This is a note to let you know that I've just added the patch titled
igb: fix deadlock caused by taking RTNL in RPM resume path
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
igb-fix-deadlock-caused-by-taking-rtnl-in-rpm-resume.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit d0ad048b83b089e8c6c32f4e12e778f7568dec37
Author: Heiner Kallweit <hkallweit1@xxxxxxxxx>
Date: Mon Dec 20 12:18:44 2021 -0800
igb: fix deadlock caused by taking RTNL in RPM resume path
[ 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@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/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@xxxxxxxxx>
Signed-off-by: Heiner Kallweit <hkallweit1@xxxxxxxxx>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@xxxxxxxxx>
Link: https://lore.kernel.org/r/20211220201844.2714498-1-anthony.l.nguyen@xxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 533199d819501..82a712f77cb34 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -9247,7 +9247,7 @@ 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);
@@ -9290,17 +9290,24 @@ 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);
@@ -9319,7 +9326,7 @@ 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)
@@ -9435,7 +9442,7 @@ 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)
{
@@ -9475,7 +9482,7 @@ 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)
{
