This reverts commit 05703271c3cd ("PCI/IOV: Add PCI rescan-remove
locking when enabling/disabling SR-IOV") which causes a deadlock by
recursively taking pci_rescan_remove_lock when sriov_del_vfs() is called
as part of pci_stop_and_remove_bus_device(). For example with the
following sequence of commands:

$ echo <NUM> > /sys/bus/pci/devices/<pf>/sriov_numvfs
$ echo 1 > /sys/bus/pci/devices/<pf>/remove

A trimmed trace of the deadlock on a mlx5 device is as below:

 mutex_lock_nested+0x3c/0x50
 sriov_disable+0x34/0x140
 mlx5_sriov_disable+0x50/0x80 [mlx5_core]
 remove_one+0x5e/0xf0 [mlx5_core]
 pci_device_remove+0x3c/0xa0
 device_release_driver_internal+0x18e/0x280
 pci_stop_bus_device+0x82/0xa0
 pci_stop_and_remove_bus_device_locked+0x5e/0x80
 remove_store+0x72/0x90

This is not a complete fix as it restores the issue the cited commit
tried to solve.

Cc: stable@vger.kernel.org
Fixes: 05703271c3cd ("PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV")
Reported-by: Benjamin Block <bblock@linux.ibm.com>
Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
---
 drivers/pci/iov.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 77dee43b785838d215b58db2d22088e9346e0583..ac4375954c9479b5f4a0e666b5215094fdaeefc2 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -629,18 +629,15 @@ static int sriov_add_vfs(struct pci_dev *dev, u16 num_vfs)
 	if (dev->no_vf_scan)
 		return 0;
 
-	pci_lock_rescan_remove();
 	for (i = 0; i < num_vfs; i++) {
 		rc = pci_iov_add_virtfn(dev, i);
 		if (rc)
 			goto failed;
 	}
-	pci_unlock_rescan_remove();
 	return 0;
 failed:
 	while (i--)
 		pci_iov_remove_virtfn(dev, i);
-	pci_unlock_rescan_remove();
 
 	return rc;
 }
@@ -765,10 +762,8 @@ static void sriov_del_vfs(struct pci_dev *dev)
 	struct pci_sriov *iov = dev->sriov;
 	int i;
 
-	pci_lock_rescan_remove();
 	for (i = 0; i < iov->num_VFs; i++)
 		pci_iov_remove_virtfn(dev, i);
-	pci_unlock_rescan_remove();
 }
 
 static void sriov_disable(struct pci_dev *dev)

-- 
2.48.1

On Wed, 2025-11-19 at 13:34 +0100, Niklas Schnelle wrote:
> This reverts commit 05703271c3cd ("PCI/IOV: Add PCI rescan-remove
> locking when enabling/disabling SR-IOV") which causes a deadlock by
> recursively taking pci_rescan_remove_lock when sriov_del_vfs() is called
> as part of pci_stop_and_remove_bus_device(). For example with the
> following sequence of commands:
> 
> $ echo <NUM> > /sys/bus/pci/devices/<pf>/sriov_numvfs
> $ echo 1 > /sys/bus/pci/devices/<pf>/remove
> 
> A trimmed trace of the deadlock on a mlx5 device is as below:
> 
>  mutex_lock_nested+0x3c/0x50
>  sriov_disable+0x34/0x140
>  mlx5_sriov_disable+0x50/0x80 [mlx5_core]
>  remove_one+0x5e/0xf0 [mlx5_core]
>  pci_device_remove+0x3c/0xa0
>  device_release_driver_internal+0x18e/0x280
>  pci_stop_bus_device+0x82/0xa0
>  pci_stop_and_remove_bus_device_locked+0x5e/0x80
>  remove_store+0x72/0x90

I just hit this recursive lock issue when running "reset" instead of
"remove"


$ echo <NUM> > /sys/bus/pci/devices/<pf>/sriov_numvfs
$ echo 1 > /sys/bus/pci/devices/<pf>/reset     

> This is not a complete fix as it restores the issue the cited commit
> tried to solve.
> 
> Cc: stable@vger.kernel.org
> Fixes: 05703271c3cd ("PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV")
> Reported-by: Benjamin Block <bblock@linux.ibm.com>
> Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
> Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
> ---
>  drivers/pci/iov.c | 5 -----
>  1 file changed, 5 deletions(-)
> 
> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> index 77dee43b785838d215b58db2d22088e9346e0583..ac4375954c9479b5f4a0e666b5215094fdaeefc2 100644
> --- a/drivers/pci/iov.c
> +++ b/drivers/pci/iov.c
> @@ -629,18 +629,15 @@ static int sriov_add_vfs(struct pci_dev *dev, u16 num_vfs)
>  	if (dev->no_vf_scan)
>  		return 0;
>  
> -	pci_lock_rescan_remove();
>  	for (i = 0; i < num_vfs; i++) {
>  		rc = pci_iov_add_virtfn(dev, i);
>  		if (rc)
>  			goto failed;
>  	}
> -	pci_unlock_rescan_remove();
>  	return 0;
>  failed:
>  	while (i--)
>  		pci_iov_remove_virtfn(dev, i);
> -	pci_unlock_rescan_remove();
>  
>  	return rc;
>  }
> @@ -765,10 +762,8 @@ static void sriov_del_vfs(struct pci_dev *dev)
>  	struct pci_sriov *iov = dev->sriov;
>  	int i;
>  
> -	pci_lock_rescan_remove();
>  	for (i = 0; i < iov->num_VFs; i++)
>  		pci_iov_remove_virtfn(dev, i);
> -	pci_unlock_rescan_remove();
>  }
>  
>  static void sriov_disable(struct pci_dev *dev)

Feel free to add my
Acked-by: Gerd Bayer <gbayer@linux.ibm.com>