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

Pull networking fixes from David Miller:

 1) Buffers powersave frame test is reversed in cfg80211, fix from Felix
    Fietkau.

 2) Remove bogus WARN_ON in openvswitch, from Jarno Rajahalme.

 3) Fix some tg3 ethtool logic bugs, and one that would cause no
    interrupts to be generated when rx-coalescing is set to 0.  From
    Satish Baddipadige and Siva Reddy Kallam.

 4) QLCNIC mailbox corruption and napi budget handling fix from Manish
    Chopra.

 5) Fix fib_trie logic when walking the trie during /proc/net/route
    output than can access a stale node pointer.  From David Forster.

 6) Several sctp_diag fixes from Phil Sutter.

 7) PAUSE frame handling fixes in mlxsw driver from Ido Schimmel.

 8) Checksum fixup fixes in bpf from Daniel Borkmann.

 9) Memork leaks in nfnetlink, from Liping Zhang.

10) Use after free in rxrpc, from David Howells.

11) Use after free in new skb_array code of macvtap driver, from Jason
    Wang.

12) Calipso resource leak, from Colin Ian King.

13) mediatek bug fixes (missing stats sync init, etc.) from Sean Wang.

14) Fix bpf non-linear packet write helpers, from Daniel Borkmann.

15) Fix lockdep splats in macsec, from Sabrina Dubroca.

16) hv_netvsc bug fixes from Vitaly Kuznetsov, mostly to do with VF
    handling.

17) Various tc-action bug fixes, from CONG Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  net_sched: allow flushing tc police actions
  net_sched: unify the init logic for act_police
  net_sched: convert tcf_exts from list to pointer array
  net_sched: move tc offload macros to pkt_cls.h
  net_sched: fix a typo in tc_for_each_action()
  net_sched: remove an unnecessary list_del()
  net_sched: remove the leftover cleanup_a()
  mlxsw: spectrum: Allow packets to be trapped from any PG
  mlxsw: spectrum: Unmap 802.1Q FID before destroying it
  mlxsw: spectrum: Add missing rollbacks in error path
  mlxsw: reg: Fix missing op field fill-up
  mlxsw: spectrum: Trap loop-backed packets
  mlxsw: spectrum: Add missing packet traps
  mlxsw: spectrum: Mark port as active before registering it
  mlxsw: spectrum: Create PVID vPort before registering netdevice
  mlxsw: spectrum: Remove redundant errors from the code
  mlxsw: spectrum: Don't return upon error in removal path
  i40e: check for and deal with non-contiguous TCs
  ixgbe: Re-enable ability to toggle VLAN filtering
  ixgbe: Force VLNCTRL.VFE to be set in all VMDq paths
  ...

2 files changed, 50 insertions, 69 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 4ce07dc25573..dd6ce598de89 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6045,8 +6045,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
 
-int dev_get_nest_level(struct net_device *dev,
-		       bool (*type_check)(const struct net_device *dev))
+int dev_get_nest_level(struct net_device *dev)
 {
 	struct net_device *lower = NULL;
 	struct list_head *iter;
@@ -6056,15 +6055,12 @@ int dev_get_nest_level(struct net_device *dev,
 	ASSERT_RTNL();
 
 	netdev_for_each_lower_dev(dev, lower, iter) {
-		nest = dev_get_nest_level(lower, type_check);
+		nest = dev_get_nest_level(lower);
 		if (max_nest < nest)
 			max_nest = nest;
 	}
 
-	if (type_check(dev))
-		max_nest++;
-
-	return max_nest;
+	return max_nest + 1;
 }
 EXPORT_SYMBOL(dev_get_nest_level);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 5708999f8a79..cb06aceb512a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1355,56 +1355,47 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
 {
 	int err;
 
-	if (!skb_cloned(skb))
-		return 0;
-	if (skb_clone_writable(skb, write_len))
-		return 0;
-	err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
-	if (!err)
-		bpf_compute_data_end(skb);
+	err = skb_ensure_writable(skb, write_len);
+	bpf_compute_data_end(skb);
+
 	return err;
 }
 
+static inline void bpf_push_mac_rcsum(struct sk_buff *skb)
+{
+	if (skb_at_tc_ingress(skb))
+		skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
+static inline void bpf_pull_mac_rcsum(struct sk_buff *skb)
+{
+	if (skb_at_tc_ingress(skb))
+		skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
 static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 {
-	struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
-	int offset = (int) r2;
+	unsigned int offset = (unsigned int) r2;
 	void *from = (void *) (long) r3;
 	unsigned int len = (unsigned int) r4;
 	void *ptr;
 
 	if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
 		return -EINVAL;
-
-	/* bpf verifier guarantees that:
-	 * 'from' pointer points to bpf program stack
-	 * 'len' bytes of it were initialized
-	 * 'len' > 0
-	 * 'skb' is a valid pointer to 'struct sk_buff'
-	 *
-	 * so check for invalid 'offset' and too large 'len'
-	 */
-	if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff)))
+	if (unlikely(offset > 0xffff))
 		return -EFAULT;
 	if (unlikely(bpf_try_make_writable(skb, offset + len)))
 		return -EFAULT;
 
-	ptr = skb_header_pointer(skb, offset, len, sp->buff);
-	if (unlikely(!ptr))
-		return -EFAULT;
-
+	ptr = skb->data + offset;
 	if (flags & BPF_F_RECOMPUTE_CSUM)
-		skb_postpull_rcsum(skb, ptr, len);
+		__skb_postpull_rcsum(skb, ptr, len, offset);
 
 	memcpy(ptr, from, len);
 
-	if (ptr == sp->buff)
-		/* skb_store_bits cannot return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, len);
-
 	if (flags & BPF_F_RECOMPUTE_CSUM)
-		skb_postpush_rcsum(skb, ptr, len);
+		__skb_postpush_rcsum(skb, ptr, len, offset);
 	if (flags & BPF_F_INVALIDATE_HASH)
 		skb_clear_hash(skb);
 
@@ -1425,12 +1416,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
 static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
 	const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1;
-	int offset = (int) r2;
+	unsigned int offset = (unsigned int) r2;
 	void *to = (void *)(unsigned long) r3;
 	unsigned int len = (unsigned int) r4;
 	void *ptr;
 
-	if (unlikely((u32) offset > 0xffff))
+	if (unlikely(offset > 0xffff))
 		goto err_clear;
 
 	ptr = skb_header_pointer(skb, offset, len, to);
@@ -1458,20 +1449,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 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;
+	unsigned int offset = (unsigned int) r2;
+	__sum16 *ptr;
 
 	if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
 		return -EINVAL;
-	if (unlikely((u32) offset > 0xffff))
+	if (unlikely(offset > 0xffff || offset & 1))
 		return -EFAULT;
-	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
-		return -EFAULT;
-
-	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
-	if (unlikely(!ptr))
+	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
 		return -EFAULT;
 
+	ptr = (__sum16 *)(skb->data + offset);
 	switch (flags & BPF_F_HDR_FIELD_MASK) {
 	case 0:
 		if (unlikely(from != 0))
@@ -1489,10 +1477,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 		return -EINVAL;
 	}
 
-	if (ptr == &sum)
-		/* skb_store_bits guaranteed to not return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, sizeof(sum));
-
 	return 0;
 }
 
@@ -1512,20 +1496,18 @@ 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;
 	bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
 	bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
-	int offset = (int) r2;
-	__sum16 sum, *ptr;
+	unsigned int offset = (unsigned int) r2;
+	__sum16 *ptr;
 
 	if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
 			       BPF_F_HDR_FIELD_MASK)))
 		return -EINVAL;
-	if (unlikely((u32) offset > 0xffff))
+	if (unlikely(offset > 0xffff || offset & 1))
 		return -EFAULT;
-	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
+	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
 		return -EFAULT;
 
-	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
-	if (unlikely(!ptr))
-		return -EFAULT;
+	ptr = (__sum16 *)(skb->data + offset);
 	if (is_mmzero && !*ptr)
 		return 0;
 
@@ -1548,10 +1530,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 
 	if (is_mmzero && !*ptr)
 		*ptr = CSUM_MANGLED_0;
-	if (ptr == &sum)
-		/* skb_store_bits guaranteed to not return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, sizeof(sum));
-
 	return 0;
 }
 
@@ -1607,9 +1585,6 @@ static const struct bpf_func_proto bpf_csum_diff_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	if (skb_at_tc_ingress(skb))
-		skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
-
 	return dev_forward_skb(dev, skb);
 }
 
@@ -1648,6 +1623,8 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 	if (unlikely(!skb))
 		return -ENOMEM;
 
+	bpf_push_mac_rcsum(skb);
+
 	return flags & BPF_F_INGRESS ?
 	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
@@ -1693,6 +1670,8 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
+	bpf_push_mac_rcsum(skb);
+
 	return ri->flags & BPF_F_INGRESS ?
 	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
@@ -1756,7 +1735,10 @@ static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
 		     vlan_proto != htons(ETH_P_8021AD)))
 		vlan_proto = htons(ETH_P_8021Q);
 
+	bpf_push_mac_rcsum(skb);
 	ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
+	bpf_pull_mac_rcsum(skb);
+
 	bpf_compute_data_end(skb);
 	return ret;
 }
@@ -1776,7 +1758,10 @@ static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	int ret;
 
+	bpf_push_mac_rcsum(skb);
 	ret = skb_vlan_pop(skb);
+	bpf_pull_mac_rcsum(skb);
+
 	bpf_compute_data_end(skb);
 	return ret;
 }
@@ -2298,7 +2283,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
 }
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
-static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
 	struct sk_buff *skb = (struct sk_buff *)(long)r1;
 	struct bpf_map *map = (struct bpf_map *)(long)r2;
@@ -2321,8 +2306,8 @@ static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp);
 }
 
-static const struct bpf_func_proto bpf_skb_in_cgroup_proto = {
-	.func		= bpf_skb_in_cgroup,
+static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
+	.func		= bpf_skb_under_cgroup,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
@@ -2402,8 +2387,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
 #ifdef CONFIG_SOCK_CGROUP_DATA
-	case BPF_FUNC_skb_in_cgroup:
-		return &bpf_skb_in_cgroup_proto;
+	case BPF_FUNC_skb_under_cgroup:
+		return &bpf_skb_under_cgroup_proto;
 #endif
 	default:
 		return sk_filter_func_proto(func_id);