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

Pull networking fixes from David Miller:
 "Lots of fixes, here goes:

   1) NULL deref in qtnfmac, from Gustavo A. R. Silva.

   2) Kernel oops when fw download fails in rtlwifi, from Ping-Ke Shih.

   3) Lost completion messages in AF_XDP, from Magnus Karlsson.

   4) Correct bogus self-assignment in rhashtable, from Rishabh
      Bhatnagar.

   5) Fix regression in ipv6 route append handling, from David Ahern.

   6) Fix masking in __set_phy_supported(), from Heiner Kallweit.

   7) Missing module owner set in x_tables icmp, from Florian Westphal.

   8) liquidio's timeouts are HZ dependent, fix from Nicholas Mc Guire.

   9) Link setting fixes for sh_eth and ravb, from Vladimir Zapolskiy.

  10) Fix NULL deref when using chains in act_csum, from Davide Caratti.

  11) XDP_REDIRECT needs to check if the interface is up and whether the
      MTU is sufficient. From Toshiaki Makita.

  12) Net diag can do a double free when killing TCP_NEW_SYN_RECV
      connections, from Lorenzo Colitti.

  13) nf_defrag in ipv6 can unnecessarily hold onto dst entries for a
      full minute, delaying device unregister. From Eric Dumazet.

  14) Update MAC entries in the correct order in ixgbe, from Alexander
      Duyck.

  15) Don't leave partial mangles bpf program in jit_subprogs, from
      Daniel Borkmann.

  16) Fix pfmemalloc SKB state propagation, from Stefano Brivio.

  17) Fix ACK handling in DCTCP congestion control, from Yuchung Cheng.

  18) Use after free in tun XDP_TX, from Toshiaki Makita.

  19) Stale ipv6 header pointer in ipv6 gre code, from Prashant Bhole.

  20) Don't reuse remainder of RX page when XDP is set in mlx4, from
      Saeed Mahameed.

  21) Fix window probe handling of TCP rapair sockets, from Stefan
      Baranoff.

  22) Missing socket locking in smc_ioctl(), from Ursula Braun.

  23) IPV6_ILA needs DST_CACHE, from Arnd Bergmann.

  24) Spectre v1 fix in cxgb3, from Gustavo A. R. Silva.

  25) Two spots in ipv6 do a rol32() on a hash value but ignore the
      result. Fixes from Colin Ian King"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (176 commits)
  tcp: identify cryptic messages as TCP seq # bugs
  ptp: fix missing break in switch
  hv_netvsc: Fix napi reschedule while receive completion is busy
  MAINTAINERS: Drop inactive Vitaly Bordug's email
  net: cavium: Add fine-granular dependencies on PCI
  net: qca_spi: Fix log level if probe fails
  net: qca_spi: Make sure the QCA7000 reset is triggered
  net: qca_spi: Avoid packet drop during initial sync
  ipv6: fix useless rol32 call on hash
  ipv6: sr: fix useless rol32 call on hash
  net: sched: Using NULL instead of plain integer
  net: usb: asix: replace mii_nway_restart in resume path
  net: cxgb3_main: fix potential Spectre v1
  lib/rhashtable: consider param->min_size when setting initial table size
  net/smc: reset recv timeout after clc handshake
  net/smc: add error handling for get_user()
  net/smc: optimize consumer cursor updates
  net/nfc: Avoid stalls when nfc_alloc_send_skb() returned NULL.
  ipv6: ila: select CONFIG_DST_CACHE
  net: usb: rtl8150: demote allmulti message to dev_dbg()
  ...

3 files changed, 136 insertions, 30 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 0ca6907d7efe..06da770f543f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 	     (!unaligned_ok && offset >= 0 &&
 	      offset + ip_align >= 0 &&
 	      offset + ip_align % size == 0))) {
+		bool ldx_off_ok = offset <= S16_MAX;
+
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
 		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
-		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
-		*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
-				      offset);
+		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
+				      size, 2 + endian + (!ldx_off_ok * 2));
+		if (ldx_off_ok) {
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_D, offset);
+		} else {
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
+			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_TMP, 0);
+		}
 		if (endian)
 			*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
 		*insn++ = BPF_JMP_A(8);
@@ -1762,6 +1772,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static inline int sk_skb_try_make_writable(struct sk_buff *skb,
+					   unsigned int write_len)
+{
+	int err = __bpf_try_make_writable(skb, write_len);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return err;
+}
+
+BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
+{
+	/* Idea is the following: should the needed direct read/write
+	 * test fail during runtime, we can pull in more data and redo
+	 * again, since implicitly, we invalidate previous checks here.
+	 *
+	 * Or, since we know how much we need to make read/writeable,
+	 * this can be done once at the program beginning for direct
+	 * access case. By this we overcome limitations of only current
+	 * headroom being accessible.
+	 */
+	return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
+}
+
+static const struct bpf_func_proto sk_skb_pull_data_proto = {
+	.func		= sk_skb_pull_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
 	   u64, from, u64, to, u64, flags)
 {
@@ -2779,7 +2820,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
 
 static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 {
-	return skb->dev->mtu + skb->dev->hard_header_len;
+	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
+			  SKB_MAX_ALLOC;
 }
 
 static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
@@ -2863,8 +2905,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 	return __skb_trim_rcsum(skb, new_len);
 }
 
-BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
-	   u64, flags)
+static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
+					u64 flags)
 {
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 min_len = __bpf_skb_min_len(skb);
@@ -2900,6 +2942,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 		if (!ret && skb_is_gso(skb))
 			skb_gso_reset(skb);
 	}
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
@@ -2914,9 +2963,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 	   u64, flags)
 {
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_tail_proto = {
+	.func		= sk_skb_change_tail,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
+					u64 flags)
+{
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 new_len = skb->len + head_room;
 	int ret;
@@ -2941,8 +3008,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
 		skb_reset_mac_header(skb);
 	}
 
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
 	bpf_compute_data_pointers(skb);
-	return 0;
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_skb_change_head_proto = {
@@ -2954,6 +3029,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_head_proto = {
+	.func		= sk_skb_change_head,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
 static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
 {
 	return xdp_data_meta_unsupported(xdp) ? 0 :
@@ -3046,12 +3138,16 @@ static int __bpf_tx_xdp(struct net_device *dev,
 			u32 index)
 {
 	struct xdp_frame *xdpf;
-	int sent;
+	int err, sent;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit) {
 		return -EOPNOTSUPP;
 	}
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -3285,7 +3381,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 		goto err;
 	}
 
-	if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+	err = xdp_ok_fwd_dev(fwd, skb->len);
+	if (unlikely(err))
 		goto err;
 
 	skb->dev = fwd;
@@ -4439,10 +4536,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
 	.arg4_type	= ARG_CONST_SIZE
 };
 
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 	   const void *, from, u32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_tlvs, *srh_end, *ptr;
@@ -4468,9 +4565,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 
 	memcpy(skb->data + offset, from, len);
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
@@ -4486,7 +4580,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
 BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	   u32, action, void *, param, u32, param_len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	struct ipv6_sr_hdr *srh;
@@ -4534,9 +4627,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	default:
 		return -EINVAL;
 	}
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
@@ -4552,7 +4642,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
 BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	   s32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_end, *srh_tlvs, *ptr;
@@ -4596,9 +4685,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	srh_state->hdrlen += len;
 	srh_state->valid = 0;
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
@@ -4609,6 +4695,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
+#endif /* CONFIG_IPV6_SEG6_BPF */
 
 bool bpf_helper_changes_pkt_data(void *func)
 {
@@ -4617,9 +4704,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_store_bytes ||
 	    func == bpf_skb_change_proto ||
 	    func == bpf_skb_change_head ||
+	    func == sk_skb_change_head ||
 	    func == bpf_skb_change_tail ||
+	    func == sk_skb_change_tail ||
 	    func == bpf_skb_adjust_room ||
 	    func == bpf_skb_pull_data ||
+	    func == sk_skb_pull_data ||
 	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
@@ -4627,11 +4717,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
 	    func == bpf_xdp_adjust_tail ||
-	    func == bpf_lwt_push_encap ||
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
 	    func == bpf_lwt_seg6_adjust_srh ||
-	    func == bpf_lwt_seg6_action
-	    )
+	    func == bpf_lwt_seg6_action ||
+#endif
+	    func == bpf_lwt_push_encap)
 		return true;
 
 	return false;
@@ -4871,11 +4962,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
 	case BPF_FUNC_skb_pull_data:
-		return &bpf_skb_pull_data_proto;
+		return &sk_skb_pull_data_proto;
 	case BPF_FUNC_skb_change_tail:
-		return &bpf_skb_change_tail_proto;
+		return &sk_skb_change_tail_proto;
 	case BPF_FUNC_skb_change_head:
-		return &bpf_skb_change_head_proto;
+		return &sk_skb_change_head_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
@@ -4966,12 +5057,14 @@ static const struct bpf_func_proto *
 lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	case BPF_FUNC_lwt_seg6_store_bytes:
 		return &bpf_lwt_seg6_store_bytes_proto;
 	case BPF_FUNC_lwt_seg6_action:
 		return &bpf_lwt_seg6_action_proto;
 	case BPF_FUNC_lwt_seg6_adjust_srh:
 		return &bpf_lwt_seg6_adjust_srh_proto;
+#endif
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index b2b2323bdc84..188d693cb251 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 		d->lock = lock;
 		spin_lock_bh(lock);
 	}
-	if (d->tail)
-		return gnet_stats_copy(d, type, NULL, 0, padattr);
+	if (d->tail) {
+		int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+		/* The initial attribute added in gnet_stats_copy() may be
+		 * preceded by a padding attribute, in which case d->tail will
+		 * end up pointing at the padding instead of the real attribute.
+		 * Fix this so gnet_stats_finish_copy() adjusts the length of
+		 * the right attribute.
+		 */
+		if (ret == 0 && d->tail->nla_type == padattr)
+			d->tail = (struct nlattr *)((char *)d->tail +
+						    NLA_ALIGN(d->tail->nla_len));
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index eba8dae22c25..8e51f8555e11 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
+	C(pfmemalloc);
 	n->destructor = NULL;
 	C(tail);
 	C(end);