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

Pull networking updates from David Miller:
 "Highlights:

   1) Fix the iwlwifi regression, from Johannes Berg.

   2) Support BSS coloring and 802.11 encapsulation offloading in
      hardware, from John Crispin.

   3) Fix some potential Spectre issues in qtnfmac, from Sergey
      Matyukevich.

   4) Add TTL decrement action to openvswitch, from Matteo Croce.

   5) Allow paralleization through flow_action setup by not taking the
      RTNL mutex, from Vlad Buslov.

   6) A lot of zero-length array to flexible-array conversions, from
      Gustavo A. R. Silva.

   7) Align XDP statistics names across several drivers for consistency,
      from Lorenzo Bianconi.

   8) Add various pieces of infrastructure for offloading conntrack, and
      make use of it in mlx5 driver, from Paul Blakey.

   9) Allow using listening sockets in BPF sockmap, from Jakub Sitnicki.

  10) Lots of parallelization improvements during configuration changes
      in mlxsw driver, from Ido Schimmel.

  11) Add support to devlink for generic packet traps, which report
      packets dropped during ACL processing. And use them in mlxsw
      driver. From Jiri Pirko.

  12) Support bcmgenet on ACPI, from Jeremy Linton.

  13) Make BPF compatible with RT, from Thomas Gleixnet, Alexei
      Starovoitov, and your's truly.

  14) Support XDP meta-data in virtio_net, from Yuya Kusakabe.

  15) Fix sysfs permissions when network devices change namespaces, from
      Christian Brauner.

  16) Add a flags element to ethtool_ops so that drivers can more simply
      indicate which coalescing parameters they actually support, and
      therefore the generic layer can validate the user's ethtool
      request. Use this in all drivers, from Jakub Kicinski.

  17) Offload FIFO qdisc in mlxsw, from Petr Machata.

  18) Support UDP sockets in sockmap, from Lorenz Bauer.

  19) Fix stretch ACK bugs in several TCP congestion control modules,
      from Pengcheng Yang.

  20) Support virtual functiosn in octeontx2 driver, from Tomasz
      Duszynski.

  21) Add region operations for devlink and use it in ice driver to dump
      NVM contents, from Jacob Keller.

  22) Add support for hw offload of MACSEC, from Antoine Tenart.

  23) Add support for BPF programs that can be attached to LSM hooks,
      from KP Singh.

  24) Support for multiple paths, path managers, and counters in MPTCP.
      From Peter Krystad, Paolo Abeni, Florian Westphal, Davide Caratti,
      and others.

  25) More progress on adding the netlink interface to ethtool, from
      Michal Kubecek"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2121 commits)
  net: ipv6: rpl_iptunnel: Fix potential memory leak in rpl_do_srh_inline
  cxgb4/chcr: nic-tls stats in ethtool
  net: dsa: fix oops while probing Marvell DSA switches
  net/bpfilter: remove superfluous testing message
  net: macb: Fix handling of fixed-link node
  net: dsa: ksz: Select KSZ protocol tag
  netdevsim: dev: Fix memory leak in nsim_dev_take_snapshot_write
  net: stmmac: add EHL 2.5Gbps PCI info and PCI ID
  net: stmmac: add EHL PSE0 & PSE1 1Gbps PCI info and PCI ID
  net: stmmac: create dwmac-intel.c to contain all Intel platform
  net: dsa: bcm_sf2: Support specifying VLAN tag egress rule
  net: dsa: bcm_sf2: Add support for matching VLAN TCI
  net: dsa: bcm_sf2: Move writing of CFP_DATA(5) into slicing functions
  net: dsa: bcm_sf2: Check earlier for FLOW_EXT and FLOW_MAC_EXT
  net: dsa: bcm_sf2: Disable learning for ASP port
  net: dsa: b53: Deny enslaving port 7 for 7278 into a bridge
  net: dsa: b53: Prevent tagged VLAN on port 7 for 7278
  net: dsa: b53: Restore VLAN entries upon (re)configuration
  net: dsa: bcm_sf2: Fix overflow checks
  hv_netvsc: Remove unnecessary round_up for recv_completion_cnt
  ...

