DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ilya Maximets <i.maximets@samsung.com>
To: dev@dpdk.org
Cc: Wenzhuo Lu <wenzhuo.lu@intel.com>,
	Konstantin Ananyev <konstantin.ananyev@intel.com>,
	Laurent Hardy <laurent.hardy@6wind.com>,
	Wei Dai <wei.dai@intel.com>,
	Ilya Maximets <i.maximets@samsung.com>,
	stable@dpdk.org
Subject: [dpdk-dev] [PATCH] net/ixgbe: fix busy polling while fiber link update
Date: Fri, 31 Aug 2018 15:39:46 +0300	[thread overview]
Message-ID: <20180831123824eucas1p1cd2981c716c4764703e24c3eeb4d33c7~P_GOOSRuf0867908679eucas1p1K@eucas1p1.samsung.com> (raw)
In-Reply-To: <CGME20180831123824eucas1p1cd2981c716c4764703e24c3eeb4d33c7@eucas1p1.samsung.com>

If the multispeed fiber link is in DOWN state, ixgbe_setup_link
could take around a second of busy polling. This is highly
inconvenient for the case where single thread periodically
checks the link statuses. For example, OVS main thread
periodically updates the link statuses and hangs for a really
long time busy waiting on ixgbe_setup_link() for a DOWN fiber
ports. For case with 3 down ports it hangs for a 3 seconds and
unable to do anything including packet processing.
Fix that by shifting that workaround to a separate thread by
alarm handler that will try to set up link if it is DOWN.

Fixes: c12d22f65b13 ("net/ixgbe: ensure link status is updated")
CC: stable@dpdk.org

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
---
 drivers/net/ixgbe/ixgbe_ethdev.c | 43 ++++++++++++++++++++++++--------
 1 file changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index 26b192737..a33b9a6e8 100644
--- a/drivers/net/ixgbe/ixgbe_ethdev.c
+++ b/drivers/net/ixgbe/ixgbe_ethdev.c
@@ -221,6 +221,8 @@ static int ixgbe_dev_interrupt_action(struct rte_eth_dev *dev,
 				      struct rte_intr_handle *handle);
 static void ixgbe_dev_interrupt_handler(void *param);
 static void ixgbe_dev_interrupt_delayed_handler(void *param);
+static void ixgbe_dev_setup_link_alarm_handler(void *param);
+
 static int ixgbe_add_rar(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
 			 uint32_t index, uint32_t pool);
 static void ixgbe_remove_rar(struct rte_eth_dev *dev, uint32_t index);
@@ -2791,6 +2793,8 @@ ixgbe_dev_stop(struct rte_eth_dev *dev)
 
 	PMD_INIT_FUNC_TRACE();
 
+	rte_eal_alarm_cancel(ixgbe_dev_setup_link_alarm_handler, dev);
+
 	/* disable interrupts */
 	ixgbe_disable_intr(hw);
 
@@ -3969,6 +3973,25 @@ ixgbevf_check_link(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
 	return ret_val;
 }
 
+static void
+ixgbe_dev_setup_link_alarm_handler(void *param)
+{
+	struct rte_eth_dev *dev = (struct rte_eth_dev *)param;
+	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	struct ixgbe_interrupt *intr =
+		IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private);
+	u32 speed;
+	bool autoneg = false;
+
+	speed = hw->phy.autoneg_advertised;
+	if (!speed)
+		ixgbe_get_link_capabilities(hw, &speed, &autoneg);
+
+	ixgbe_setup_link(hw, speed, true);
+
+	intr->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
+}
+
 /* return 0 means link status changed, -1 means not changed */
 int
 ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
@@ -3981,9 +4004,7 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 		IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private);
 	int link_up;
 	int diag;
-	u32 speed = 0;
 	int wait = 1;
-	bool autoneg = false;
 
 	memset(&link, 0, sizeof(link));
 	link.link_status = ETH_LINK_DOWN;
@@ -3993,13 +4014,8 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 
 	hw->mac.get_link_status = true;
 
