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

Pull networking fixes from David Miller:

 1) Fix verifier memory corruption and other bugs in BPF layer, from
    Alexei Starovoitov.

 2) Add a conservative fix for doing BPF properly in the BPF classifier
    of the packet scheduler on ingress.  Also from Alexei.

 3) The SKB scrubber should not clear out the packet MARK and security
    label, from Herbert Xu.

 4) Fix oops on rmmod in stmmac driver, from Bryan O'Donoghue.

 5) Pause handling is not correct in the stmmac driver because it
    doesn't take into consideration the RX and TX fifo sizes.  From
    Vince Bridgers.

 6) Failure path missing unlock in FOU driver, from Wang Cong.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits)
  net: dsa: use DEVICE_ATTR_RW to declare temp1_max
  netns: remove BUG_ONs from net_generic()
  IB/ipoib: Fix ndo_get_iflink
  sfc: Fix memcpy() with const destination compiler warning.
  altera tse: Fix network-delays and -retransmissions after high throughput.
  net: remove unused 'dev' argument from netif_needs_gso()
  act_mirred: Fix bogus header when redirecting from VLAN
  inet_diag: fix access to tcp cc information
  tcp: tcp_get_info() should fetch socket fields once
  net: dsa: mv88e6xxx: Add missing initialization in mv88e6xxx_set_port_state()
  skbuff: Do not scrub skb mark within the same name space
  Revert "net: Reset secmark when scrubbing packet"
  bpf: fix two bugs in verification logic when accessing 'ctx' pointer
  bpf: fix bpf helpers to use skb->mac_header relative offsets
  stmmac: Configure Flow Control to work correctly based on rxfifo size
  stmmac: Enable unicast pause frame detect in GMAC Register 6
  stmmac: Read tx-fifo-depth and rx-fifo-depth from the devicetree
  stmmac: Add defines and documentation for enabling flow control
  stmmac: Add properties for transmit and receive fifo sizes
  stmmac: fix oops on rmmod after assigning ip addr
  ...

net/core/dev.c

@@ -2713,7 +2713,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (unlikely(!skb))
 		goto out_null;
 
-	if (netif_needs_gso(dev, skb, features)) {
+	if (netif_needs_gso(skb, features)) {
 		struct sk_buff *segs;
 
 		segs = skb_gso_segment(skb, features);

net/core/filter.c

@@ -1175,12 +1175,27 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 	return 0;
 }
 
+/**
+ *	bpf_skb_clone_not_writable - is the header of a clone not writable
+ *	@skb: buffer to check
+ *	@len: length up to which to write, can be negative
+ *
+ *	Returns true if modifying the header part of the cloned buffer
+ *	does require the data to be copied. I.e. this version works with
+ *	negative lengths needed for eBPF case!
+ */
+static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len)
+{
+	return skb_header_cloned(skb) ||
+	       (int) skb_headroom(skb) + len > skb->hdr_len;
+}
+
 #define BPF_RECOMPUTE_CSUM(flags)	((flags) & 1)
 
 static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
-	unsigned int offset = (unsigned int) r2;
+	int offset = (int) r2;
 	void *from = (void *) (long) r3;
 	unsigned int len = (unsigned int) r4;
 	char buf[16];
@@ -1194,10 +1209,12 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 	 *
 	 * so check for invalid 'offset' and too large 'len'
 	 */
-	if (unlikely(offset > 0xffff || len > sizeof(buf)))
+	if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
 		return -EFAULT;
 
-	if (skb_cloned(skb) && !skb_clone_writable(skb, offset + len))
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + len)))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, len, buf);
@@ -1232,15 +1249,18 @@ const struct bpf_func_proto bpf_skb_store_bytes_proto = {
 #define BPF_HEADER_FIELD_SIZE(flags)	((flags) & 0x0f)
 #define BPF_IS_PSEUDO_HEADER(flags)	((flags) & 0x10)
 
-static u64 bpf_l3_csum_replace(u64 r1, u64 offset, u64 from, u64 to, u64 flags)
+static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	int offset = (int) r2;
 	__sum16 sum, *ptr;
 
-	if (unlikely(offset > 0xffff))
+	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
 
-	if (skb_cloned(skb) && !skb_clone_writable(skb, offset + sizeof(sum)))
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1276,16 +1296,19 @@ const struct bpf_func_proto bpf_l3_csum_replace_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_l4_csum_replace(u64 r1, u64 offset, u64 from, u64 to, u64 flags)
+static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags);
+	int offset = (int) r2;
 	__sum16 sum, *ptr;
 
-	if (unlikely(offset > 0xffff))
+	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
 
-	if (skb_cloned(skb) && !skb_clone_writable(skb, offset + sizeof(sum)))
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);

net/core/net_namespace.c

@@ -16,7 +16,6 @@
 #include <linux/export.h>
 #include <linux/user_namespace.h>
 #include <linux/net_namespace.h>
-#include <linux/rtnetlink.h>
 #include <net/sock.h>
 #include <net/netlink.h>
 #include <net/net_namespace.h>

net/core/skbuff.c

@@ -4124,19 +4124,21 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	if (xnet)
-		skb_orphan(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
-	skb->mark = 0;
 	skb_sender_cpu_clear(skb);
-	skb_init_secmark(skb);
 	secpath_reset(skb);
 	nf_reset(skb);
 	nf_reset_trace(skb);
+
+	if (!xnet)
+		return;
+
+	skb_orphan(skb);
+	skb->mark = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 

net/dsa/dsa.c

@@ -124,7 +124,7 @@ static ssize_t temp1_max_store(struct device *dev,
 
 	return count;
 }
-static DEVICE_ATTR(temp1_max, S_IRUGO, temp1_max_show, temp1_max_store);
+static DEVICE_ATTR_RW(temp1_max);
 
 static ssize_t temp1_max_alarm_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
@@ -159,8 +159,8 @@ static umode_t dsa_hwmon_attrs_visible(struct kobject *kobj,
 	if (index == 1) {
 		if (!drv->get_temp_limit)
 			mode = 0;
-		else if (drv->set_temp_limit)
-			mode |= S_IWUSR;
+		else if (!drv->set_temp_limit)
+			mode &= ~S_IWUSR;
 	} else if (index == 2 && !drv->get_temp_alarm) {
 		mode = 0;
 	}

net/ipv4/fou.c

@@ -711,11 +711,10 @@ static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				    cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				    skb, FOU_CMD_GET);
 		if (ret)
-			goto done;
+			break;
 	}
 	mutex_unlock(&fn->fou_lock);
 
