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

Pull networking fixes from David Miller:
 "Various fixes, all over:

   1) Fix overflow in ptp_qoriq_adjfine(), from Yangbo Lu.

   2) Always store the rx queue mapping in veth, from Maciej
      Fijalkowski.

   3) Don't allow vmlinux btf in map_create, from Alexei Starovoitov.

   4) Fix memory leak in octeontx2-af from Colin Ian King.

   5) Use kvalloc in bpf x86 JIT for storing jit'd addresses, from
      Yonghong Song.

   6) Fix tx ptp stats in mlx5, from Aya Levin.

   7) Check correct ip version in tun decap, fropm Roi Dayan.

   8) Fix rate calculation in mlx5 E-Switch code, from arav Pandit.

   9) Work item memork leak in mlx5, from Shay Drory.

  10) Fix ip6ip6 tunnel crash with bpf, from Daniel Borkmann.

  11) Lack of preemptrion awareness in macvlan, from Eric Dumazet.

  12) Fix data race in pxa168_eth, from Pavel Andrianov.

  13) Range validate stab in red_check_params(), from Eric Dumazet.

  14) Inherit vlan filtering setting properly in b53 driver, from
      Florian Fainelli.

  15) Fix rtnl locking in igc driver, from Sasha Neftin.

  16) Pause handling fixes in igc driver, from Muhammad Husaini
      Zulkifli.

  17) Missing rtnl locking in e1000_reset_task, from Vitaly Lifshits.

  18) Use after free in qlcnic, from Lv Yunlong.

  19) fix crash in fritzpci mISDN, from Tong Zhang.

  20) Premature rx buffer reuse in igb, from Li RongQing.

  21) Missing termination of ip[a driver message handler arrays, from
      Alex Elder.

  22) Fix race between "x25_close" and "x25_xmit"/"x25_rx" in hdlc_x25
      driver, from Xie He.

  23) Use after free in c_can_pci_remove(), from Tong Zhang.

  24) Uninitialized variable use in nl80211, from Jarod Wilson.

  25) Off by one size calc in bpf verifier, from Piotr Krysiuk.

  26) Use delayed work instead of deferrable for flowtable GC, from
      Yinjun Zhang.

  27) Fix infinite loop in NPC unmap of octeontx2 driver, from
      Hariprasad Kelam.

  28) Fix being unable to change MTU of dwmac-sun8i devices due to lack
      of fifo sizes, from Corentin Labbe.

  29) DMA use after free in r8169 with WoL, fom Heiner Kallweit.

  30) Mismatched prototypes in isdn-capi, from Arnd Bergmann.

  31) Fix psample UAPI breakage, from Ido Schimmel"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (171 commits)
  psample: Fix user API breakage
  math: Export mul_u64_u64_div_u64
  ch_ktls: fix enum-conversion warning
  octeontx2-af: Fix memory leak of object buf
  ptp_qoriq: fix overflow in ptp_qoriq_adjfine() u64 calcalation
  net: bridge: don't notify switchdev for local FDB addresses
  net/sched: act_ct: clear post_ct if doing ct_clear
  net: dsa: don't assign an error value to tag_ops
  isdn: capi: fix mismatched prototypes
  net/mlx5: SF, do not use ecpu bit for vhca state processing
  net/mlx5e: Fix division by 0 in mlx5e_select_queue
  net/mlx5e: Fix error path for ethtool set-priv-flag
  net/mlx5e: Offload tuple rewrite for non-CT flows
  net/mlx5e: Allow to match on MPLS parameters only for MPLS over UDP
  net/mlx5: Add back multicast stats for uplink representor
  net: ipconfig: ic_dev can be NULL in ic_close_devs
  MAINTAINERS: Combine "QLOGIC QLGE 10Gb ETHERNET DRIVER" sections into one
  docs: networking: Fix a typo
  r8169: fix DMA being used after buffer free if WoL is enabled
  net: ipa: fix init header command validation
  ...

7 files changed, 40 insertions, 14 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cccaef1088ea..3625f019767d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -21,6 +21,7 @@
 #include <linux/capability.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
+#include <linux/percpu-refcount.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -556,7 +557,8 @@ struct bpf_tramp_progs {
  *      fentry = a set of program to run before calling original function
  *      fexit = a set of program to run after original function
  */
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+struct bpf_tramp_image;
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_progs *tprogs,
 				void *orig_call);
@@ -565,6 +567,8 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
 u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
 void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
 struct bpf_ksym {
 	unsigned long		 start;
@@ -583,6 +587,18 @@ enum bpf_tramp_prog_type {
 	BPF_TRAMP_REPLACE, /* more than MAX */
 };
 
+struct bpf_tramp_image {
+	void *image;
+	struct bpf_ksym ksym;
+	struct percpu_ref pcref;
+	void *ip_after_call;
+	void *ip_epilogue;
+	union {
+		struct rcu_head rcu;
+		struct work_struct work;
+	};
+};
+
 struct bpf_trampoline {
 	/* hlist for trampoline_table */
 	struct hlist_node hlist;
@@ -605,9 +621,8 @@ struct bpf_trampoline {
 	/* Number of attached programs. A counter per kind. */
 	int progs_cnt[BPF_TRAMP_MAX];
 	/* Executable image of trampoline */
-	void *image;
+	struct bpf_tramp_image *cur_image;
 	u64 selector;
-	struct bpf_ksym ksym;
 };
 
 struct bpf_attach_target_info {
@@ -691,6 +706,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
+int bpf_jit_charge_modmem(u32 pages);
+void bpf_jit_uncharge_modmem(u32 pages);
 #else
 static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
 					   struct bpf_trampoline *tr)
@@ -787,7 +804,6 @@ struct bpf_prog_aux {
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
-	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
@@ -1093,7 +1109,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		_ret;							\
 	 })
 
-#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage)	\
 	({						\
 		struct bpf_prog_array_item *_item;	\
 		struct bpf_prog *_prog;			\
@@ -1106,7 +1122,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			goto _out;			\
 		_item = &_array->items[0];		\
 		while ((_prog = READ_ONCE(_item->prog))) {		\
-			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			if (set_cg_storage)		\
+				bpf_cgroup_storage_set(_item->cgroup_storage);	\
 			_ret &= func(_prog, ctx);	\
 			_item++;			\
 		}					\
@@ -1153,10 +1170,10 @@ _out:							\
 	})
 
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, false, true)
 
 #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, true, false)
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 96556c64c95d..10c94a3936ca 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -43,13 +43,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 	if (likely(success)) {
 		struct vlan_pcpu_stats *pcpu_stats;
 
-		pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
+		pcpu_stats = get_cpu_ptr(vlan->pcpu_stats);
 		u64_stats_update_begin(&pcpu_stats->syncp);
 		pcpu_stats->rx_packets++;
 		pcpu_stats->rx_bytes += len;
 		if (multicast)
 			pcpu_stats->rx_multicast++;
 		u64_stats_update_end(&pcpu_stats->syncp);
+		put_cpu_ptr(vlan->pcpu_stats);
 	} else {
 		this_cpu_inc(vlan->pcpu_stats->rx_errors);
 	}
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index d75ef8aa8fac..b7deb790f257 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -547,4 +547,11 @@ static inline const char *mlx5_qp_state_str(int state)
 	}
 }
 
+static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
+{
+	return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
+		       MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING :
+		       MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
+}
+
 #endif /* MLX5_QP_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5b67ea89d5f2..87a5d186faff 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -360,6 +360,7 @@ enum {
 	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
+	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
 };
 
 enum {
@@ -372,6 +373,7 @@ enum {
 	NAPIF_STATE_IN_BUSY_POLL	= BIT(NAPI_STATE_IN_BUSY_POLL),
 	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
+	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
 };
 
 enum gro_result {
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 8ebb64193757..8ec48466410a 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -227,7 +227,7 @@ struct xt_table {
 	unsigned int valid_hooks;
 
 	/* Man behind the curtain... */
-	struct xt_table_info __rcu *private;
+	struct xt_table_info *private;
 
 	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
 	struct module *me;
@@ -376,7 +376,7 @@ static inline unsigned int xt_write_recseq_begin(void)
 	 * since addend is most likely 1
 	 */
 	__this_cpu_add(xt_recseq.sequence, addend);
-	smp_wmb();
+	smp_mb();
 
 	return addend;
 }
@@ -448,9 +448,6 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 
 struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
-struct xt_table_info
-*xt_table_get_private_protected(const struct xt_table *table);
-
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6d0a33d1c0db..f2c9ee71cb2c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -285,6 +285,7 @@ struct nf_bridge_info {
 struct tc_skb_ext {
 	__u32 chain;
 	__u16 mru;
+	bool post_ct;
 };
 #endif
 
diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
index 073a9e0ec07d..ad970416260d 100644
--- a/include/linux/usermode_driver.h
+++ b/include/linux/usermode_driver.h
@@ -14,5 +14,6 @@ struct umd_info {
 int umd_load_blob(struct umd_info *info, const void *data, size_t len);
 int umd_unload_blob(struct umd_info *info);
 int fork_usermode_driver(struct umd_info *info);
+void umd_cleanup_helper(struct umd_info *info);
 
 #endif /* __LINUX_USERMODE_DRIVER_H__ */