diff mbox series

[iwl-net,v2] e1000: Hold RTNL when e1000_down can be called

Message ID 20241023172745.181265-1-jdamato@fastly.com
State Accepted
Delegated to: Anthony Nguyen
Headers show
Series [iwl-net,v2] e1000: Hold RTNL when e1000_down can be called | expand

Commit Message

Joe Damato Oct. 23, 2024, 5:27 p.m. UTC
e1000_down calls netif_queue_set_napi, which assumes that RTNL is held.

There are a few paths for e1000_down to be called in e1000 where RTNL is
not currently being held:
  - e1000_shutdown (pci shutdown)
  - e1000_suspend (power management)
  - e1000_reinit_locked (via e1000_reset_task delayed work)
  - e1000_io_error_detected (via pci error handler)

Hold RTNL in three places to fix this issue:
  - e1000_reset_task: igc, igb, and e100e all hold rtnl in this path.
  - e1000_io_error_detected (pci error handler): e1000e and ixgbe hold
    rtnl in this path. A patch has been posted for igc to do the same
    [1].
  - __e1000_shutdown (which is called from both e1000_shutdown and
    e1000_suspend): igb, ixgbe, and e1000e all hold rtnl in the same
    path.

The other paths which call e1000_down seemingly hold RTNL and are OK:
  - e1000_close (ndo_stop)
  - e1000_change_mtu (ndo_change_mtu)

Based on the above analysis and mailing list discussion [2], I believe
adding rtnl in the three places mentioned above is correct.

Fixes: 8f7ff18a5ec7 ("e1000: Link NAPI instances to queues and IRQs")
Reported-by: Dmitry Antipov <dmantipov@yandex.ru>
Closes: https://lore.kernel.org/netdev/8cf62307-1965-46a0-a411-ff0080090ff9@yandex.ru/
Link: https://lore.kernel.org/netdev/20241022215246.307821-3-jdamato@fastly.com/ [1]
Link: https://lore.kernel.org/netdev/ZxgVRX7Ne-lTjwiJ@LQ3V64L9R2/ [2]
Signed-off-by: Joe Damato <jdamato@fastly.com>
---
 v2:
   - No longer an RFC
   - Include an rtnl_lock/rtnl_unlock in e1000_io_error_detected
     inspired by ixgbe's implementation of the same

 drivers/net/ethernet/intel/e1000/e1000_main.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)


base-commit: d05596f248578be943015c1237120574a8d845dd

Comments

Tony Nguyen Oct. 29, 2024, 10:48 p.m. UTC | #1
On 10/23/2024 10:27 AM, Joe Damato wrote:
> e1000_down calls netif_queue_set_napi, which assumes that RTNL is held.
> 
> There are a few paths for e1000_down to be called in e1000 where RTNL is
> not currently being held:
>    - e1000_shutdown (pci shutdown)
>    - e1000_suspend (power management)
>    - e1000_reinit_locked (via e1000_reset_task delayed work)
>    - e1000_io_error_detected (via pci error handler)
> 
> Hold RTNL in three places to fix this issue:
>    - e1000_reset_task: igc, igb, and e100e all hold rtnl in this path.
>    - e1000_io_error_detected (pci error handler): e1000e and ixgbe hold
>      rtnl in this path. A patch has been posted for igc to do the same
>      [1].
>    - __e1000_shutdown (which is called from both e1000_shutdown and
>      e1000_suspend): igb, ixgbe, and e1000e all hold rtnl in the same
>      path.
> 
> The other paths which call e1000_down seemingly hold RTNL and are OK:
>    - e1000_close (ndo_stop)
>    - e1000_change_mtu (ndo_change_mtu)
> 
> Based on the above analysis and mailing list discussion [2], I believe
> adding rtnl in the three places mentioned above is correct.
> 
> Fixes: 8f7ff18a5ec7 ("e1000: Link NAPI instances to queues and IRQs")

Hi Joe,

I've applied the patch to iwl-next as this commit hasn't landed in 
net/iwl-net yet.

Thanks,
Tony

> Reported-by: Dmitry Antipov <dmantipov@yandex.ru>
> Closes: https://lore.kernel.org/netdev/8cf62307-1965-46a0-a411-ff0080090ff9@yandex.ru/
> Link: https://lore.kernel.org/netdev/20241022215246.307821-3-jdamato@fastly.com/ [1]
> Link: https://lore.kernel.org/netdev/ZxgVRX7Ne-lTjwiJ@LQ3V64L9R2/ [2]
> Signed-off-by: Joe Damato <jdamato@fastly.com>
> ---
>   v2:
>     - No longer an RFC
>     - Include an rtnl_lock/rtnl_unlock in e1000_io_error_detected
>       inspired by ixgbe's implementation of the same
> 
>   drivers/net/ethernet/intel/e1000/e1000_main.c | 10 +++++++++-
>   1 file changed, 9 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
> index 4de9b156b2be..3f089c3d47b2 100644
> --- a/drivers/net/ethernet/intel/e1000/e1000_main.c
> +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
> @@ -3509,7 +3509,9 @@ static void e1000_reset_task(struct work_struct *work)
>   		container_of(work, struct e1000_adapter, reset_task);
>   
>   	e_err(drv, "Reset adapter\n");
> +	rtnl_lock();
>   	e1000_reinit_locked(adapter);
> +	rtnl_unlock();
>   }
>   
>   /**
> @@ -5074,7 +5076,9 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake)
>   			usleep_range(10000, 20000);
>   
>   		WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
> +		rtnl_lock();
>   		e1000_down(adapter);
> +		rtnl_unlock();
>   	}
>   
>   	status = er32(STATUS);
> @@ -5235,16 +5239,20 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
>   	struct net_device *netdev = pci_get_drvdata(pdev);
>   	struct e1000_adapter *adapter = netdev_priv(netdev);
>   
> +	rtnl_lock();
>   	netif_device_detach(netdev);
>   
> -	if (state == pci_channel_io_perm_failure)
> +	if (state == pci_channel_io_perm_failure) {
> +		rtnl_unlock();
>   		return PCI_ERS_RESULT_DISCONNECT;
> +	}
>   
>   	if (netif_running(netdev))
>   		e1000_down(adapter);
>   
>   	if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags))
>   		pci_disable_device(pdev);
> +	rtnl_unlock();
>   
>   	/* Request a slot reset. */
>   	return PCI_ERS_RESULT_NEED_RESET;
> 
> base-commit: d05596f248578be943015c1237120574a8d845dd
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 4de9b156b2be..3f089c3d47b2 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3509,7 +3509,9 @@  static void e1000_reset_task(struct work_struct *work)
 		container_of(work, struct e1000_adapter, reset_task);
 
 	e_err(drv, "Reset adapter\n");
+	rtnl_lock();
 	e1000_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**
@@ -5074,7 +5076,9 @@  static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake)
 			usleep_range(10000, 20000);
 
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
+		rtnl_lock();
 		e1000_down(adapter);
+		rtnl_unlock();
 	}
 
 	status = er32(STATUS);
@@ -5235,16 +5239,20 @@  static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	if (state == pci_channel_io_perm_failure)
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
+	}
 
 	if (netif_running(netdev))
 		e1000_down(adapter);
 
 	if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags))
 		pci_disable_device(pdev);
+	rtnl_unlock();
 
 	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;