-done:
 	cb->args[0] = idx;
 	return skb->len;
 }

net/ipv4/inet_diag.c

@@ -111,6 +111,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		      const struct nlmsghdr *unlh)
 {
 	const struct inet_sock *inet = inet_sk(sk);
+	const struct tcp_congestion_ops *ca_ops;
 	const struct inet_diag_handler *handler;
 	int ext = req->idiag_ext;
 	struct inet_diag_msg *r;
@@ -208,16 +209,31 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		info = nla_data(attr);
 	}
 
-	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops)
-		if (nla_put_string(skb, INET_DIAG_CONG,
-				   icsk->icsk_ca_ops->name) < 0)
+	if (ext & (1 << (INET_DIAG_CONG - 1))) {
+		int err = 0;
+
+		rcu_read_lock();
+		ca_ops = READ_ONCE(icsk->icsk_ca_ops);
+		if (ca_ops)
+			err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
+		rcu_read_unlock();
+		if (err < 0)
 			goto errout;
+	}
 
 	handler->idiag_get_info(sk, r, info);
 
-	if (sk->sk_state < TCP_TIME_WAIT &&
-	    icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
-		icsk->icsk_ca_ops->get_info(sk, ext, skb);
+	if (sk->sk_state < TCP_TIME_WAIT) {
+		int err = 0;
+
+		rcu_read_lock();
+		ca_ops = READ_ONCE(icsk->icsk_ca_ops);
+		if (ca_ops && ca_ops->get_info)
+			err = ca_ops->get_info(sk, ext, skb);
+		rcu_read_unlock();
+		if (err < 0)
+			goto errout;
+	}
 
 out:
 	nlmsg_end(skb, nlh);

net/ipv4/tcp.c

@@ -2595,6 +2595,7 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
+	u32 rate;
 
 	memset(info, 0, sizeof(*info));
 
@@ -2655,10 +2656,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_total_retrans = tp->total_retrans;
 
-	info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
-					sk->sk_pacing_rate : ~0ULL;
-	info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
-					sk->sk_max_pacing_rate : ~0ULL;
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+	rate = READ_ONCE(sk->sk_max_pacing_rate);
+	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 

net/ipv4/tcp_dctcp.c

@@ -277,7 +277,7 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	}
 }
 
-static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 {
 	const struct dctcp *ca = inet_csk_ca(sk);
 
@@ -297,8 +297,9 @@ static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 			info.dctcp_ab_tot = ca->acked_bytes_total;
 		}
 
-		nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
+		return nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops dctcp __read_mostly = {

net/ipv4/tcp_illinois.c

@@ -300,8 +300,7 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-static void tcp_illinois_info(struct sock *sk, u32 ext,
-			      struct sk_buff *skb)
+static int tcp_illinois_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 {
 	const struct illinois *ca = inet_csk_ca(sk);
 
@@ -318,8 +317,9 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
 			do_div(t, info.tcpv_rttcnt);
 			info.tcpv_rtt = t;
 		}
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops tcp_illinois __read_mostly = {

net/ipv4/tcp_vegas.c

@@ -286,7 +286,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 {
 	const struct vegas *ca = inet_csk_ca(sk);
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
@@ -297,8 +297,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 			.tcpv_minrtt = ca->minRTT,
 		};
 
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
 	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
 

net/ipv4/tcp_vegas.h

@@ -19,6 +19,6 @@ void tcp_vegas_init(struct sock *sk);
 void tcp_vegas_state(struct sock *sk, u8 ca_state);
 void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
 void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
-void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
+int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
 
 #endif	/* __TCP_VEGAS_H */

net/ipv4/tcp_westwood.c

@@ -256,8 +256,7 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-static void tcp_westwood_info(struct sock *sk, u32 ext,
-			      struct sk_buff *skb)
+static int tcp_westwood_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 {
 	const struct westwood *ca = inet_csk_ca(sk);
 
@@ -268,8 +267,9 @@ static void tcp_westwood_info(struct sock *sk, u32 ext,
 			.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
 		};
 
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops tcp_westwood __read_mostly = {

net/sched/act_bpf.c

@@ -38,6 +38,9 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
 	struct tcf_bpf *prog = act->priv;
 	int action, filter_res;
 
+	if (unlikely(!skb_mac_header_was_set(skb)))
+		return TC_ACT_UNSPEC;
+
 	spin_lock(&prog->tcf_lock);
 
 	prog->tcf_tm.lastuse = jiffies;

net/sched/act_mirred.c

@@ -157,7 +157,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb2->dev->hard_header_len);
+			skb_push(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */

net/sched/cls_bpf.c

@@ -66,6 +66,9 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_bpf_prog *prog;
 	int ret = -1;
 
+	if (unlikely(!skb_mac_header_was_set(skb)))
+		return -1;
+
 	/* Needed here for accessing maps. */
 	rcu_read_lock();
 	list_for_each_entry_rcu(prog, &head->plist, link) {