Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix TCP checksum offload handling in iwlwifi driver, from Emmanuel
    Grumbach.

 2) In ksz DSA tagging code, free SKB if skb_put_padto() fails. From
    Vivien Didelot.

 3) Fix two regressions with bonding on wireless, from Andreas Born.

 4) Fix build when busypoll is disabled, from Daniel Borkmann.

 5) Fix copy_linear_skb() wrt. SO_PEEK_OFF, from Eric Dumazet.

 6) Set SKB cached route properly in inet_rtm_getroute(), from Florian
    Westphal.

 7) Fix PCI-E relaxed ordering handling in cxgb4 driver, from Ding
    Tianhong.

 8) Fix module refcnt leak in ULP code, from Sabrina Dubroca.

 9) Fix use of GFP_KERNEL in atomic contexts in AF_KEY code, from Eric
    Dumazet.

10) Need to purge socket write queue in dccp_destroy_sock(), also from
    Eric Dumazet.

11) Make bpf_trace_printk() work properly on 32-bit architectures, from
    Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (47 commits)
  bpf: fix bpf_trace_printk on 32 bit archs
  PCI: fix oops when try to find Root Port for a PCI device
  sfc: don't try and read ef10 data on non-ef10 NIC
  net_sched: remove warning from qdisc_hash_add
  net_sched/sfq: update hierarchical backlog when drop packet
  net_sched: reset pointers to tcf blocks in classful qdiscs' destructors
  ipv4: fix NULL dereference in free_fib_info_rcu()
  net: Fix a typo in comment about sock flags.
  ipv6: fix NULL dereference in ip6_route_dev_notify()
  tcp: fix possible deadlock in TCP stack vs BPF filter
  dccp: purge write queue in dccp_destroy_sock()
  udp: fix linear skb reception with PEEK_OFF
  ipv6: release rt6->rt6i_idev properly during ifdown
  af_key: do not use GFP_KERNEL in atomic contexts
  tcp: ulp: avoid module refcnt leak in tcp_set_ulp
  net/cxgb4vf: Use new PCI_DEV_FLAGS_NO_RELAXED_ORDERING flag
  net/cxgb4: Use new PCI_DEV_FLAGS_NO_RELAXED_ORDERING flag
  PCI: Disable Relaxed Ordering Attributes for AMD A1100
  PCI: Disable Relaxed Ordering for some Intel processors
  PCI: Disable PCIe Relaxed Ordering if unsupported
  ...

kernel/trace/bpf_trace.c

@@ -204,10 +204,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {