netdev - [WIP v2] igc: fix deadlock caused by taking RTNL in RPM resume path

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: <20220811202524.78323-1-vinicius.gomes@intel.com>
Date:   Thu, 11 Aug 2022 17:25:24 -0300
From:   Vinicius Costa Gomes <vinicius.gomes@...el.com>
To:     jhogan@...nel.org
Cc:     Vinicius Costa Gomes <vinicius.gomes@...el.com>,
        Paul Menzel <pmenzel@...gen.mpg.de>,
        Tony Nguyen <anthony.l.nguyen@...el.com>,
        Jesse Brandeburg <jesse.brandeburg@...el.com>,
        netdev@...r.kernel.org, intel-wired-lan@...ts.osuosl.org,
        Sasha Neftin <sasha.neftin@...el.com>,
        Aleksandr Loktionov <aleksandr.loktionov@...el.com>
Subject: [WIP v2] igc: fix deadlock caused by taking RTNL in RPM resume path

It was reported a RTNL deadlock in the igc driver that was causing
problems during suspend/resume.

The solution is similar to commit ac8c58f5b535 ("igb: fix deadlock
caused by taking RTNL in RPM resume path").

Reported-by: James Hogan <jhogan@...nel.org>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@...el.com>
---
Sorry for the noise earlier, my kernel config didn't have runtime PM
enabled.


 drivers/net/ethernet/intel/igc/igc_main.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ebff0e04045d..9b0d4becfcfc 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6600,7 +6600,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int __maybe_unused igc_resume(struct device *dev)
+static int __maybe_unused __igc_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -6642,20 +6642,27 @@ static int __maybe_unused igc_resume(struct device *dev)
 
 	wr32(IGC_WUS, ~0);
 
-	rtnl_lock();
+	if (!rpm)
+		rtnl_lock();
 	if (!err && netif_running(netdev))
 		err = __igc_open(netdev, true);
 
 	if (!err)
 		netif_device_attach(netdev);
-	rtnl_unlock();
+	if (!rpm)
+		rtnl_unlock();
 
 	return err;
 }
 
 static int __maybe_unused igc_runtime_resume(struct device *dev)
 {
-	return igc_resume(dev);
+	return __igc_resume(dev, true);
+}
+
+static int __maybe_unused igc_resume(struct device *dev)
+{
+	return __igc_resume(dev, false);
 }
 
 static int __maybe_unused igc_suspend(struct device *dev)
@@ -6719,7 +6726,7 @@ static pci_ers_result_t igc_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 igc_resume routine.
+ *  resembles the first-half of the __igc_resume routine.
  **/
 static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 {
@@ -6758,7 +6765,7 @@ static pci_ers_result_t igc_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 igc_resume routine.
+ *  second-half of the __igc_resume routine.
  */
 static void igc_io_resume(struct pci_dev *pdev)
 {
-- 
2.37.1