1 files changed, 130 insertions, 33 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 212991f6f2a5..fd2b2322412d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -18,6 +18,7 @@
 #include <linux/refcount.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kallsyms.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -233,6 +234,7 @@ enum bpf_arg_type {
 	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */
 
 	ARG_PTR_TO_CTX,		/* pointer to context */
+	ARG_PTR_TO_CTX_OR_NULL,	/* pointer to context or NULL */
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
@@ -434,6 +436,16 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
 
+/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
+ * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
+ */
+#define BPF_MAX_TRAMP_PROGS 40
+
+struct bpf_tramp_progs {
+	struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS];
+	int nr_progs;
+};
+
 /* Different use cases for BPF trampoline:
  * 1. replace nop at the function entry (kprobe equivalent)
  *    flags = BPF_TRAMP_F_RESTORE_REGS
@@ -456,16 +468,25 @@ struct btf_func_model {
  */
 int arch_prepare_bpf_trampoline(void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
-				struct bpf_prog **fentry_progs, int fentry_cnt,
-				struct bpf_prog **fexit_progs, int fexit_cnt,
+				struct bpf_tramp_progs *tprogs,
 				void *orig_call);
 /* these two functions are called from generated trampoline */
 u64 notrace __bpf_prog_enter(void);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
 
+struct bpf_ksym {
+	unsigned long		 start;
+	unsigned long		 end;
+	char			 name[KSYM_NAME_LEN];
+	struct list_head	 lnode;
+	struct latch_tree_node	 tnode;
+	bool			 prog;
+};
+
 enum bpf_tramp_prog_type {
 	BPF_TRAMP_FENTRY,
 	BPF_TRAMP_FEXIT,
+	BPF_TRAMP_MODIFY_RETURN,
 	BPF_TRAMP_MAX,
 	BPF_TRAMP_REPLACE, /* more than MAX */
 };
@@ -494,6 +515,7 @@ struct bpf_trampoline {
 	/* Executable image of trampoline */
 	void *image;
 	u64 selector;
+	struct bpf_ksym ksym;
 };
 
 #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
@@ -511,9 +533,10 @@ struct bpf_dispatcher {
 	int num_progs;
 	void *image;
 	u32 image_off;
+	struct bpf_ksym ksym;
 };
 
-static __always_inline unsigned int bpf_dispatcher_nopfunc(
+static __always_inline unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	unsigned int (*bpf_func)(const void *,
@@ -526,17 +549,21 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
 int bpf_trampoline_link_prog(struct bpf_prog *prog);
 int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
-#define BPF_DISPATCHER_INIT(name) {			\
-	.mutex = __MUTEX_INITIALIZER(name.mutex),	\
-	.func = &name##func,				\
-	.progs = {},					\
-	.num_progs = 0,					\
-	.image = NULL,					\
-	.image_off = 0					\
+#define BPF_DISPATCHER_INIT(_name) {				\
+	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
+	.func = &_name##_func,					\
+	.progs = {},						\
+	.num_progs = 0,						\
+	.image = NULL,						\
+	.image_off = 0,						\
+	.ksym = {						\
+		.name  = #_name,				\
+		.lnode = LIST_HEAD_INIT(_name.ksym.lnode),	\
+	},							\
 }
 
 #define DEFINE_BPF_DISPATCHER(name)					\
-	noinline unsigned int name##func(				\
+	noinline unsigned int bpf_dispatcher_##name##_func(		\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		unsigned int (*bpf_func)(const void *,			\
@@ -544,26 +571,26 @@ void bpf_trampoline_put(struct bpf_trampoline *tr);
 	{								\
 		return bpf_func(ctx, insnsi);				\
 	}								\
-	EXPORT_SYMBOL(name##func);			\
-	struct bpf_dispatcher name = BPF_DISPATCHER_INIT(name);
+	EXPORT_SYMBOL(bpf_dispatcher_##name##_func);			\
+	struct bpf_dispatcher bpf_dispatcher_##name =			\
+		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
 #define DECLARE_BPF_DISPATCHER(name)					\
-	unsigned int name##func(					\
+	unsigned int bpf_dispatcher_##name##_func(			\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		unsigned int (*bpf_func)(const void *,			\
 					 const struct bpf_insn *));	\
-	extern struct bpf_dispatcher name;
-#define BPF_DISPATCHER_FUNC(name) name##func
-#define BPF_DISPATCHER_PTR(name) (&name)
+	extern struct bpf_dispatcher bpf_dispatcher_##name;
+#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
+#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 				struct bpf_prog *to);
-struct bpf_image {
-	struct latch_tree_node tnode;
-	unsigned char data[];
-};
-#define BPF_IMAGE_SIZE (PAGE_SIZE - sizeof(struct bpf_image))
-bool is_bpf_image_address(unsigned long address);
-void *bpf_image_alloc(void);
+/* Called only from JIT-enabled code, so there's no need for stubs. */
+void *bpf_jit_alloc_exec_page(void);
+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);
 #else
 static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
@@ -580,7 +607,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #define DEFINE_BPF_DISPATCHER(name)
 #define DECLARE_BPF_DISPATCHER(name)
-#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nopfunc
+#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func
 #define BPF_DISPATCHER_PTR(name) NULL
 static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
 					      struct bpf_prog *from,
@@ -641,8 +668,7 @@ struct bpf_prog_aux {
 	void *jit_data; /* JIT specific data. arch dependent */
 	struct bpf_jit_poke_descriptor *poke_tab;
 	u32 size_poke_tab;
-	struct latch_tree_node ksym_tnode;
-	struct list_head ksym_lnode;
+	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;
@@ -860,7 +886,7 @@ struct bpf_prog_array_item {
 
