This happened when I tried to boot normal Fedora 29 system with latest
available kernel (from fedora rawhide, plus some unrelated custom
patches):

        BUG: unable to handle kernel NULL pointer dereference at 
0000000000000000
        PGD 0 P4D 0
        Oops: 0010 [#1] SMP PTI
        CPU: 6 PID: 1422 Comm: libvirtd Tainted: G          I       
4.20.0-0.rc7.git3.hpsa2.1.fc29.x86_64 #1
        Hardware name: HP ProLiant BL460c G6, BIOS I24 05/21/2018
        RIP: 0010:          (null)
        Code: Bad RIP value.
        RSP: 0018:ffffa47ccdc9fbe0 EFLAGS: 00010246
        RAX: 0000000000000000 RBX: 00000000000003e8 RCX: ffffa47ccdc9fbf8
        RDX: ffffa47ccdc9fc00 RSI: ffff97d9ee7b01f8 RDI: ffff97d9f0150b80
        RBP: ffff97d9f0150b80 R08: 0000000000000000 R09: 0000000000000000
        R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000003
        R13: ffff97d9ef1e53e8 R14: 0000000000000009 R15: ffff97d9f0ac6730
        FS:  00007f4d224ef700(0000) GS:ffff97d9fa200000(0000) 
knlGS:0000000000000000
        CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
        CR2: ffffffffffffffd6 CR3: 00000011ece52006 CR4: 00000000000206e0
        Call Trace:
         ? bnx2x_chip_cleanup+0x195/0x610 [bnx2x]
         ? bnx2x_nic_unload+0x1e2/0x8f0 [bnx2x]
         ? bnx2x_reload_if_running+0x24/0x40 [bnx2x]
         ? bnx2x_set_features+0x79/0xa0 [bnx2x]
         ? __netdev_update_features+0x244/0x9e0
         ? netlink_broadcast_filtered+0x136/0x4b0
         ? netdev_update_features+0x22/0x60
         ? dev_disable_lro+0x1c/0xe0
         ? devinet_sysctl_forward+0x1c6/0x211
         ? proc_sys_call_handler+0xab/0x100
         ? __vfs_write+0x36/0x1a0
         ? rcu_read_lock_sched_held+0x79/0x80
         ? rcu_sync_lockdep_assert+0x2e/0x60
         ? __sb_start_write+0x14c/0x1b0
         ? vfs_write+0x159/0x1c0
         ? vfs_write+0xba/0x1c0
         ? ksys_write+0x52/0xc0
         ? do_syscall_64+0x60/0x1f0
         ? entry_SYSCALL_64_after_hwframe+0x49/0xbe

After some investigation I figured out that recently added cleanup code
tries to call VLAN filtering de-initialization function which exist only
for newer hardware. Corresponding function pointer is not
initialized (== 0) for older hardware, namely these chips:

        #define CHIP_NUM_57710                  0x164e
        #define CHIP_NUM_57711                  0x164f
        #define CHIP_NUM_57711E                 0x1650

And I have one of those in my test system:

        02:00.0 Ethernet controller [0200]: Broadcom Inc. and subsidiaries 
NetXtreme II BCM57711E 10-Gigabit PCIe [14e4:1650]
        02:00.1 Ethernet controller [0200]: Broadcom Inc. and subsidiaries 
NetXtreme II BCM57711E 10-Gigabit PCIe [14e4:1650]

Function bnx2x_init_vlan_mac_fp_objs() from
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h decides whether to
initialize relevant pointers in bnx2x_sp_objs.vlan_obj or not.

This regression was introduced after v4.20-rc7.

Fixes: 04f05230c5c13 ("bnx2x: Remove configured vlans as part of unload 
sequence.")
Signed-off-by: Ivan Mironov <mironov.i...@gmail.com>
---
 .../net/ethernet/broadcom/bnx2x/bnx2x_main.c  | 22 +++++++++++++------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c 
b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index b164f705709d..0e37c2484ac2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8504,15 +8504,23 @@ int bnx2x_set_vlan_one(struct bnx2x *bp, u16 vlan,
 static int bnx2x_del_all_vlans(struct bnx2x *bp)
 {
        struct bnx2x_vlan_mac_obj *vlan_obj = &bp->sp_objs[0].vlan_obj;
-       unsigned long ramrod_flags = 0, vlan_flags = 0;
        struct bnx2x_vlan_entry *vlan;
-       int rc;
 
-       __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
-       __set_bit(BNX2X_VLAN, &vlan_flags);
-       rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_flags, &ramrod_flags);
-       if (rc)
-               return rc;
+       /* The whole *vlan_obj structure may be not initialized if VLAN
+        * filtering offload is not supported by hardware. Currently this is
+        * true for all hardware covered by CHIP_IS_E1x().
+        */
+       if (vlan_obj->delete_all) {
+               unsigned long ramrod_flags = 0, vlan_flags = 0;
+               int rc;
+
+               __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+               __set_bit(BNX2X_VLAN, &vlan_flags);
+               rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_flags,
+                                         &ramrod_flags);
+               if (rc)
+                       return rc;
+       }
 
        /* Mark that hw forgot all entries */
        list_for_each_entry(vlan, &bp->vlan_reg, link)
-- 
2.20.1

Reply via email to