lkml.org 
[lkml]   [2021]   [Dec]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 5.10 20/76] igb: fix deadlock caused by taking RTNL in RPM resume path
Date
From: Heiner Kallweit <hkallweit1@gmail.com>

[ Upstream commit ac8c58f5b535d6272324e2b8b4a0454781c9147e ]

Recent net core changes caused an issue with few Intel drivers
(reportedly igb), where taking RTNL in RPM resume path results in a
deadlock. See [0] for a bug report. I don't think the core changes
are wrong, but taking RTNL in RPM resume path isn't needed.
The Intel drivers are the only ones doing this. See [1] for a
discussion on the issue. Following patch changes the RPM resume path
to not take RTNL.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=215129
[1] https://lore.kernel.org/netdev/20211125074949.5f897431@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com/t/

Fixes: bd869245a3dc ("net: core: try to runtime-resume detached device in __dev_open")
Fixes: f32a21376573 ("ethtool: runtime-resume netdev parent before ethtool ioctl ops")
Tested-by: Martin Stolpe <martin.stolpe@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20211220201844.2714498-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/intel/igb/igb_main.c | 19 +++++++++++++------
1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 1662c0985eca4..f854d41c6c94d 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -9260,7 +9260,7 @@ static int __maybe_unused igb_suspend(struct device *dev)
return __igb_shutdown(to_pci_dev(dev), NULL, 0);
}

-static int __maybe_unused igb_resume(struct device *dev)
+static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
@@ -9303,17 +9303,24 @@ static int __maybe_unused igb_resume(struct device *dev)

wr32(E1000_WUS, ~0);

- rtnl_lock();
+ if (!rpm)
+ rtnl_lock();
if (!err && netif_running(netdev))
err = __igb_open(netdev, true);

if (!err)
netif_device_attach(netdev);
- rtnl_unlock();
+ if (!rpm)
+ rtnl_unlock();

return err;
}

+static int __maybe_unused igb_resume(struct device *dev)
+{
+ return __igb_resume(dev, false);
+}
+
static int __maybe_unused igb_runtime_idle(struct device *dev)
{
struct net_device *netdev = dev_get_drvdata(dev);
@@ -9332,7 +9339,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev)

static int __maybe_unused igb_runtime_resume(struct device *dev)
{
- return igb_resume(dev);
+ return __igb_resume(dev, true);
}

static void igb_shutdown(struct pci_dev *pdev)
@@ -9448,7 +9455,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
* @pdev: Pointer to PCI device
*
* Restart the card from scratch, as if from a cold-boot. Implementation
- * resembles the first-half of the igb_resume routine.
+ * resembles the first-half of the __igb_resume routine.
**/
static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
{
@@ -9488,7 +9495,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
*
* This callback is called when the error recovery driver tells us that
* its OK to resume normal operation. Implementation resembles the
- * second-half of the igb_resume routine.
+ * second-half of the __igb_resume routine.
*/
static void igb_io_resume(struct pci_dev *pdev)
{
--
2.34.1


\
 
 \ /
  Last update: 2021-12-27 16:39    [W:0.586 / U:1.316 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site