 struct bpf_prog_array {
 	struct rcu_head rcu;
-	struct bpf_prog_array_item items[0];
+	struct bpf_prog_array_item items[];
 };
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
@@ -886,7 +912,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		struct bpf_prog *_prog;			\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
-		preempt_disable();			\
+		migrate_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
@@ -899,7 +925,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
-		preempt_enable();			\
+		migrate_enable();			\
 		_ret;					\
 	 })
 
@@ -933,7 +959,7 @@ _out:							\
 		u32 ret;				\
 		u32 _ret = 1;				\
 		u32 _cn = 0;				\
-		preempt_disable();			\
+		migrate_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		_item = &_array->items[0];		\
@@ -945,7 +971,7 @@ _out:							\
 			_item++;			\
 		}					\
 		rcu_read_unlock();			\
-		preempt_enable();			\
+		migrate_enable();			\
 		if (_ret)				\
 			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
 		else					\
@@ -962,6 +988,36 @@ _out:							\
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
+/*
+ * Block execution of BPF programs attached to instrumentation (perf,
+ * kprobes, tracepoints) to prevent deadlocks on map operations as any of
+ * these events can happen inside a region which holds a map bucket lock
+ * and can deadlock on it.
+ *
+ * Use the preemption safe inc/dec variants on RT because migrate disable
+ * is preemptible on RT and preemption in the middle of the RMW operation
+ * might lead to inconsistent state. Use the raw variants for non RT
+ * kernels as migrate_disable() maps to preempt_disable() so the slightly
+ * more expensive save operation can be avoided.
+ */
+static inline void bpf_disable_instrumentation(void)
+{
+	migrate_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_inc(bpf_prog_active);
+	else
+		__this_cpu_inc(bpf_prog_active);
+}
+
+static inline void bpf_enable_instrumentation(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		this_cpu_dec(bpf_prog_active);
+	else
+		__this_cpu_dec(bpf_prog_active);
+	migrate_enable();
+}
+
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 
@@ -994,6 +1050,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 
+struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
 void bpf_map_inc(struct bpf_map *map);
@@ -1026,6 +1083,29 @@ extern int sysctl_unprivileged_bpf_disabled;
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
+struct bpf_link {
+	atomic64_t refcnt;
+	const struct bpf_link_ops *ops;
+	struct bpf_prog *prog;
+	struct work_struct work;
+};
+
+struct bpf_link_ops {
+	void (*release)(struct bpf_link *link);
+	void (*dealloc)(struct bpf_link *link);
+
+};
+
+void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops,
+		   struct bpf_prog *prog);
+void bpf_link_cleanup(struct bpf_link *link, struct file *link_file,
+		      int link_fd);
+void bpf_link_inc(struct bpf_link *link);
+void bpf_link_put(struct bpf_link *link);
+int bpf_link_new_fd(struct bpf_link *link);
+struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
+struct bpf_link *bpf_link_get_from_fd(u32 ufd);
+
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
 int bpf_obj_get_user(const char __user *pathname, int flags);
 
@@ -1103,6 +1183,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_tracing(struct bpf_prog *prog,
+			      const union bpf_attr *kattr,
+			      union bpf_attr __user *uattr);
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
@@ -1260,6 +1343,13 @@ static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
 	return -ENOTSUPP;
 }
 
+static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog,
+					    const union bpf_attr *kattr,
+					    union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
 static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 						   const union bpf_attr *kattr,
 						   union bpf_attr __user *uattr)
@@ -1356,6 +1446,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 #if defined(CONFIG_BPF_STREAM_PARSER)
 int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
+void sock_map_unhash(struct sock *sk);
+void sock_map_close(struct sock *sk, long timeout);
 #else
 static inline int sock_map_prog_update(struct bpf_map *map,
 				       struct bpf_prog *prog, u32 which)
@@ -1368,7 +1460,7 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
-#endif
+#endif /* CONFIG_BPF_STREAM_PARSER */
 
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
 void bpf_sk_reuseport_detach(struct sock *sk);
@@ -1418,6 +1510,7 @@ extern const struct bpf_func_proto bpf_get_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
+extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
 extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
@@ -1429,6 +1522,10 @@ extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
 extern const struct bpf_func_proto bpf_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_jiffies64_proto;
+extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto;
+
+const struct bpf_func_proto *bpf_tracing_func_proto(
+	enum bpf_func_id func_id, const struct bpf_prog *prog);
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);