44 ` [dpdk-dev] [PATCH 1/2] kni: fix rtnl deadlocks and race conditions v3 Elad Nachman
2021-02-23 13:45 ` [dpdk-dev] [PATCH 2/2] " Elad Nachman
2021-02-24 12:49 ` Igor Ryzhov
2021-02-24 13:33 ` Elad Nachman
2021-02-24 14:04 ` Igor Ryzhov
2021-02-24 14:06 ` Elad Nachman
2021-02-24 14:41 ` Igor Ryzhov
2021-02-24 14:56 ` Elad Nachman
2021-02-24 15:18 ` Igor Ryzhov
[not found] ` <CACXF7qkhkzFc-=v=iiBzh2V7rLjk1U34VUfPbNrnYJND_0TKHQ@mail.gmail.com>
2021-02-24 16:31 ` Igor Ryzhov
2021-02-24 15:54 ` Stephen Hemminger
2021-02-25 14:32 ` Elad Nachman [this message]
2021-02-25 14:32 ` [dpdk-dev] [PATCH 2/2] kni: fix rtnl deadlocks and race conditions v4 Elad Nachman
2021-02-25 21:01 ` Igor Ryzhov
2021-02-26 15:48 ` Stephen Hemminger
2021-02-26 17:43 ` Elad Nachman
2021-03-01 8:10 ` Igor Ryzhov
2021-03-01 16:38 ` Stephen Hemminger
2021-03-15 16:58 ` Ferruh Yigit
2021-03-01 20:27 ` Dan Gora
2021-03-01 21:26 ` Dan Gora
2021-03-02 16:44 ` Elad Nachman
2021-03-15 17:17 ` Ferruh Yigit
2021-03-16 18:35 ` Elad Nachman
2021-03-16 18:42 ` Ferruh Yigit
2021-03-15 17:17 ` [dpdk-dev] [PATCH 1/2] kni: fix kernel deadlock when using mlx devices Ferruh Yigit
2021-03-29 14:36 ` [dpdk-dev] [PATCH v5 1/3] kni: refactor user request processing Ferruh Yigit
2021-03-29 14:36 ` [dpdk-dev] [PATCH v5 2/3] kni: support async user request Ferruh Yigit
2021-03-29 14:36 ` [dpdk-dev] [PATCH v5 3/3] kni: fix kernel deadlock when using mlx devices Ferruh Yigit
2021-04-09 14:56 ` [dpdk-dev] [dpdk-stable] " Ferruh Yigit
2021-04-12 14:35 ` Elad Nachman
2021-04-20 23:07 ` Thomas Monjalon
2021-04-23 8:41 ` Igor Ryzhov
2021-04-23 8:59 ` Ferruh Yigit
2021-04-23 12:43 ` Igor Ryzhov
2021-04-23 12:58 ` Igor Ryzhov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210225143239.14220-1-eladv6@gmail.com \
--to=eladv6@gmail.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=iryzhov@nfware.com \
--cc=stephen@networkplumber.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).