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

Pull networking fixes from David Miller:
 "Lots of bug fixes here:

   1) Out of bounds access in __bpf_skc_lookup, from Lorenz Bauer.

   2) Fix rate reporting in cfg80211_calculate_bitrate_he(), from John
      Crispin.

   3) Use after free in psock backlog workqueue, from John Fastabend.

   4) Fix source port matching in fdb peer flow rule of mlx5, from Raed
      Salem.

   5) Use atomic_inc_not_zero() in fl6_sock_lookup(), from Eric Dumazet.

   6) Network header needs to be set for packet redirect in nfp, from
      John Hurley.

   7) Fix udp zerocopy refcnt, from Willem de Bruijn.

   8) Don't assume linear buffers in vxlan and geneve error handlers,
      from Stefano Brivio.

   9) Fix TOS matching in mlxsw, from Jiri Pirko.

  10) More SCTP cookie memory leak fixes, from Neil Horman.

  11) Fix VLAN filtering in rtl8366, from Linus Walluij.

  12) Various TCP SACK payload size and fragmentation memory limit fixes
      from Eric Dumazet.

  13) Use after free in pneigh_get_next(), also from Eric Dumazet.

  14) LAPB control block leak fix from Jeremy Sowden"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (145 commits)
  lapb: fixed leak of control-blocks.
  tipc: purge deferredq list for each grp member in tipc_group_delete
  ax25: fix inconsistent lock state in ax25_destroy_timer
  neigh: fix use-after-free read in pneigh_get_next
  tcp: fix compile error if !CONFIG_SYSCTL
  hv_sock: Suppress bogus "may be used uninitialized" warnings
  be2net: Fix number of Rx queues used for flow hashing
  net: handle 802.1P vlan 0 packets properly
  tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
  tcp: add tcp_min_snd_mss sysctl
  tcp: tcp_fragment() should apply sane memory limits
  tcp: limit payload size of sacked skbs
  Revert "net: phylink: set the autoneg state in phylink_phy_change"
  bpf: fix nested bpf tracepoints with per-cpu data
  bpf: Fix out of bounds memory access in bpf_sk_storage
  vsock/virtio: set SOCK_DONE on peer shutdown
  net: dsa: rtl8366: Fix up VLAN filtering
  net: phylink: set the autoneg state in phylink_phy_change
  net: add high_order_alloc_disable sysctl/static key
  tcp: add tcp_tx_skb_cache sysctl
  ...

7 files changed, 137 insertions, 46 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7c473f208a10..080e2bb644cc 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2097,7 +2097,6 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
 
 DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 EXPORT_SYMBOL(bpf_stats_enabled_key);
-int sysctl_bpf_stats_enabled __read_mostly;
 
 /* All definitions of tracepoints related to BPF. */
 #define CREATE_TRACE_POINTS
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 15dbc15c5b0c..cd8297b3bdb9 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -178,6 +178,7 @@ static void dev_map_free(struct bpf_map *map)
 		if (!dev)
 			continue;
 
+		free_percpu(dev->bulkq);
 		dev_put(dev->dev);
 		kfree(dev);
 	}
@@ -273,6 +274,7 @@ void __dev_map_flush(struct bpf_map *map)
 	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
 	u32 bit;
 
+	rcu_read_lock();
 	for_each_set_bit(bit, bitmap, map->max_entries) {
 		struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]);
 		struct xdp_bulk_queue *bq;
@@ -283,11 +285,12 @@ void __dev_map_flush(struct bpf_map *map)
 		if (unlikely(!dev))
 			continue;
 
-		__clear_bit(bit, bitmap);
-
 		bq = this_cpu_ptr(dev->bulkq);
 		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
+
+		__clear_bit(bit, bitmap);
 	}
+	rcu_read_unlock();
 }
 
 /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
@@ -380,6 +383,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 
 		int cpu;
 
+		rcu_read_lock();
 		for_each_online_cpu(cpu) {
 			bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu);
 			__clear_bit(dev->bit, bitmap);
@@ -387,6 +391,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 			bq = per_cpu_ptr(dev->bulkq, cpu);
 			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
 		}
+		rcu_read_unlock();
 	}
 }
 
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index e61630c2e50b..864e2a496376 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -716,9 +716,14 @@ find_leftmost:
 	 * have exact two children, so this function will never return NULL.
 	 */
 	for (node = search_root; node;) {
-		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
+		if (node->flags & LPM_TREE_NODE_FLAG_IM) {
+			node = rcu_dereference(node->child[0]);
+		} else {
 			next_node = node;
-		node = rcu_dereference(node->child[0]);
+			node = rcu_dereference(node->child[0]);
+			if (!node)
+				node = rcu_dereference(next_node->child[1]);
+		}
 	}
 do_copy:
 	next_key->prefixlen = next_node->prefixlen;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ef63d26622f2..42d17f730780 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1573,6 +1573,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 		case BPF_CGROUP_INET6_CONNECT:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
 			return 0;
 		default:
 			return -EINVAL;
@@ -1867,6 +1869,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_INET6_CONNECT:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UDP4_RECVMSG:
+	case BPF_CGROUP_UDP6_RECVMSG:
 		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 		break;
 	case BPF_CGROUP_SOCK_OPS:
@@ -1952,6 +1956,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_INET6_CONNECT:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UDP4_RECVMSG:
+	case BPF_CGROUP_UDP6_RECVMSG:
 		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 		break;
 	case BPF_CGROUP_SOCK_OPS:
@@ -2003,6 +2009,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET6_CONNECT:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UDP4_RECVMSG:
+	case BPF_CGROUP_UDP6_RECVMSG:
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 	case BPF_CGROUP_SYSCTL:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d15cc4fafa89..a5c369e60343 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5353,9 +5353,12 @@ static int check_return_code(struct bpf_verifier_env *env)
 	struct tnum range = tnum_range(0, 1);
 
 	switch (env->prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
+		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+			range = tnum_range(1, 1);
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
-	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
@@ -5372,16 +5375,17 @@ static int check_return_code(struct bpf_verifier_env *env)
 	}
 
 	if (!tnum_in(range, reg->var_off)) {
+		char tn_buf[48];
+
 		verbose(env, "At program exit the register R0 ");
 		if (!tnum_is_unknown(reg->var_off)) {
-			char tn_buf[48];
-
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
 			verbose(env, "has value %s", tn_buf);
 		} else {
 			verbose(env, "has unknown scalar value");
 		}
-		verbose(env, " should have been 0 or 1\n");
+		tnum_strn(tn_buf, sizeof(tn_buf), range);
+		verbose(env, " should have been in %s\n", tn_buf);
 		return -EINVAL;
 	}
 	return 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7d1008be6173..1beca96fb625 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -230,11 +230,6 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
 #endif
 static int proc_dopipe_max_size(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp, loff_t *ppos);
-#ifdef CONFIG_BPF_SYSCALL
-static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
-					  void __user *buffer, size_t *lenp,
-					  loff_t *ppos);
-#endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
 /* Note: sysrq code uses its own private copy */
@@ -1253,12 +1248,10 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.procname	= "bpf_stats_enabled",
-		.data		= &sysctl_bpf_stats_enabled,
-		.maxlen		= sizeof(sysctl_bpf_stats_enabled),
+		.data		= &bpf_stats_enabled_key.key,
+		.maxlen		= sizeof(bpf_stats_enabled_key),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax_bpf_stats,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.proc_handler	= proc_do_static_key,
 	},
 #endif
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
@@ -3374,26 +3367,35 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 
 #endif /* CONFIG_PROC_SYSCTL */
 
-#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
-static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
-					  void __user *buffer, size_t *lenp,
-					  loff_t *ppos)
+#if defined(CONFIG_SYSCTL)
+int proc_do_static_key(struct ctl_table *table, int write,
+		       void __user *buffer, size_t *lenp,
+		       loff_t *ppos)
 {
-	int ret, bpf_stats = *(int *)table->data;
-	struct ctl_table tmp = *table;
+	struct static_key *key = (struct static_key *)table->data;
+	static DEFINE_MUTEX(static_key_mutex);
+	int val, ret;
+	struct ctl_table tmp = {
+		.data   = &val,
+		.maxlen = sizeof(val),
+		.mode   = table->mode,
+		.extra1 = &zero,
+		.extra2 = &one,
+	};
 
 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	tmp.data = &bpf_stats;
+	mutex_lock(&static_key_mutex);
+	val = static_key_enabled(key);
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 	if (write && !ret) {
-		*(int *)table->data = bpf_stats;
-		if (bpf_stats)
-			static_branch_enable(&bpf_stats_enabled_key);
+		if (val)
+			static_key_enable(key);
 		else
-			static_branch_disable(&bpf_stats_enabled_key);
+			static_key_disable(key);
 	}
+	mutex_unlock(&static_key_mutex);
 	return ret;
 }
 #endif
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f92d6ad5e080..1c9a4745e596 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -410,8 +410,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
-
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 			u64 flags, struct perf_sample_data *sd)
@@ -442,24 +440,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	return perf_event_output(event, sd, regs);
 }
 
+/*
+ * Support executing tracepoints in normal, irq, and nmi context that each call
+ * bpf_perf_event_output
+ */
+struct bpf_trace_sample_data {
+	struct perf_sample_data sds[3];
+};
+
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds);
+static DEFINE_PER_CPU(int, bpf_trace_nest_level);
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
+	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
+	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
 			.data = data,
 		},
 	};
+	struct perf_sample_data *sd;
+	int err;
 
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	sd = &sds->sds[nest_level - 1];
+
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, sd);
+
+out:
+	this_cpu_dec(bpf_trace_nest_level);
+	return err;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -822,16 +846,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 /*
  * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
  * to avoid potential recursive reuse issue when/if tracepoints are added
- * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack
+ * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack.
+ *
+ * Since raw tracepoints run despite bpf_prog_active, support concurrent usage
+ * in normal, irq, and nmi context.
  */
-static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+struct bpf_raw_tp_regs {
+	struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs);
+static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level);
+static struct pt_regs *get_bpf_raw_tp_regs(void)
+{
+	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
+
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+		this_cpu_dec(bpf_raw_tp_nest_level);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return &tp_regs->regs[nest_level - 1];
+}
+
+static void put_bpf_raw_tp_regs(void)
+{
+	this_cpu_dec(bpf_raw_tp_nest_level);
+}
+
 BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return ____bpf_perf_event_output(regs, map, flags, data, size);
+	ret = ____bpf_perf_event_output(regs, map, flags, data, size);
+
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
@@ -848,12 +904,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
 	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
-	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
-			       flags, 0, 0);
+	ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+			      flags, 0, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
@@ -868,11 +930,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
 BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   void *, buf, u32, size, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
-			     (unsigned long) size, flags, 0);
+	ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+			    (unsigned long) size, flags, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {