Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-01-24

We've added 80 non-merge commits during the last 14 day(s) which contain
a total of 128 files changed, 4990 insertions(+), 895 deletions(-).

The main changes are:

1) Add XDP multi-buffer support and implement it for the mvneta driver,
   from Lorenzo Bianconi, Eelco Chaudron and Toke Høiland-Jørgensen.

2) Add unstable conntrack lookup helpers for BPF by using the BPF kfunc
   infra, from Kumar Kartikeya Dwivedi.

3) Extend BPF cgroup programs to export custom ret value to userspace via
   two helpers bpf_get_retval() and bpf_set_retval(), from YiFei Zhu.

4) Add support for AF_UNIX iterator batching, from Kuniyuki Iwashima.

5) Complete missing UAPI BPF helper description and change bpf_doc.py script
   to enforce consistent & complete helper documentation, from Usama Arif.

6) Deprecate libbpf's legacy BPF map definitions and streamline XDP APIs to
   follow tc-based APIs, from Andrii Nakryiko.

7) Support BPF_PROG_QUERY for BPF programs attached to sockmap, from Di Zhu.

8) Deprecate libbpf's bpf_map__def() API and replace users with proper getters
   and setters, from Christy Lee.

9) Extend libbpf's btf__add_btf() with an additional hashmap for strings to
   reduce overhead, from Kui-Feng Lee.

10) Fix bpftool and libbpf error handling related to libbpf's hashmap__new()
    utility function, from Mauricio Vásquez.

11) Add support to BTF program names in bpftool's program dump, from Raman Shukhau.

12) Fix resolve_btfids build to pick up host flags, from Connor O'Brien.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (80 commits)
  selftests, bpf: Do not yet switch to new libbpf XDP APIs
  selftests, xsk: Fix rx_full stats test
  bpf: Fix flexible_array.cocci warnings
  xdp: disable XDP_REDIRECT for xdp frags
  bpf: selftests: add CPUMAP/DEVMAP selftests for xdp frags
  bpf: selftests: introduce bpf_xdp_{load,store}_bytes selftest
  net: xdp: introduce bpf_xdp_pointer utility routine
  bpf: generalise tail call map compatibility check
  libbpf: Add SEC name for xdp frags programs
  bpf: selftests: update xdp_adjust_tail selftest to include xdp frags
  bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature
  bpf: introduce frags support to bpf_prog_test_run_xdp()
  bpf: move user_size out of bpf_test_init
  bpf: add frags support to xdp copy helpers
  bpf: add frags support to the bpf_xdp_adjust_tail() API
  bpf: introduce bpf_xdp_get_buff_len helper
  net: mvneta: enable jumbo frames if the loaded XDP program support frags
  bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program
  net: mvneta: add frags support to XDP_TX
  xdp: add frags support to xdp_return_{buff/frame}
  ...
====================

Link: https://lore.kernel.org/r/20220124221235.18993-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 293 insertions, 84 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fa517ae604ad..8c92c974bd12 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -194,6 +194,17 @@ struct bpf_map {
 	struct work_struct work;
 	struct mutex freeze_mutex;
 	atomic64_t writecnt;
+	/* 'Ownership' of program-containing map is claimed by the first program
+	 * that is going to use this map or by the first program which FD is
+	 * stored in the map to make sure that all callers and callees have the
+	 * same prog type, JITed flag and xdp_has_frags flag.
+	 */
+	struct {
+		spinlock_t lock;
+		enum bpf_prog_type type;
+		bool jited;
+		bool xdp_has_frags;
+	} owner;
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -578,7 +589,6 @@ struct bpf_verifier_ops {
 				 const struct btf_type *t, int off, int size,
 				 enum bpf_access_type atype,
 				 u32 *next_btf_id);
-	bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner);
 };
 
 struct bpf_prog_offload_ops {
@@ -939,6 +949,7 @@ struct bpf_prog_aux {
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
+	bool xdp_has_frags;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
@@ -999,16 +1010,6 @@ struct bpf_prog_aux {
 };
 
 struct bpf_array_aux {
-	/* 'Ownership' of prog array is claimed by the first program that
-	 * is going to use this map or by the first program which FD is
-	 * stored in the map to make sure that all callers and callees have
-	 * the same prog type and JITed flag.
-	 */
-	struct {
-		spinlock_t lock;
-		enum bpf_prog_type type;
-		bool jited;
-	} owner;
 	/* Programs with direct jumps into programs part of this array. */
 	struct list_head poke_progs;
 	struct bpf_map *map;
@@ -1183,7 +1184,14 @@ struct bpf_event_entry {
 	struct rcu_head rcu;
 };
 
-bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
+static inline bool map_type_contains_progs(struct bpf_map *map)
+{
+	return map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+	       map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	       map->map_type == BPF_MAP_TYPE_CPUMAP;
+}
+
+bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
@@ -1251,6 +1259,7 @@ struct bpf_run_ctx {};
 struct bpf_cg_run_ctx {
 	struct bpf_run_ctx run_ctx;
 	const struct bpf_prog_array_item *prog_item;
+	int retval;
 };
 
 struct bpf_trace_run_ctx {
@@ -1283,19 +1292,19 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
 
 typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
 
-static __always_inline u32
+static __always_inline int
 BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
 			    const void *ctx, bpf_prog_run_fn run_prog,
-			    u32 *ret_flags)
+			    int retval, u32 *ret_flags)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
 	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_cg_run_ctx run_ctx;
-	u32 ret = 1;
 	u32 func_ret;
 
+	run_ctx.retval = retval;
 	migrate_disable();
 	rcu_read_lock();
 	array = rcu_dereference(array_rcu);
@@ -1304,27 +1313,29 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
 	while ((prog = READ_ONCE(item->prog))) {
 		run_ctx.prog_item = item;
 		func_ret = run_prog(prog, ctx);
-		ret &= (func_ret & 1);
+		if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
+			run_ctx.retval = -EPERM;
 		*(ret_flags) |= (func_ret >> 1);
 		item++;
 	}
 	bpf_reset_run_ctx(old_run_ctx);
 	rcu_read_unlock();
 	migrate_enable();
-	return ret;
+	return run_ctx.retval;
 }
 
-static __always_inline u32
+static __always_inline int
 BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
-		      const void *ctx, bpf_prog_run_fn run_prog)
+		      const void *ctx, bpf_prog_run_fn run_prog,
+		      int retval)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
 	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_cg_run_ctx run_ctx;
-	u32 ret = 1;
 
+	run_ctx.retval = retval;
 	migrate_disable();
 	rcu_read_lock();
 	array = rcu_dereference(array_rcu);
@@ -1332,13 +1343,14 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	while ((prog = READ_ONCE(item->prog))) {
 		run_ctx.prog_item = item;
-		ret &= run_prog(prog, ctx);
+		if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
+			run_ctx.retval = -EPERM;
 		item++;
 	}
 	bpf_reset_run_ctx(old_run_ctx);
 	rcu_read_unlock();
 	migrate_enable();
-	return ret;
+	return run_ctx.retval;
 }
 
 static __always_inline u32
@@ -1391,19 +1403,21 @@ out:
  *   0: NET_XMIT_SUCCESS  skb should be transmitted
  *   1: NET_XMIT_DROP     skb should be dropped and cn
  *   2: NET_XMIT_CN       skb should be transmitted and cn
- *   3: -EPERM            skb should be dropped
+ *   3: -err              skb should be dropped
  */
 #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func)		\
 	({						\
 		u32 _flags = 0;				\
 		bool _cn;				\
 		u32 _ret;				\
-		_ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \
+		_ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \
 		_cn = _flags & BPF_RET_SET_CN;		\
-		if (_ret)				\
+		if (_ret && !IS_ERR_VALUE((long)_ret))	\
+			_ret = -EFAULT;			\
+		if (!_ret)				\
 			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
 		else					\
-			_ret = (_cn ? NET_XMIT_DROP : -EPERM);		\
+			_ret = (_cn ? NET_XMIT_DROP : _ret);		\
 		_ret;					\
 	})
 
@@ -1724,7 +1738,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
 int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
 				const union bpf_attr *kattr,
 				union bpf_attr __user *uattr);
-bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner);
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
@@ -1976,12 +1989,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
 	return -ENOTSUPP;
 }
 
