Re: [PATCH v2] PCI: lock each enable/disable num_vfs operation in sysfs

[Bjorn Helgaas]

On Fri, Jan 06, 2017 at 01:59:08PM -0800, Emil Tantilov wrote:
> Enabling/disabling SRIOV via sysfs by echo-ing multiple values
> simultaneously:
> 
> echo 63 > /sys/class/net/ethX/device/sriov_numvfs&
> echo 63 > /sys/class/net/ethX/device/sriov_numvfs
> 
> sleep 5
> 
> echo 0 > /sys/class/net/ethX/device/sriov_numvfs&
> echo 0 > /sys/class/net/ethX/device/sriov_numvfs
> 
> Results in the following bug:
> 
> kernel BUG at drivers/pci/iov.c:495!
> invalid opcode: 0000 [#1] SMP
> CPU: 1 PID: 8050 Comm: bash Tainted: G   W   4.9.0-rc7-net-next #2092
> RIP: 0010:[<ffffffff813b1647>]
> 	  [<ffffffff813b1647>] pci_iov_release+0x57/0x60
> 
> Call Trace:
>  [<ffffffff81391726>] pci_release_dev+0x26/0x70
>  [<ffffffff8155be6e>] device_release+0x3e/0xb0
>  [<ffffffff81365ee7>] kobject_cleanup+0x67/0x180
>  [<ffffffff81365d9d>] kobject_put+0x2d/0x60
>  [<ffffffff8155bc27>] put_device+0x17/0x20
>  [<ffffffff8139c08a>] pci_dev_put+0x1a/0x20
>  [<ffffffff8139cb6b>] pci_get_dev_by_id+0x5b/0x90
>  [<ffffffff8139cca5>] pci_get_subsys+0x35/0x40
>  [<ffffffff8139ccc8>] pci_get_device+0x18/0x20
>  [<ffffffff8139ccfb>] pci_get_domain_bus_and_slot+0x2b/0x60
>  [<ffffffff813b09e7>] pci_iov_remove_virtfn+0x57/0x180
>  [<ffffffff813b0b95>] pci_disable_sriov+0x65/0x140
>  [<ffffffffa00a1af7>] ixgbe_disable_sriov+0xc7/0x1d0 [ixgbe]
>  [<ffffffffa00a1e9d>] ixgbe_pci_sriov_configure+0x3d/0x170 [ixgbe]
>  [<ffffffff8139d28c>] sriov_numvfs_store+0xdc/0x130
> ...
> RIP  [<ffffffff813b1647>] pci_iov_release+0x57/0x60
> 
> Use the existing mutex lock to protect each enable/disable operation.
> 
> -v2: move the existing lock from protecting the config of the IOV bus
> to protecting the writes to sriov_numvfs in sysfs without maintaining
> a "locked" version of pci_iov_add/remove_virtfn().
> As suggested by Gavin Shan <gwshan@xxxxxxxxxxxxxxxxxx>
> 
> CC: Alexander Duyck <alexander.h.duyck@xxxxxxxxx>
> Signed-off-by: Emil Tantilov <emil.s.tantilov@xxxxxxxxx>

Applied with Gavin's reviewed-by to pci/virtualization for v4.11, thanks!

