ice: prevent NULL pointer deref during reload

Calling ethtool during reload can lead to call trace, because VSI isn't
configured for some time, but netdev is alive.

To fix it add rtnl lock for VSI deconfig and config. Set ::num_q_vectors
to 0 after freeing and add a check for ::tx/rx_rings in ring related
ethtool ops.

Add proper unroll of filters in ice_start_eth().

Reproduction:
$watch -n 0.1 -d 'ethtool -g enp24s0f0np0'
$devlink dev reload pci/0000:18:00.0 action driver_reinit

Call trace before fix:
[66303.926205] BUG: kernel NULL pointer dereference, address: 0000000000000000
[66303.926259] #PF: supervisor read access in kernel mode
[66303.926286] #PF: error_code(0x0000) - not-present page
[66303.926311] PGD 0 P4D 0
[66303.926332] Oops: 0000 [#1] PREEMPT SMP PTI
[66303.926358] CPU: 4 PID: 933821 Comm: ethtool Kdump: loaded Tainted: G           OE      6.4.0-rc5+ #1
[66303.926400] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.00.01.0014.070920180847 07/09/2018
[66303.926446] RIP: 0010:ice_get_ringparam+0x22/0x50 [ice]
[66303.926649] Code: 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 48 8b 87 c0 09 00 00 c7 46 04 e0 1f 00 00 c7 46 10 e0 1f 00 00 48 8b 50 20 <48> 8b 12 0f b7 52 3a 89 56 14 48 8b 40 28 48 8b 00 0f b7 40 58 48
[66303.926722] RSP: 0018:ffffad40472f39c8 EFLAGS: 00010246
[66303.926749] RAX: ffff98a8ada05828 RBX: ffff98a8c46dd060 RCX: ffffad40472f3b48
[66303.926781] RDX: 0000000000000000 RSI: ffff98a8c46dd068 RDI: ffff98a8b23c4000
[66303.926811] RBP: ffffad40472f3b48 R08: 00000000000337b0 R09: 0000000000000000
[66303.926843] R10: 0000000000000001 R11: 0000000000000100 R12: ffff98a8b23c4000
[66303.926874] R13: ffff98a8c46dd060 R14: 000000000000000f R15: ffffad40472f3a50
[66303.926906] FS:  00007f6397966740(0000) GS:ffff98b390900000(0000) knlGS:0000000000000000
[66303.926941] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[66303.926967] CR2: 0000000000000000 CR3: 000000011ac20002 CR4: 00000000007706e0
[66303.926999] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[66303.927029] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[66303.927060] PKRU: 55555554
[66303.927075] Call Trace:
[66303.927094]  <TASK>
[66303.927111]  ? __die+0x23/0x70
[66303.927140]  ? page_fault_oops+0x171/0x4e0
[66303.927176]  ? exc_page_fault+0x7f/0x180
[66303.927209]  ? asm_exc_page_fault+0x26/0x30
[66303.927244]  ? ice_get_ringparam+0x22/0x50 [ice]
[66303.927433]  rings_prepare_data+0x62/0x80
[66303.927469]  ethnl_default_doit+0xe2/0x350
[66303.927501]  genl_family_rcv_msg_doit.isra.0+0xe3/0x140
[66303.927538]  genl_rcv_msg+0x1b1/0x2c0
[66303.927561]  ? __pfx_ethnl_default_doit+0x10/0x10
[66303.927590]  ? __pfx_genl_rcv_msg+0x10/0x10
[66303.927615]  netlink_rcv_skb+0x58/0x110
[66303.927644]  genl_rcv+0x28/0x40
[66303.927665]  netlink_unicast+0x19e/0x290
[66303.927691]  netlink_sendmsg+0x254/0x4d0
[66303.927717]  sock_sendmsg+0x93/0xa0
[66303.927743]  __sys_sendto+0x126/0x170
[66303.927780]  __x64_sys_sendto+0x24/0x30
[66303.928593]  do_syscall_64+0x5d/0x90
[66303.929370]  ? __count_memcg_events+0x60/0xa0
[66303.930146]  ? count_memcg_events.constprop.0+0x1a/0x30
[66303.930920]  ? handle_mm_fault+0x9e/0x350
[66303.931688]  ? do_user_addr_fault+0x258/0x740
[66303.932452]  ? exc_page_fault+0x7f/0x180
[66303.933193]  entry_SYSCALL_64_after_hwframe+0x72/0xdc

Fixes: 5b246e5 ("ice: split probe into smaller functions")
Reviewed-by: Przemek Kitszel <[email protected]>
Signed-off-by: Michal Swiatkowski <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Tested-by: Pucha Himasekhar Reddy <[email protected]> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <[email protected]>

Author: Michal Swiatkowski

drivers/net/ethernet/intel/ice/ice_base.c

@@ -800,6 +800,8 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
 
 	ice_for_each_q_vector(vsi, v_idx)
 		ice_free_q_vector(vsi, v_idx);
+
+	vsi->num_q_vectors = 0;
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -2681,8 +2681,13 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 
 	ring->rx_max_pending = ICE_MAX_NUM_DESC;
 	ring->tx_max_pending = ICE_MAX_NUM_DESC;
-	ring->rx_pending = vsi->rx_rings[0]->count;
-	ring->tx_pending = vsi->tx_rings[0]->count;
+	if (vsi->tx_rings && vsi->rx_rings) {
+		ring->rx_pending = vsi->rx_rings[0]->count;
+		ring->tx_pending = vsi->tx_rings[0]->count;
+	} else {
+		ring->rx_pending = 0;
+		ring->tx_pending = 0;
+	}
 
 	/* Rx mini and jumbo rings are not supported */
 	ring->rx_mini_max_pending = 0;
@@ -2716,6 +2721,10 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		return -EINVAL;
 	}
 
+	/* Return if there is no rings (device is reloading) */
+	if (!vsi->tx_rings || !vsi->rx_rings)
+		return -EBUSY;
+
 	new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE);
 	if (new_tx_cnt != ring->tx_pending)
 		netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n",

drivers/net/ethernet/intel/ice/ice_main.c

@@ -4430,9 +4430,9 @@ static int ice_start_eth(struct ice_vsi *vsi)
 	if (err)
 		return err;
 
-	rtnl_lock();
 	err = ice_vsi_open(vsi);
-	rtnl_unlock();
+	if (err)
+		ice_fltr_remove_all(vsi);
 
 	return err;
 }
@@ -4895,13 +4895,15 @@ int ice_load(struct ice_pf *pf)
 	params = ice_vsi_to_params(vsi);
 	params.flags = ICE_VSI_FLAG_INIT;
 
+	rtnl_lock();
 	err = ice_vsi_cfg(vsi, &params);
 	if (err)
 		goto err_vsi_cfg;
 
 	err = ice_start_eth(ice_get_main_vsi(pf));
 	if (err)
 		goto err_start_eth;
+	rtnl_unlock();
 
 	err = ice_init_rdma(pf);
 	if (err)
@@ -4916,9 +4918,11 @@ int ice_load(struct ice_pf *pf)
 
 err_init_rdma:
 	ice_vsi_close(ice_get_main_vsi(pf));
+	rtnl_lock();
 err_start_eth:
 	ice_vsi_decfg(ice_get_main_vsi(pf));
 err_vsi_cfg:
+	rtnl_unlock();
 	ice_deinit_dev(pf);
 	return err;
 }
@@ -4931,8 +4935,10 @@ void ice_unload(struct ice_pf *pf)
 {
 	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	rtnl_lock();
 	ice_stop_eth(ice_get_main_vsi(pf));
 	ice_vsi_decfg(ice_get_main_vsi(pf));
+	rtnl_unlock();
 	ice_deinit_dev(pf);
 }