-static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id,
-						  struct module *owner)
-{
-	return false;
-}
-
 static inline void bpf_map_put(struct bpf_map *map)
 {
 }
@@ -2076,6 +2083,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog,
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
 int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
+int sock_map_bpf_prog_query(const union bpf_attr *attr,
+			    union bpf_attr __user *uattr);
+
 void sock_map_unhash(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
@@ -2129,6 +2139,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
+					  union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e9993172f892..7a7be8c057f2 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 
 int check_ptr_off_reg(struct bpf_verifier_env *env,
 		      const struct bpf_reg_state *reg, int regno);
+int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+			     u32 regno);
 int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 		   u32 regno, u32 mem_size);
 
@@ -564,4 +566,9 @@ static inline u32 type_flag(u32 type)
 	return type & ~BPF_BASE_TYPE_MASK;
 }
 
+static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
+{
+	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
+}
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 0c74348cbc9d..b12cfe3b12bb 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -12,11 +12,33 @@
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val)
 
+enum btf_kfunc_type {
+	BTF_KFUNC_TYPE_CHECK,
+	BTF_KFUNC_TYPE_ACQUIRE,
+	BTF_KFUNC_TYPE_RELEASE,
+	BTF_KFUNC_TYPE_RET_NULL,
+	BTF_KFUNC_TYPE_MAX,
+};
+
 struct btf;
 struct btf_member;
 struct btf_type;
 union bpf_attr;
 struct btf_show;
+struct btf_id_set;
+
+struct btf_kfunc_id_set {
+	struct module *owner;
+	union {
+		struct {
+			struct btf_id_set *check_set;
+			struct btf_id_set *acquire_set;
+			struct btf_id_set *release_set;
+			struct btf_id_set *ret_null_set;
+		};
+		struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
+	};
+};
 
 extern const struct file_operations btf_fops;
 
@@ -307,6 +329,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
+bool btf_kfunc_id_set_contains(const struct btf *btf,
+			       enum bpf_prog_type prog_type,
+			       enum btf_kfunc_type type, u32 kfunc_btf_id);
+int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+			      const struct btf_kfunc_id_set *s);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
@@ -318,50 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf,
 {
 	return NULL;
 }
-#endif
-
-struct kfunc_btf_id_set {
-	struct list_head list;
-	struct btf_id_set *set;
-	struct module *owner;
-};
-
-struct kfunc_btf_id_list {
-	struct list_head list;
-	struct mutex mutex;
-};
-
-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
-void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-			       struct kfunc_btf_id_set *s);
-void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-				 struct kfunc_btf_id_set *s);
-bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
-			      struct module *owner);
-
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-#else
-static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-					     struct kfunc_btf_id_set *s)
-{
-}
-static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-					       struct kfunc_btf_id_set *s)
+static inline bool btf_kfunc_id_set_contains(const struct btf *btf,
+					     enum bpf_prog_type prog_type,
+					     enum btf_kfunc_type type,
+					     u32 kfunc_btf_id)
 {
+	return false;
 }
-static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist,
-					    u32 kfunc_id, struct module *owner)
+static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+					    const struct btf_kfunc_id_set *s)
 {
-	return false;
+	return 0;
 }
-
-static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
-static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
 #endif
 
-#define DEFINE_KFUNC_BTF_ID_SET(set, name)                                     \
-	struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set),     \
-					 THIS_MODULE }
-
 #endif
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 919c0fde1c51..bc5d9cc34e4c 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -11,6 +11,7 @@ struct btf_id_set {
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */
+#include <linux/compiler_attributes.h> /* for __maybe_unused */
 
 /*
  * Following macros help to define lists of BTF IDs placed
@@ -146,14 +147,14 @@ extern struct btf_id_set name;
 
 #else
 
-#define BTF_ID_LIST(name) static u32 name[5];
+#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
-#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n];
-#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
-#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1];
-#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
-#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
+#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1];
+#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
 #define BTF_SET_END(name)
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 71fa57b88bfc..d23e999dc032 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1356,7 +1356,10 @@ struct bpf_sockopt_kern {
 	s32		level;
 	s32		optname;
 	s32		optlen;
-	s32		retval;
+	/* for retval in struct bpf_cg_run_ctx */
+	struct task_struct *current_task;
+	/* Temporary "register" for indirect stores to ppos. */
+	u64		tmp_reg;
 };
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bf11e1fbd69b..8131d0de7559 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -557,6 +557,7 @@ struct skb_shared_info {
 	 * Warning : all fields before dataref are cleared in __alloc_skb()
 	 */
 	atomic_t	dataref;
+	unsigned int	xdp_frags_size;
 
