net: 8139cp: fix a BUG triggered by changing mtu with network traffic

[ Upstream commit a5d4a892 ]

When changing mtu many times with traffic, a bug is triggered:

[ 1035.684037] kernel BUG at lib/dynamic_queue_limits.c:26!
[ 1035.684042] invalid opcode: 0000 [#1] SMP
[ 1035.684049] Modules linked in: loop binfmt_misc 8139cp(OE) macsec
tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag tcp_lp
fuse uinput xt_CHECKSUM iptable_mangle ipt_MASQUERADE
nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4
nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun
bridge stp llc ebtable_filter ebtables ip6table_filter devlink
ip6_tables iptable_filter sunrpc snd_hda_codec_generic snd_hda_intel
snd_hda_codec snd_hda_core snd_hwdep ppdev snd_seq iosf_mbi crc32_pclmul
parport_pc snd_seq_device ghash_clmulni_intel parport snd_pcm
aesni_intel joydev lrw snd_timer virtio_balloon sg gf128mul glue_helper
ablk_helper cryptd snd soundcore i2c_piix4 pcspkr ip_tables xfs
libcrc32c sr_mod sd_mod cdrom crc_t10dif crct10dif_generic ata_generic
[ 1035.684102]  pata_acpi virtio_console qxl drm_kms_helper syscopyarea
sysfillrect sysimgblt floppy fb_sys_fops crct10dif_pclmul
crct10dif_common ttm crc32c_intel serio_raw ata_piix drm libata 8139too
virtio_pci drm_panel_orientation_quirks virtio_ring virtio mii dm_mirror
dm_region_hash dm_log dm_mod [last unloaded: 8139cp]
[ 1035.684132] CPU: 9 PID: 25140 Comm: if-mtu-change Kdump: loaded
Tainted: G           OE  ------------ T 3.10.0-957.el7.x86_64 #1
[ 1035.684134] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[ 1035.684136] task: ffff8f59b1f5a080 ti: ffff8f5a2e32c000 task.ti:
ffff8f5a2e32c000
[ 1035.684149] RIP: 0010:[<ffffffffba3a40d0>]  [<ffffffffba3a40d0>]
dql_completed+0x180/0x190
[ 1035.684162] RSP: 0000:ffff8f5a75483e50  EFLAGS: 00010093
[ 1035.684162] RAX: 00000000000000c2 RBX: ffff8f5a6f91c000 RCX:
0000000000000000
[ 1035.684162] RDX: 0000000000000000 RSI: 0000000000000184 RDI:
ffff8f599fea3ec0
[ 1035.684162] RBP: ffff8f5a75483ea8 R08: 00000000000000c2 R09:
0000000000000000
[ 1035.684162] R10: 00000000000616ef R11: ffff8f5a75483b56 R12:
ffff8f599fea3e00
[ 1035.684162] R13: 0000000000000001 R14: 0000000000000000 R15:
0000000000000184
[ 1035.684162] FS:  00007fa8434de740(0000) GS:ffff8f5a75480000(0000)
knlGS:0000000000000000
[ 1035.684162] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1035.684162] CR2: 00000000004305d0 CR3: 000000024eb66000 CR4:
00000000001406e0
[ 1035.684162] Call Trace:
[ 1035.684162]  <IRQ>
[ 1035.684162]  [<ffffffffc08cbaf8>] ? cp_interrupt+0x478/0x580 [8139cp]
[ 1035.684162]  [<ffffffffba14a294>]
__handle_irq_event_percpu+0x44/0x1c0
[ 1035.684162]  [<ffffffffba14a442>] handle_irq_event_percpu+0x32/0x80
[ 1035.684162]  [<ffffffffba14a4cc>] handle_irq_event+0x3c/0x60
[ 1035.684162]  [<ffffffffba14db29>] handle_fasteoi_irq+0x59/0x110
[ 1035.684162]  [<ffffffffba02e554>] handle_irq+0xe4/0x1a0
[ 1035.684162]  [<ffffffffba7795dd>] do_IRQ+0x4d/0xf0
[ 1035.684162]  [<ffffffffba76b362>] common_interrupt+0x162/0x162
[ 1035.684162]  <EOI>
[ 1035.684162]  [<ffffffffba0c2ae4>] ? __wake_up_bit+0x24/0x70
[ 1035.684162]  [<ffffffffba1e46f5>] ? do_set_pte+0xd5/0x120
[ 1035.684162]  [<ffffffffba1b64fb>] unlock_page+0x2b/0x30
[ 1035.684162]  [<ffffffffba1e4879>] do_read_fault.isra.61+0x139/0x1b0
[ 1035.684162]  [<ffffffffba1e9134>] handle_pte_fault+0x2f4/0xd10
[ 1035.684162]  [<ffffffffba1ebc6d>] handle_mm_fault+0x39d/0x9b0
[ 1035.684162]  [<ffffffffba76f5e3>] __do_page_fault+0x203/0x500
[ 1035.684162]  [<ffffffffba76f9c6>] trace_do_page_fault+0x56/0x150
[ 1035.684162]  [<ffffffffba76ef42>] do_async_page_fault+0x22/0xf0
[ 1035.684162]  [<ffffffffba76b788>] async_page_fault+0x28/0x30
[ 1035.684162] Code: 54 c7 47 54 ff ff ff ff 44 0f 49 ce 48 8b 35 48 2f
9c 00 48 89 77 58 e9 fe fe ff ff 0f 1f 80 00 00 00 00 41 89 d1 e9 ef fe
ff ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 55 8d 42 ff 48
[ 1035.684162] RIP  [<ffffffffba3a40d0>] dql_completed+0x180/0x190
[ 1035.684162]  RSP <ffff8f5a75483e50>

It's not the same as in 7fe0ee09 patch described.
As 8139cp uses shared irq mode, other device irq will trigger
cp_interrupt to execute.

cp_change_mtu
 -> cp_close
 -> cp_open

In cp_close routine  just before free_irq(), some interrupt may occur.
In my environment, cp_interrupt exectutes and IntrStatus is 0x4,
exactly TxOk. That will cause cp_tx to wake device queue.

As device queue is started, cp_start_xmit and cp_open will run at same
time which will cause kernel BUG.

For example:
[#] for tx descriptor

At start:

[#][#][#]
num_queued=3

After cp_init_hw->cp_start_hw->netdev_reset_queue:

[#][#][#]
num_queued=0

When 8139cp starts to work then cp_tx will check
num_queued mismatchs the complete_bytes.

The patch will check IntrMask before check IntrStatus in cp_interrupt.
When 8139cp interrupt is disabled, just return.
Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/net/ethernet/realtek/8139cp.c

@@ -571,6 +571,7 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 	struct cp_private *cp;
 	int handled = 0;
 	u16 status;
+	u16 mask;
 
 	if (unlikely(dev == NULL))
 		return IRQ_NONE;
@@ -578,6 +579,10 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 
 	spin_lock(&cp->lock);
 
+	mask = cpr16(IntrMask);
+	if (!mask)
+		goto out_unlock;
+
 	status = cpr16(IntrStatus);
 	if (!status || (status == 0xFFFF))
 		goto out_unlock;