-	if ((intr->flags & IXGBE_FLAG_NEED_LINK_CONFIG) &&
-		ixgbe_get_media_type(hw) == ixgbe_media_type_fiber) {
-		speed = hw->phy.autoneg_advertised;
-		if (!speed)
-			ixgbe_get_link_capabilities(hw, &speed, &autoneg);
-		ixgbe_setup_link(hw, speed, true);
-	}
+	if (intr->flags & IXGBE_FLAG_NEED_LINK_CONFIG)
+		return rte_eth_linkstatus_set(dev, &link);
 
 	/* check if it needs to wait to complete, if lsc interrupt is enabled */
 	if (wait_to_complete == 0 || dev->data->dev_conf.intr_conf.lsc != 0)
@@ -4017,11 +4033,14 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
 	}
 
 	if (link_up == 0) {
-		intr->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
+		if (ixgbe_get_media_type(hw) == ixgbe_media_type_fiber) {
+			intr->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
+			rte_eal_alarm_set(10,
+				ixgbe_dev_setup_link_alarm_handler, dev);
+		}
 		return rte_eth_linkstatus_set(dev, &link);
 	}
 
-	intr->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
 	link.link_status = ETH_LINK_UP;
 	link.link_duplex = ETH_LINK_FULL_DUPLEX;
 
@@ -5128,6 +5147,8 @@ ixgbevf_dev_stop(struct rte_eth_dev *dev)
 
 	PMD_INIT_FUNC_TRACE();
 
+	rte_eal_alarm_cancel(ixgbe_dev_setup_link_alarm_handler, dev);
+
 	ixgbevf_intr_disable(dev);
 
 	hw->adapter_stopped = 1;
-- 
2.17.1

       reply	other threads:[~2018-08-31 12:38 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20180831123824eucas1p1cd2981c716c4764703e24c3eeb4d33c7@eucas1p1.samsung.com>
2018-08-31 12:39 ` Ilya Maximets [this message]
2018-09-04  6:08   ` Zhang, Qi Z
2018-09-10 15:08     ` Ilya Maximets
2018-09-12  6:49       ` Zhang, Qi Z
2018-09-12  8:05         ` Ilya Maximets
2018-09-12  8:28           ` Zhang, Qi Z
2018-09-21 14:25             ` Zhang, Qi Z
2018-10-03  7:43               ` Ilya Maximets
2018-10-09 10:22                 ` Zhao1, Wei
2018-10-11  9:56           ` Zhao1, Wei
2018-10-11 10:26             ` Ilya Maximets
2018-10-11 12:21               ` Laurent Hardy
2018-10-12  7:36                 ` Zhao1, Wei
2018-10-15 10:43                   ` Laurent Hardy
2018-10-16  8:29                     ` Zhao1, Wei
2018-10-12  9:19               ` Zhao1, Wei
2018-10-12 10:14                 ` Ilya Maximets
2018-10-15  3:03                   ` Zhao1, Wei
2018-10-15  8:40                     ` Ilya Maximets
2018-10-16  8:59                       ` Zhao1, Wei
2018-10-30 10:20   ` Ilya Maximets
2018-11-01 15:45     ` Zhang, Qi Z
2018-11-01 16:05       ` Ilya Maximets
     [not found]   ` <CGME20181101160505eucas1p1fcf268f3febaa80dcbb3e573b2fc2c68@eucas1p1.samsung.com>
2018-11-01 16:04     ` [dpdk-dev] [PATCH v2] " Ilya Maximets
2018-11-02 13:49       ` Zhang, Qi Z
2018-11-07 15:52       ` Burakov, Anatoly
2018-11-08 10:27         ` Ilya Maximets

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='20180831123824eucas1p1cd2981c716c4764703e24c3eeb4d33c7~P_GOOSRuf0867908679eucas1p1K@eucas1p1.samsung.com' \
    --to=i.maximets@samsung.com \
    --cc=dev@dpdk.org \
    --cc=konstantin.ananyev@intel.com \
    --cc=laurent.hardy@6wind.com \
    --cc=stable@dpdk.org \
    --cc=wei.dai@intel.com \
    --cc=wenzhuo.lu@intel.com \
    /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).