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

Pull networking fixes from David Miller:

 1) Verify netlink attributes properly in nf_queue, from Eric Dumazet.

 2) Need to bump memory lock rlimit for test_sockmap bpf test, from
    Yonghong Song.

 3) Fix VLAN handling in lan78xx driver, from Dave Stevenson.

 4) Fix uninitialized read in nf_log, from Jann Horn.

 5) Fix raw command length parsing in mlx5, from Alex Vesker.

 6) Cleanup loopback RDS connections upon netns deletion, from Sowmini
    Varadhan.

 7) Fix regressions in FIB rule matching during create, from Jason A.
    Donenfeld and Roopa Prabhu.

 8) Fix mpls ether type detection in nfp, from Pieter Jansen van Vuuren.

 9) More bpfilter build fixes/adjustments from Masahiro Yamada.

10) Fix XDP_{TX,REDIRECT} flushing in various drivers, from Jesper
    Dangaard Brouer.

11) fib_tests.sh file permissions were broken, from Shuah Khan.

12) Make sure BH/preemption is disabled in data path of mac80211, from
    Denis Kenzior.

13) Don't ignore nla_parse_nested() return values in nl80211, from
    Johannes berg.

14) Properly account sock objects ot kmemcg, from Shakeel Butt.

15) Adjustments to setting bpf program permissions to read-only, from
    Daniel Borkmann.

16) TCP Fast Open key endianness was broken, it always took on the host
    endiannness. Whoops. Explicitly make it little endian. From Yuching
    Cheng.

17) Fix prefix route setting for link local addresses in ipv6, from
    David Ahern.

18) Potential Spectre v1 in zatm driver, from Gustavo A. R. Silva.

19) Various bpf sockmap fixes, from John Fastabend.

20) Use after free for GRO with ESP, from Sabrina Dubroca.

21) Passing bogus flags to crypto_alloc_shash() in ipv6 SR code, from
    Eric Biggers.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  qede: Adverstise software timestamp caps when PHC is not available.
  qed: Fix use of incorrect size in memcpy call.
  qed: Fix setting of incorrect eswitch mode.
  qed: Limit msix vectors in kdump kernel to the minimum required count.
  ipvlan: call dev_change_flags when ipvlan mode is reset
  ipv6: sr: fix passing wrong flags to crypto_alloc_shash()
  net: fix use-after-free in GRO with ESP
  tcp: prevent bogus FRTO undos with non-SACK flows
  bpf: sockhash, add release routine
  bpf: sockhash fix omitted bucket lock in sock_close
  bpf: sockmap, fix smap_list_map_remove when psock is in many maps
  bpf: sockmap, fix crash when ipv6 sock is added
  net: fib_rules: bring back rule_exists to match rule during add
  hv_netvsc: split sub-channel setup into async and sync
  net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN
  atm: zatm: Fix potential Spectre v1
  s390/qeth: consistently re-enable device features
  s390/qeth: don't clobber buffer on async TX completion
  s390/qeth: avoid using is_multicast_ether_addr_64bits on (u8 *)[6]
  s390/qeth: fix race when setting MAC address
  ...

11 files changed, 97 insertions, 57 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 975fb4cf1bb7..79795c5fa7c3 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -188,12 +188,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 									      \
 	__ret;								      \
 })
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr);
 #else
 
+struct bpf_prog;
 struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype,
+					 struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+					union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7df32a3200f7..8827e797ff97 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+			struct bpf_prog *prog);
 #else
 static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+				      struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
 #endif
 
 #if defined(CONFIG_XDP_SOCKETS)
diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h
index 5f8a4283092d..9d9ff755ec29 100644
--- a/include/linux/bpf_lirc.h
+++ b/include/linux/bpf_lirc.h
@@ -5,11 +5,12 @@
 #include <uapi/linux/bpf.h>
 
 #ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int lirc_prog_detach(const union bpf_attr *attr);
 int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
 #else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+				   struct bpf_prog *prog)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 20f2659dd829..300baad62c88 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -470,9 +470,7 @@ struct sock_fprog_kern {
 };
 
 struct bpf_binary_header {
-	u16 pages;
-	u16 locked:1;
-
+	u32 pages;
 	/* Some arches need word alignment for their instructions */
 	u8 image[] __aligned(4);
 };
@@ -481,7 +479,7 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				locked:1,	/* Program image locked? */
+				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -677,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	fp->locked = 1;
-	if (set_memory_ro((unsigned long)fp, fp->pages))
-		fp->locked = 0;
-#endif
+	fp->undo_set_mem = 1;
+	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (fp->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		fp->locked = 0;
-	}
-#endif
+	if (fp->undo_set_mem)
+		set_memory_rw((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	hdr->locked = 1;
-	if (set_memory_ro((unsigned long)hdr, hdr->pages))
-		hdr->locked = 0;
-#endif
+	set_memory_ro((unsigned long)hdr, hdr->pages);
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (hdr->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		hdr->locked = 0;
-	}
-#endif
+	set_memory_rw((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -728,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp)
 	return (void *)addr;
 }
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
-{
-	if (!fp->locked)
-		return -ENOLCK;
-	if (fp->jited) {
-		const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
-
-		if (!hdr->locked)
-			return -ENOLCK;
-	}
-
-	return 0;
-}
-#endif
-
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index d3c9db492b30..fab5121ffb8f 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -8,6 +8,8 @@
 
 #include <linux/mlx5/driver.h>
 
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
 enum {
 	SRIOV_NONE,
 	SRIOV_LEGACY,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 27134c4fcb76..ac281f5ec9b8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vnic_env_queue_counters[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         eswitch_flow_table[0x1];
+	u8         eswitch_manager[0x1];
 	u8         device_memory[0x1];
 	u8         mcam_reg[0x1];
 	u8         pcam_reg[0x1];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec9850c7936..3d0cc0b5cec2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp,
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
 #else
 static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
 #endif
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 47e35cce3b64..a71264d75d7f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -128,6 +128,7 @@ struct net {
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	struct netns_nf_frag	nf_frag;
+	struct ctl_table_header *nf_frag_frags_hdr;
 #endif
 	struct sock		*nfnl;
 	struct sock		*nfnl_stash;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index c978a31b0f84..762ac9931b62 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -109,7 +109,6 @@ struct netns_ipv6 {
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 struct netns_nf_frag {
-	struct netns_sysctl_ipv6 sysctl;
 	struct netns_frags	frags;
 };
 #endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3c1a2c47cd4..20b059574e60 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 }
 
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 59b19b6a40d7..b7db3261c62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		*     packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,7 +2639,11 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */