[PATCH 5.19 238/365] igb: Add lock to avoid data race

[Greg Kroah-Hartman]

From: Lin Ma <linma@xxxxxxxxxx>

commit 6faee3d4ee8be0f0367d0c3d826afb3571b7a5e0 upstream.

The commit c23d92b80e0b ("igb: Teardown SR-IOV before
unregister_netdev()") places the unregister_netdev() call after the
igb_disable_sriov() call to avoid functionality issue.

However, it introduces several race conditions when detaching a device.
For example, when .remove() is called, the below interleaving leads to
use-after-free.

 (FREE from device detaching)      |   (USE from netdev core)
igb_remove                         |  igb_ndo_get_vf_config
 igb_disable_sriov                 |  vf >= adapter->vfs_allocated_count?
  kfree(adapter->vf_data)          |
  adapter->vfs_allocated_count = 0 |
                                   |    memcpy(... adapter->vf_data[vf]

Moreover, the igb_disable_sriov() also suffers from data race with the
requests from VF driver.

 (FREE from device detaching)      |   (USE from requests)
igb_remove                         |  igb_msix_other
 igb_disable_sriov                 |   igb_msg_task
  kfree(adapter->vf_data)          |    vf < adapter->vfs_allocated_count
  adapter->vfs_allocated_count = 0 |

To this end, this commit first eliminates the data races from netdev
core by using rtnl_lock (similar to commit 719479230893 ("dpaa2-eth: add
MAC/PHY support through phylink")). And then adds a spinlock to
eliminate races from driver requests. (similar to commit 1e53834ce541
("ixgbe: Add locking to prevent panic when setting sriov_numvfs to zero")

Fixes: c23d92b80e0b ("igb: Teardown SR-IOV before unregister_netdev()")
Signed-off-by: Lin Ma <linma@xxxxxxxxxx>
Tested-by: Konrad Jankowski <konrad0.jankowski@xxxxxxxxx>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@xxxxxxxxx>
Link: https://lore.kernel.org/r/20220817184921.735244-1-anthony.l.nguyen@xxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 drivers/net/ethernet/intel/igb/igb.h      |    2 ++
 drivers/net/ethernet/intel/igb/igb_main.c |   12 +++++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -664,6 +664,8 @@ struct igb_adapter {
 	struct igb_mac_addr *mac_table;
 	struct vf_mac_filter vf_macs;
 	struct vf_mac_filter *vf_mac_list;
+	/* lock for VF resources */
+	spinlock_t vfs_lock;
 };
 
 /* flags controlling PTP/1588 function */
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3637,6 +3637,7 @@ static int igb_disable_sriov(struct pci_
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 
 	/* reclaim resources allocated to VFs */
 	if (adapter->vf_data) {
@@ -3649,12 +3650,13 @@ static int igb_disable_sriov(struct pci_
 			pci_disable_sriov(pdev);
 			msleep(500);
 		}
-
+		spin_lock_irqsave(&adapter->vfs_lock, flags);
 		kfree(adapter->vf_mac_list);
 		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		adapter->vfs_allocated_count = 0;
+		spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
 		wrfl();
 		msleep(100);
@@ -3814,7 +3816,9 @@ static void igb_remove(struct pci_dev *p
 	igb_release_hw_control(adapter);
 
 #ifdef CONFIG_PCI_IOV
+	rtnl_lock();
 	igb_disable_sriov(pdev);
+	rtnl_unlock();
 #endif
 
 	unregister_netdev(netdev);
@@ -3974,6 +3978,9 @@ static int igb_sw_init(struct igb_adapte
 
 	spin_lock_init(&adapter->nfc_lock);
 	spin_lock_init(&adapter->stats64_lock);
+
+	/* init spinlock to avoid concurrency of VF resources */
+	spin_lock_init(&adapter->vfs_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
 	case e1000_82576:
@@ -7924,8 +7931,10 @@ unlock:
 static void igb_msg_task(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 	u32 vf;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
 		/* process any reset requests */
 		if (!igb_check_for_rst(hw, vf))
@@ -7939,6 +7948,7 @@ static void igb_msg_task(struct igb_adap
 		if (!igb_check_for_ack(hw, vf))
 			igb_rcv_ack_from_vf(adapter, vf);
 	}
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 }
 
 /**