[Intel-wired-lan] [PATCH] ixgbe: Add locking to prevent panic when setting sriov_numvfs to zero.

[Szlosek, Marek]

It is possible to disable VFs while the PF driver is processing requests from the VF driver.  This can result in a panic.

BUG: unable to handle kernel paging request at 000000000000106c PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 8 PID: 0 Comm: swapper/8 Kdump: loaded Tainted: G          I      --------- -  -
Hardware name: Dell Inc. PowerEdge R740/06WXJT, BIOS 2.8.2 08/27/2020
RIP: 0010:ixgbe_msg_task+0x4c8/0x1690 [ixgbe]
Code: 00 00 48 8d 04 40 48 c1 e0 05 89 7c 24 24 89 fd 48 89 44 24 10 83 ff 01 0f 84 b8 04 00 00 4c 8b 64 24 10 4d 03 a5 48 22 00 00 <41> 80 7c 24 4c 00 0f 84 8a 03 00 00 0f b7 c7 83 f8 08 0f 84 8f 0a
RSP: 0018:ffffb337869f8df8 EFLAGS: 00010002
RAX: 0000000000001020 RBX: 0000000000000000 RCX: 000000000000002b
RDX: 0000000000000002 RSI: 0000000000000008 RDI: 0000000000000006
RBP: 0000000000000006 R08: 0000000000000002 R09: 0000000000029780
R10: 00006957d8f42832 R11: 0000000000000000 R12: 0000000000001020
R13: ffff8a00e8978ac0 R14: 000000000000002b R15: ffff8a00e8979c80
FS:  0000000000000000(0000) GS:ffff8a07dfd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000000106c CR3: 0000000063e10004 CR4: 00000000007726e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <IRQ>
 ? ttwu_do_wakeup+0x19/0x140
 ? try_to_wake_up+0x1cd/0x550
 ? ixgbevf_update_xcast_mode+0x71/0xc0 [ixgbevf]
 ixgbe_msix_other+0x17e/0x310 [ixgbe]
 __handle_irq_event_percpu+0x40/0x180
 handle_irq_event_percpu+0x30/0x80
 handle_irq_event+0x36/0x53
 handle_edge_irq+0x82/0x190
 handle_irq+0x1c/0x30
 do_IRQ+0x49/0xd0
 common_interrupt+0xf/0xf

This can be eventually be reproduced with the following script:

while :
do
	echo 63 > /sys/class/net/ens3f0/device/sriov_numvfs
	sleep 1
	echo 0 > /sys/class/net/ens3f0/device/sriov_numvfs
        sleep 1
done

Signed-off-by: Ken Cox <jkc at redhat.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h       | 1 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index a604552fa634..696bb2a61ea7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -807,6 +807,7 @@ enum ixgbe_state_t {
 	__IXGBE_PTP_RUNNING,
 	__IXGBE_PTP_TX_IN_PROGRESS,
 	__IXGBE_RESET_REQUESTED,
+	__IXGBE_DISABLING_VFS,
 };
 
 struct ixgbe_cb {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 214a38de3f41..e2df7729876d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -206,8 +206,12 @@ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
 	unsigned int num_vfs = adapter->num_vfs, vf;
 	int rss;
 
+       while (test_and_set_bit(__IXGBE_DISABLING_VFS, &adapter->state))
+               usleep_range(1000, 2000);
+
 	/* set num VFs to 0 to prevent access to vfinfo */
 	adapter->num_vfs = 0;
+	clear_bit(__IXGBE_DISABLING_VFS, &adapter->state);
 
 	/* put the reference to all of the vf devices */
 	for (vf = 0; vf < num_vfs; ++vf) {
@@ -1292,6 +1296,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 	return retval;
 }
 
+
 static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)  {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1307,6 +1312,9 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 vf;
 
+	if (test_and_set_bit(__IXGBE_DISABLING_VFS, &adapter->state))
+		return;
+
 	for (vf = 0; vf < adapter->num_vfs; vf++) {
 		/* process any reset requests */
 		if (!ixgbe_check_for_rst(hw, vf))
@@ -1320,6 +1328,7 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter)
 		if (!ixgbe_check_for_ack(hw, vf))
 			ixgbe_rcv_ack_from_vf(adapter, vf);
 	}
+	clear_bit(__IXGBE_DISABLING_VFS, &adapter->state);
 }
 
 void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
--
2.26.3

Tested-by: Marek Szlosek <marek.szlosek at intel.com>