 	/* Intermediate layers must ensure that destructor_arg
 	 * remains valid until skb destructor */
diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h
new file mode 100644
index 000000000000..a473b56842c5
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_bpf.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _NF_CONNTRACK_BPF_H
+#define _NF_CONNTRACK_BPF_H
+
+#include <linux/btf.h>
+#include <linux/kconfig.h>
+
+#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+    (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES))
+
+extern int register_nf_conntrack_bpf(void);
+
+#else
+
+static inline int register_nf_conntrack_bpf(void)
+{
+	return 0;
+}
+
+#endif
+
+#endif /* _NF_CONNTRACK_BPF_H */
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8f0812e4996d..b7721c3e4d1f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -60,12 +60,20 @@ struct xdp_rxq_info {
 	u32 reg_state;
 	struct xdp_mem_info mem;
 	unsigned int napi_id;
+	u32 frag_size;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
 struct xdp_txq_info {
 	struct net_device *dev;
 };
 
+enum xdp_buff_flags {
+	XDP_FLAGS_HAS_FRAGS		= BIT(0), /* non-linear xdp buff */
+	XDP_FLAGS_FRAGS_PF_MEMALLOC	= BIT(1), /* xdp paged memory is under
+						   * pressure
+						   */
+};
+
 struct xdp_buff {
 	void *data;
 	void *data_end;
@@ -74,13 +82,40 @@ struct xdp_buff {
 	struct xdp_rxq_info *rxq;
 	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
+	u32 flags; /* supported values defined in xdp_buff_flags */
 };
 
+static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS);
+}
+
+static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp)
+{
+	xdp->flags |= XDP_FLAGS_HAS_FRAGS;
+}
+
+static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp)
+{
+	xdp->flags &= ~XDP_FLAGS_HAS_FRAGS;
+}
+
+static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
+static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC;
+}
+
 static __always_inline void
 xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
 {
 	xdp->frame_sz = frame_sz;
 	xdp->rxq = rxq;
+	xdp->flags = 0;
 }
 
 static __always_inline void
@@ -111,6 +146,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
 	return (struct skb_shared_info *)xdp_data_hard_end(xdp);
 }
 
+static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp)
+{
+	unsigned int len = xdp->data_end - xdp->data;
+	struct skb_shared_info *sinfo;
+
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	len += sinfo->xdp_frags_size;
+out:
+	return len;
+}
+
 struct xdp_frame {
 	void *data;
 	u16 len;
@@ -122,8 +171,19 @@ struct xdp_frame {
 	 */
 	struct xdp_mem_info mem;
 	struct net_device *dev_rx; /* used by cpumap */
+	u32 flags; /* supported values defined in xdp_buff_flags */
 };
 
+static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame)
+{
+	return !!(frame->flags & XDP_FLAGS_HAS_FRAGS);
+}
+
+static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame)
+{
+	return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
 #define XDP_BULK_QUEUE_SIZE	16
 struct xdp_frame_bulk {
 	int count;
@@ -159,6 +219,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+static inline void
+xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
+			   unsigned int size, unsigned int truesize,
+			   bool pfmemalloc)
+{
+	skb_shinfo(skb)->nr_frags = nr_frags;
+
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += truesize;
+	skb->pfmemalloc |= pfmemalloc;
+}
+
 /* Avoids inlining WARN macro in fast-path */
 void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
@@ -180,6 +253,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 	xdp->data_end = frame->data + frame->len;
 	xdp->data_meta = frame->data - frame->metasize;
 	xdp->frame_sz = frame->frame_sz;
+	xdp->flags = frame->flags;
 }
 
 static inline
@@ -206,6 +280,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp,
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
 	xdp_frame->frame_sz = xdp->frame_sz;
+	xdp_frame->flags = xdp->flags;
 
 	return 0;
 }
@@ -230,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
 	return xdp_frame;
 }
 