> ---
>  drivers/pci/iov.c       |    7 -------
>  drivers/pci/pci-sysfs.c |   23 ++++++++++++++++-------
>  drivers/pci/pci.h       |    2 +-
>  3 files changed, 17 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> index 4722782..2479ae8 100644
> --- a/drivers/pci/iov.c
> +++ b/drivers/pci/iov.c
> @@ -124,7 +124,6 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
>  	struct pci_sriov *iov = dev->sriov;
>  	struct pci_bus *bus;
>  
> -	mutex_lock(&iov->dev->sriov->lock);
>  	bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id));
>  	if (!bus)
>  		goto failed;
> @@ -162,7 +161,6 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
>  		__pci_reset_function(virtfn);
>  
>  	pci_device_add(virtfn, virtfn->bus);
> -	mutex_unlock(&iov->dev->sriov->lock);
>  
>  	pci_bus_add_device(virtfn);
>  	sprintf(buf, "virtfn%u", id);
> @@ -181,12 +179,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset)
>  	sysfs_remove_link(&dev->dev.kobj, buf);
>  failed1:
>  	pci_dev_put(dev);
> -	mutex_lock(&iov->dev->sriov->lock);
>  	pci_stop_and_remove_bus_device(virtfn);
>  failed0:
>  	virtfn_remove_bus(dev->bus, bus);
>  failed:
> -	mutex_unlock(&iov->dev->sriov->lock);
>  
>  	return rc;
>  }
> @@ -195,7 +191,6 @@ void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset)
>  {
>  	char buf[VIRTFN_ID_LEN];
>  	struct pci_dev *virtfn;
> -	struct pci_sriov *iov = dev->sriov;
>  
>  	virtfn = pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
>  					     pci_iov_virtfn_bus(dev, id),
> @@ -218,10 +213,8 @@ void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset)
>  	if (virtfn->dev.kobj.sd)
>  		sysfs_remove_link(&virtfn->dev.kobj, "physfn");
>  
> -	mutex_lock(&iov->dev->sriov->lock);
>  	pci_stop_and_remove_bus_device(virtfn);
>  	virtfn_remove_bus(dev->bus, virtfn->bus);
> -	mutex_unlock(&iov->dev->sriov->lock);
>  
>  	/* balance pci_get_domain_bus_and_slot() */
>  	pci_dev_put(virtfn);
> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index 0666287..25d010d 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
> @@ -472,6 +472,7 @@ static ssize_t sriov_numvfs_store(struct device *dev,
>  				  const char *buf, size_t count)
>  {
>  	struct pci_dev *pdev = to_pci_dev(dev);
> +	struct pci_sriov *iov = pdev->sriov;
>  	int ret;
>  	u16 num_vfs;
>  
> @@ -482,38 +483,46 @@ static ssize_t sriov_numvfs_store(struct device *dev,
>  	if (num_vfs > pci_sriov_get_totalvfs(pdev))
>  		return -ERANGE;
>  
> +	mutex_lock(&iov->dev->sriov->lock);
> +
>  	if (num_vfs == pdev->sriov->num_VFs)
> -		return count;		/* no change */
> +		goto exit;
>  
>  	/* is PF driver loaded w/callback */
>  	if (!pdev->driver || !pdev->driver->sriov_configure) {
>  		dev_info(&pdev->dev, "Driver doesn't support SRIOV configuration via sysfs\n");
> -		return -ENOSYS;
> +		ret = -ENOENT;
> +		goto exit;
>  	}
>  
>  	if (num_vfs == 0) {
>  		/* disable VFs */
>  		ret = pdev->driver->sriov_configure(pdev, 0);
> -		if (ret < 0)
> -			return ret;
> -		return count;
> +		goto exit;
>  	}
>  
>  	/* enable VFs */
>  	if (pdev->sriov->num_VFs) {
>  		dev_warn(&pdev->dev, "%d VFs already enabled. Disable before enabling %d VFs\n",
>  			 pdev->sriov->num_VFs, num_vfs);
> -		return -EBUSY;
> +		ret = -EBUSY;
> +		goto exit;
>  	}
>  
>  	ret = pdev->driver->sriov_configure(pdev, num_vfs);
>  	if (ret < 0)
> -		return ret;
> +		goto exit;
>  
>  	if (ret != num_vfs)
>  		dev_warn(&pdev->dev, "%d VFs requested; only %d enabled\n",
>  			 num_vfs, ret);
>  
> +exit:
> +	mutex_unlock(&iov->dev->sriov->lock);
> +
> +	if (ret < 0)
> +		return ret;
> +
>  	return count;
>  }
>  
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index cb17db2..8dd38e6 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -270,7 +270,7 @@ struct pci_sriov {
>  	u16 driver_max_VFs;	/* max num VFs driver supports */
>  	struct pci_dev *dev;	/* lowest numbered PF */
>  	struct pci_dev *self;	/* this PF */
> -	struct mutex lock;	/* lock for VF bus */
> +	struct mutex lock;	/* lock for setting sriov_numvfs in sysfs */
>  	resource_size_t barsz[PCI_SRIOV_NUM_BARS];	/* VF BAR size */
>  };
>  
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pci" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html