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+		  struct xdp_buff *xdp);
 void xdp_return_frame(struct xdp_frame *xdpf);
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
 void xdp_return_buff(struct xdp_buff *xdp);
@@ -246,14 +323,37 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem);
 static inline void xdp_release_frame(struct xdp_frame *xdpf)
 {
 	struct xdp_mem_info *mem = &xdpf->mem;
+	struct skb_shared_info *sinfo;
+	int i;
 
 	/* Curr only page_pool needs this */
-	if (mem->type == MEM_TYPE_PAGE_POOL)
-		__xdp_release_frame(xdpf->data, mem);
+	if (mem->type != MEM_TYPE_PAGE_POOL)
+		return;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_release_frame(page_address(page), mem);
+	}
+out:
+	__xdp_release_frame(xdpf->data, mem);
+}
+
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		       struct net_device *dev, u32 queue_index,
+		       unsigned int napi_id, u32 frag_size);
+static inline int
+xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		 struct net_device *dev, u32 queue_index,
+		 unsigned int napi_id)
+{
+	return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0);
 }
 
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index, unsigned int napi_id);
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
 bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b0383d371b9a..16a7574292a5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -330,6 +330,8 @@ union bpf_iter_link_info {
  *			*ctx_out*, *data_in* and *data_out* must be NULL.
  *			*repeat* must be zero.
  *
+ *		BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
@@ -1111,6 +1113,11 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS	(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
@@ -1775,6 +1782,8 @@ union bpf_attr {
  * 		0 on success, or a negative error in case of failure.
  *
  * u64 bpf_get_current_pid_tgid(void)
+ * 	Description
+ * 		Get the current pid and tgid.
  * 	Return
  * 		A 64-bit integer containing the current tgid and pid, and
  * 		created as such:
@@ -1782,6 +1791,8 @@ union bpf_attr {
  * 		*current_task*\ **->pid**.
  *
  * u64 bpf_get_current_uid_gid(void)
+ * 	Description
+ * 		Get the current uid and gid.
  * 	Return
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
@@ -2256,6 +2267,8 @@ union bpf_attr {
  * 		The 32-bit hash.
  *
  * u64 bpf_get_current_task(void)
+ * 	Description
+ * 		Get the current task.
  * 	Return
  * 		A pointer to the current task struct.
  *
@@ -2369,6 +2382,8 @@ union bpf_attr {
  * 		indicate that the hash is outdated and to trigger a
  * 		recalculation the next time the kernel tries to access this
  * 		hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * 	Return
+ * 		void.
  *
  * long bpf_get_numa_node_id(void)
  * 	Description
@@ -2466,6 +2481,8 @@ union bpf_attr {
  * 		A 8-byte long unique number or 0 if *sk* is NULL.
  *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * 	Description
+ * 		Get the owner UID of the socked associated to *skb*.
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
  * 		is **NULL**, or if it is not a full socket (i.e. if it is a
@@ -3240,6 +3257,9 @@ union bpf_attr {
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
  * u64 bpf_get_current_cgroup_id(void)
+ * 	Description
+ * 		Get the current cgroup id based on the cgroup within which
+ * 		the current task is running.
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
@@ -5018,6 +5038,44 @@ union bpf_attr {
  *
  *	Return
  *		The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ *	Description
+ *		Get the syscall's return value that will be returned to userspace.
+ *
+ *		This helper is currently supported by cgroup programs only.
+ *	Return
+ *		The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ *	Description
+ *		Set the syscall's return value that will be returned to userspace.
+ *
+ *		This helper is currently supported by cgroup programs only.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ *	Description
+ *		Get the total size of a given xdp buff (linear and paged area)
+ *	Return
+ *		The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		This helper is provided as an easy way to load data from a
+ *		xdp buffer. It can be used to load *len* bytes from *offset* from
+ *		the frame associated to *xdp_md*, into the buffer pointed by
+ *		*buf*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ *	Description
+ *		Store *len* bytes from buffer *buf* into the frame
+ *		associated to *xdp_md*, at *offset*.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5206,6 +5264,11 @@ union bpf_attr {
 	FN(get_func_arg),		\
 	FN(get_func_ret),		\
 	FN(get_func_arg_cnt),		\
+	FN(get_retval),			\
+	FN(set_retval),			\
+	FN(xdp_get_buff_len),		\
+	FN(xdp_load_bytes),		\
+	FN(xdp_store_bytes),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper