Merge branch 'Add skb + xdp dynptrs'

Joanne Koong says:

====================

This patchset is the 2nd in the dynptr series. The 1st can be found here [0].

This patchset adds skb and xdp type dynptrs, which have two main benefits for
packet parsing:
    * allowing operations on sizes that are not statically known at
      compile-time (eg variable-sized accesses).
    * more ergonomic and less brittle iteration through data (eg does not need
      manual if checking for being within bounds of data_end)

When comparing the differences in runtime for packet parsing without dynptrs
vs. with dynptrs, there is no noticeable difference. Patch 9 contains more
details as well as examples of how to use skb and xdp dynptrs.

[0] https://lore.kernel.org/bpf/20220523210712.3641569-1-joannelkoong@gmail.com/
---
Changelog:

v12 = https://lore.kernel.org/bpf/20230226085120.3907863-1-joannelkoong@gmail.com/
v12 -> v13:
    * Fix missing { } for case statement

v11 = https://lore.kernel.org/bpf/20230222060747.2562549-1-joannelkoong@gmail.com/
v11 -> v12:
    * Change constant mem size checking to use "__szk" kfunc annotation
      for slices
    * Use autoloading for success selftests

v10 = https://lore.kernel.org/bpf/20230216225524.1192789-1-joannelkoong@gmail.com/
v10 -> v11:
    * Reject bpf_dynptr_slice_rdwr() for non-writable progs at load time
      instead of runtime
    * Add additional patch (__uninit kfunc annotation)
    * Expand on documentation
    * Add bpf_dynptr_write() calls for persisting writes in tests

v9 = https://lore.kernel.org/bpf/20230127191703.3864860-1-joannelkoong@gmail.com/
v9 -> v10:
    * Add bpf_dynptr_slice and bpf_dynptr_slice_rdwr interface
    * Add some more tests
    * Split up patchset into more parts to make it easier to review

v8 = https://lore.kernel.org/bpf/20230126233439.3739120-1-joannelkoong@gmail.com/
v8 -> v9:
    * Fix dynptr_get_type() to check non-stack dynptrs

v7 = https://lore.kernel.org/bpf/20221021011510.1890852-1-joannelkoong@gmail.com/
v7 -> v8:
    * Change helpers to kfuncs
    * Add 2 new patches (1/5 and 2/5)

v6 = https://lore.kernel.org/bpf/20220907183129.745846-1-joannelkoong@gmail.com/
v6 -> v7
    * Change bpf_dynptr_data() to return read-only data slices if the skb prog
      is read-only (Martin)
    * Add test "skb_invalid_write" to test that writes to rd-only data slices
      are rejected

v5 = https://lore.kernel.org/bpf/20220831183224.3754305-1-joannelkoong@gmail.com/
v5 -> v6
    * Address kernel test robot errors by static inlining

v4 = https://lore.kernel.org/bpf/20220822235649.2218031-1-joannelkoong@gmail.com/
v4 -> v5
    * Address kernel test robot errors for configs w/out CONFIG_NET set
    * For data slices, return PTR_TO_MEM instead of PTR_TO_PACKET (Kumar)
    * Split selftests into subtests (Andrii)
    * Remove insn patching. Use rdonly and rdwr protos for dynptr skb
      construction (Andrii)
    * bpf_dynptr_data() returns NULL for rd-only dynptrs. There will be a
      separate bpf_dynptr_data_rdonly() added later (Andrii and Kumar)

v3 = https://lore.kernel.org/bpf/20220822193442.657638-1-joannelkoong@gmail.com/
v3 -> v4
    * Forgot to commit --amend the kernel test robot error fixups

v2 = https://lore.kernel.org/bpf/20220811230501.2632393-1-joannelkoong@gmail.com/
v2 -> v3
    * Fix kernel test robot build test errors

v1 = https://lore.kernel.org/bpf/20220726184706.954822-1-joannelkoong@gmail.com/
v1 -> v2
  * Return data slices to rd-only skb dynptrs (Martin)
  * bpf_dynptr_write allows writes to frags for skb dynptrs, but always
    invalidates associated data slices (Martin)
  * Use switch casing instead of ifs (Andrii)
  * Use 0xFD for experimental kind number in the selftest (Zvi)
  * Put selftest conversions w/ dynptrs into new files (Alexei)
  * Add new selftest "test_cls_redirect_dynptr.c"
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Documentation/bpf/kfuncs.rst

@@ -100,6 +100,23 @@ Hence, whenever a constant scalar argument is accepted by a kfunc which is not a
 size parameter, and the value of the constant matters for program safety, __k
 suffix should be used.
 
+2.2.2 __uninit Annotation
+--------------------
+
+This annotation is used to indicate that the argument will be treated as
+uninitialized.
+
+An example is given below::
+
+        __bpf_kfunc int bpf_dynptr_from_skb(..., struct bpf_dynptr_kern *ptr__uninit)
+        {
+        ...
+        }
+
+Here, the dynptr will be treated as an uninitialized dynptr. Without this
+annotation, the verifier will reject the program if the dynptr passed in is
+not initialized.
+
 .. _BPF_kfunc_nodef:
 
 2.3 Using an existing kernel function

include/linux/bpf.h

@@ -607,11 +607,18 @@ enum bpf_type_flag {
 	 */
 	NON_OWN_REF		= BIT(14 + BPF_BASE_TYPE_BITS),
 
+	/* DYNPTR points to sk_buff */
+	DYNPTR_TYPE_SKB		= BIT(15 + BPF_BASE_TYPE_BITS),
+
+	/* DYNPTR points to xdp_buff */
+	DYNPTR_TYPE_XDP		= BIT(16 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
-#define DYNPTR_TYPE_FLAG_MASK	(DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
+#define DYNPTR_TYPE_FLAG_MASK	(DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \
+				 | DYNPTR_TYPE_XDP)
 
 /* Max number of base types. */
 #define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
@@ -1124,6 +1131,37 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 
+/* the implementation of the opaque uapi struct bpf_dynptr */
+struct bpf_dynptr_kern {
+	void *data;
+	/* Size represents the number of usable bytes of dynptr data.
+	 * If for example the offset is at 4 for a local dynptr whose data is
+	 * of type u64, the number of usable bytes is 4.
+	 *
+	 * The upper 8 bits are reserved. It is as follows:
+	 * Bits 0 - 23 = size
+	 * Bits 24 - 30 = dynptr type
+	 * Bit 31 = whether dynptr is read-only
+	 */
+	u32 size;
+	u32 offset;
+} __aligned(8);
+
+enum bpf_dynptr_type {
+	BPF_DYNPTR_TYPE_INVALID,
+	/* Points to memory that is local to the bpf program */
+	BPF_DYNPTR_TYPE_LOCAL,
+	/* Underlying data is a ringbuf record */
+	BPF_DYNPTR_TYPE_RINGBUF,
+	/* Underlying data is a sk_buff */
+	BPF_DYNPTR_TYPE_SKB,
+	/* Underlying data is a xdp_buff */
+	BPF_DYNPTR_TYPE_XDP,
+};
+
+int bpf_dynptr_check_size(u32 size);
+u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr);
+
 #ifdef CONFIG_BPF_JIT
 int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
 int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
@@ -2266,6 +2304,11 @@ static inline bool has_current_bpf_ctx(void)
 }
 
 void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog);
+
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+		     enum bpf_dynptr_type type, u32 offset, u32 size);
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
+void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -2495,6 +2538,19 @@ static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog)
 static inline void bpf_cgrp_storage_free(struct cgroup *cgroup)
 {
 }
+
+static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+				   enum bpf_dynptr_type type, u32 offset, u32 size)
+{
+}
+
+static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
+{
+}
+
+static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
@@ -2801,6 +2857,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				struct bpf_insn *insn_buf,
 				struct bpf_prog *prog,
 				u32 *target_size);
+int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
+			       struct bpf_dynptr_kern *ptr);
 #else
 static inline bool bpf_sock_common_is_valid_access(int off, int size,
 						   enum bpf_access_type type,
@@ -2822,6 +2880,11 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 {
 	return 0;
 }
+static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
+					     struct bpf_dynptr_kern *ptr)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #ifdef CONFIG_INET
@@ -2913,36 +2976,6 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 num_args, struct bpf_bprintf_data *data);
 void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
 
-/* the implementation of the opaque uapi struct bpf_dynptr */
-struct bpf_dynptr_kern {
-	void *data;
-	/* Size represents the number of usable bytes of dynptr data.
-	 * If for example the offset is at 4 for a local dynptr whose data is
-	 * of type u64, the number of usable bytes is 4.
-	 *
-	 * The upper 8 bits are reserved. It is as follows:
-	 * Bits 0 - 23 = size
-	 * Bits 24 - 30 = dynptr type
-	 * Bit 31 = whether dynptr is read-only
-	 */
-	u32 size;
-	u32 offset;
-} __aligned(8);
-
-enum bpf_dynptr_type {
-	BPF_DYNPTR_TYPE_INVALID,
-	/* Points to memory that is local to the bpf program */
-	BPF_DYNPTR_TYPE_LOCAL,
-	/* Underlying data is a kernel-produced ringbuf record */
-	BPF_DYNPTR_TYPE_RINGBUF,
-};
-
-void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
-		     enum bpf_dynptr_type type, u32 offset, u32 size);
-void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
-int bpf_dynptr_check_size(u32 size);
-u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr);
-
 #ifdef CONFIG_BPF_LSM
 void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
 void bpf_cgroup_atype_put(int cgroup_atype);

include/linux/bpf_verifier.h

@@ -616,9 +616,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 			   enum bpf_arg_type arg_type);
 int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 		   u32 regno, u32 mem_size);
-struct bpf_call_arg_meta;
-int process_dynptr_func(struct bpf_verifier_env *env, int regno,
-			enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta);
 
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,

include/linux/filter.h

@@ -1542,4 +1542,50 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index
 	return XDP_REDIRECT;
 }
 
+#ifdef CONFIG_NET
+int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len);
+int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from,
+			  u32 len, u64 flags);
+int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);
+int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);
+void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len);
+void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
+		      void *buf, unsigned long len, bool flush);
+#else /* CONFIG_NET */
+static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset,
+				       void *to, u32 len)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset,
+					const void *from, u32 len, u64 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset,
+				       void *buf, u32 len)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset,
+					void *buf, u32 len)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
+{
+	return NULL;
+}
+
+static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf,
+				     unsigned long len, bool flush)
+{
+	return NULL;
+}
+#endif /* CONFIG_NET */
+
 #endif /* __LINUX_FILTER_H__ */

include/uapi/linux/bpf.h

@@ -5325,11 +5325,22 @@ union bpf_attr {
  *	Description
  *		Write *len* bytes from *src* into *dst*, starting from *offset*
  *		into *dst*.
- *		*flags* is currently unused.
+ *
+ *		*flags* must be 0 except for skb-type dynptrs.
+ *
+ *		For skb-type dynptrs:
+ *		    *  All data slices of the dynptr are automatically
+ *		       invalidated after **bpf_dynptr_write**\ (). This is
+ *		       because writing may pull the skb and change the
+ *		       underlying packet buffer.
+ *
+ *		    *  For *flags*, please see the flags accepted by
+ *		       **bpf_skb_store_bytes**\ ().
  *	Return
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
- *		is a read-only dynptr or if *flags* is not 0.
+ *		is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
+ *		other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
  *
  * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
  *	Description
@@ -5337,6 +5348,9 @@ union bpf_attr {
  *
  *		*len* must be a statically known value. The returned data slice
  *		is invalidated whenever the dynptr is invalidated.
+ *
+ *		skb and xdp type dynptrs may not use bpf_dynptr_data. They should
+ *		instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
  *	Return
  *		Pointer to the underlying dynptr data, NULL if the dynptr is
  *		read-only, if the dynptr is invalid, or if the offset and length

kernel/bpf/btf.c

@@ -207,6 +207,11 @@ enum btf_kfunc_hook {
 	BTF_KFUNC_HOOK_TRACING,
 	BTF_KFUNC_HOOK_SYSCALL,
 	BTF_KFUNC_HOOK_FMODRET,
+	BTF_KFUNC_HOOK_CGROUP_SKB,
+	BTF_KFUNC_HOOK_SCHED_ACT,
+	BTF_KFUNC_HOOK_SK_SKB,
+	BTF_KFUNC_HOOK_SOCKET_FILTER,
+	BTF_KFUNC_HOOK_LWT,
 	BTF_KFUNC_HOOK_MAX,
 };
 
@@ -5683,6 +5688,10 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 	 * int socket_filter_bpf_prog(struct __sk_buff *skb)
 	 * { // no fields of skb are ever used }
 	 */
+	if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0)
+		return ctx_type;
+	if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0)
+		return ctx_type;
 	if (strcmp(ctx_tname, tname)) {
 		/* bpf_user_pt_regs_t is a typedef, so resolve it to
 		 * underlying struct and check name again
@@ -7704,6 +7713,19 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
 		return BTF_KFUNC_HOOK_TRACING;
 	case BPF_PROG_TYPE_SYSCALL:
 		return BTF_KFUNC_HOOK_SYSCALL;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		return BTF_KFUNC_HOOK_CGROUP_SKB;
+	case BPF_PROG_TYPE_SCHED_ACT:
+		return BTF_KFUNC_HOOK_SCHED_ACT;
+	case BPF_PROG_TYPE_SK_SKB:
+		return BTF_KFUNC_HOOK_SK_SKB;
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+		return BTF_KFUNC_HOOK_SOCKET_FILTER;
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_XMIT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+		return BTF_KFUNC_HOOK_LWT;
 	default:
 		return BTF_KFUNC_HOOK_MAX;
 	}

kernel/bpf/helpers.c

@@ -1420,11 +1420,21 @@ static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr)
 	return ptr->size & DYNPTR_RDONLY_BIT;
 }
 
+void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
+{
+	ptr->size |= DYNPTR_RDONLY_BIT;
+}
+
 static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type)
 {
 	ptr->size |= type << DYNPTR_TYPE_SHIFT;
 }
 
+static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *ptr)
+{
+	return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT;
+}
+
 u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr)
 {
 	return ptr->size & DYNPTR_SIZE_MASK;
@@ -1497,6 +1507,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
 BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
 	   u32, offset, u64, flags)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
 	if (!src->data || flags)
@@ -1506,13 +1517,25 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern
 	if (err)
 		return err;
 
+	type = bpf_dynptr_get_type(src);
+
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
 		/* Source and destination may possibly overlap, hence use memmove to
 		 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
 		 * pointing to overlapping PTR_TO_MAP_VALUE regions.
 		 */
 		memmove(dst, src->data + src->offset + offset, len);
-
 		return 0;
+	case BPF_DYNPTR_TYPE_SKB:
+		return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len);
+	case BPF_DYNPTR_TYPE_XDP:
+		return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len);
+	default:
+		WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type);
+		return -EFAULT;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_read_proto = {
@@ -1529,22 +1552,40 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = {
 BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
 	   u32, len, u64, flags)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
-	if (!dst->data || flags || bpf_dynptr_is_rdonly(dst))
+	if (!dst->data || bpf_dynptr_is_rdonly(dst))
 		return -EINVAL;
 
 	err = bpf_dynptr_check_off_len(dst, offset, len);
 	if (err)
 		return err;
 
+	type = bpf_dynptr_get_type(dst);
+
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		if (flags)
+			return -EINVAL;
 		/* Source and destination may possibly overlap, hence use memmove to
 		 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
 		 * pointing to overlapping PTR_TO_MAP_VALUE regions.
 		 */
 		memmove(dst->data + dst->offset + offset, src, len);
-
 		return 0;
+	case BPF_DYNPTR_TYPE_SKB:
+		return __bpf_skb_store_bytes(dst->data, dst->offset + offset, src, len,
+					     flags);
+	case BPF_DYNPTR_TYPE_XDP:
+		if (flags)
+			return -EINVAL;
+		return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len);
+	default:
+		WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type);
+		return -EFAULT;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_write_proto = {
@@ -1560,6 +1601,7 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = {
 
 BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
 	if (!ptr->data)
@@ -1572,7 +1614,20 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3
 	if (bpf_dynptr_is_rdonly(ptr))
 		return 0;
 
+	type = bpf_dynptr_get_type(ptr);
+
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
 		return (unsigned long)(ptr->data + ptr->offset + offset);
+	case BPF_DYNPTR_TYPE_SKB:
+	case BPF_DYNPTR_TYPE_XDP:
+		/* skb and xdp dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */
+		return 0;
+	default:
+		WARN_ONCE(true, "bpf_dynptr_data: unknown dynptr type %d\n", type);
+		return 0;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_data_proto = {
@@ -2138,6 +2193,142 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
 	return p;
 }
 
+/**
+ * bpf_dynptr_slice - Obtain a read-only pointer to the dynptr data.
+ *
+ * For non-skb and non-xdp type dynptrs, there is no difference between
+ * bpf_dynptr_slice and bpf_dynptr_data.
+ *
+ * If the intention is to write to the data slice, please use
+ * bpf_dynptr_slice_rdwr.
+ *
+ * The user must check that the returned pointer is not null before using it.
+ *
+ * Please note that in the case of skb and xdp dynptrs, bpf_dynptr_slice
+ * does not change the underlying packet data pointers, so a call to
+ * bpf_dynptr_slice will not invalidate any ctx->data/data_end pointers in
+ * the bpf program.
+ *
+ * @ptr: The dynptr whose data slice to retrieve
+ * @offset: Offset into the dynptr
+ * @buffer: User-provided buffer to copy contents into
+ * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
+ * requested slice. This must be a constant.
+ *
+ * @returns: NULL if the call failed (eg invalid dynptr), pointer to a read-only
+ * data slice (can be either direct pointer to the data or a pointer to the user
+ * provided buffer, with its contents containing the data, if unable to obtain
+ * direct pointer)
+ */
+__bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset,
+				   void *buffer, u32 buffer__szk)
+{
+	enum bpf_dynptr_type type;
+	u32 len = buffer__szk;
+	int err;
+
+	if (!ptr->data)
+		return 0;
+
+	err = bpf_dynptr_check_off_len(ptr, offset, len);
+	if (err)
+		return 0;
+
+	type = bpf_dynptr_get_type(ptr);
+
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		return ptr->data + ptr->offset + offset;
+	case BPF_DYNPTR_TYPE_SKB:
+		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer);
+	case BPF_DYNPTR_TYPE_XDP:
+	{
+		void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
+		if (xdp_ptr)
+			return xdp_ptr;
+
+		bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false);
+		return buffer;
+	}
+	default:
+		WARN_ONCE(true, "unknown dynptr type %d\n", type);
+		return 0;
+	}
+}
+
+/**
+ * bpf_dynptr_slice_rdwr - Obtain a writable pointer to the dynptr data.
+ *
+ * For non-skb and non-xdp type dynptrs, there is no difference between
+ * bpf_dynptr_slice and bpf_dynptr_data.
+ *
+ * The returned pointer is writable and may point to either directly the dynptr
+ * data at the requested offset or to the buffer if unable to obtain a direct
+ * data pointer to (example: the requested slice is to the paged area of an skb
+ * packet). In the case where the returned pointer is to the buffer, the user
+ * is responsible for persisting writes through calling bpf_dynptr_write(). This
+ * usually looks something like this pattern:
+ *
+ * struct eth_hdr *eth = bpf_dynptr_slice_rdwr(&dynptr, 0, buffer, sizeof(buffer));
+ * if (!eth)
+ *	return TC_ACT_SHOT;
+ *
+ * // mutate eth header //
+ *
+ * if (eth == buffer)
+ *	bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0);
+ *
+ * Please note that, as in the example above, the user must check that the
+ * returned pointer is not null before using it.
+ *
+ * Please also note that in the case of skb and xdp dynptrs, bpf_dynptr_slice_rdwr
+ * does not change the underlying packet data pointers, so a call to
+ * bpf_dynptr_slice_rdwr will not invalidate any ctx->data/data_end pointers in
+ * the bpf program.
+ *
+ * @ptr: The dynptr whose data slice to retrieve
+ * @offset: Offset into the dynptr
+ * @buffer: User-provided buffer to copy contents into
+ * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
+ * requested slice. This must be a constant.
+ *
+ * @returns: NULL if the call failed (eg invalid dynptr), pointer to a
+ * data slice (can be either direct pointer to the data or a pointer to the user
+ * provided buffer, with its contents containing the data, if unable to obtain
+ * direct pointer)
+ */
+__bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset,
+					void *buffer, u32 buffer__szk)
+{
+	if (!ptr->data || bpf_dynptr_is_rdonly(ptr))
+		return 0;
+
+	/* bpf_dynptr_slice_rdwr is the same logic as bpf_dynptr_slice.
+	 *
+	 * For skb-type dynptrs, it is safe to write into the returned pointer
+	 * if the bpf program allows skb data writes. There are two possiblities
+	 * that may occur when calling bpf_dynptr_slice_rdwr:
+	 *
+	 * 1) The requested slice is in the head of the skb. In this case, the
+	 * returned pointer is directly to skb data, and if the skb is cloned, the
+	 * verifier will have uncloned it (see bpf_unclone_prologue()) already.
+	 * The pointer can be directly written into.
+	 *
+	 * 2) Some portion of the requested slice is in the paged buffer area.
+	 * In this case, the requested data will be copied out into the buffer
+	 * and the returned pointer will be a pointer to the buffer. The skb
+	 * will not be pulled. To persist the write, the user will need to call
+	 * bpf_dynptr_write(), which will pull the skb and commit the write.
+	 *
+	 * Similarly for xdp programs, if the requested slice is not across xdp
+	 * fragments, then a direct pointer will be returned, otherwise the data
+	 * will be copied out into the buffer and the user will need to call
+	 * bpf_dynptr_write() to commit changes.
+	 */
+	return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk);
+}
+
 __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj)
 {
 	return obj;
@@ -2207,6 +2398,8 @@ BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx)
 BTF_ID_FLAGS(func, bpf_rdonly_cast)
 BTF_ID_FLAGS(func, bpf_rcu_read_lock)
 BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
+BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
 BTF_SET8_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {

net/core/filter.c

@@ -1721,6 +1721,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from,
+			  u32 len, u64 flags)
+{
+	return ____bpf_skb_store_bytes(skb, offset, from, len, flags);
+}
+
 BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset,
 	   void *, to, u32, len)
 {
@@ -1751,6 +1757,11 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+{
+	return ____bpf_skb_load_bytes(skb, offset, to, len);
+}
+
 BPF_CALL_4(bpf_flow_dissector_load_bytes,
 	   const struct bpf_flow_dissector *, ctx, u32, offset,
 	   void *, to, u32, len)
@@ -3883,7 +3894,7 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
+void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
 		      void *buf, unsigned long len, bool flush)
 {
 	unsigned long ptr_len, ptr_off = 0;
@@ -3930,7 +3941,7 @@ static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
 	}
 }
 
-static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
+void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	u32 size = xdp->data_end - xdp->data;
@@ -3988,6 +3999,11 @@ static const struct bpf_func_proto bpf_xdp_load_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len)
+{
+	return ____bpf_xdp_load_bytes(xdp, offset, buf, len);
+}
+
 BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset,
 	   void *, buf, u32, len)
 {
@@ -4015,6 +4031,11 @@ static const struct bpf_func_proto bpf_xdp_store_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len)
+{
+	return ____bpf_xdp_store_bytes(xdp, offset, buf, len);
+}
+
 static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -11621,3 +11642,82 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 
 	return func;
 }
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags,
+				    struct bpf_dynptr_kern *ptr__uninit)
+{
+	if (flags) {
+		bpf_dynptr_set_null(ptr__uninit);
+		return -EINVAL;
+	}
+
+	bpf_dynptr_init(ptr__uninit, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len);
+
+	return 0;
+}
+
+__bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags,
+				    struct bpf_dynptr_kern *ptr__uninit)
+{
+	if (flags) {
+		bpf_dynptr_set_null(ptr__uninit);
+		return -EINVAL;
+	}
+
+	bpf_dynptr_init(ptr__uninit, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp));
+
+	return 0;
+}
+__diag_pop();
+
+int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
+			       struct bpf_dynptr_kern *ptr__uninit)
+{
+	int err;
+
+	err = bpf_dynptr_from_skb(skb, flags, ptr__uninit);
+	if (err)
+		return err;
+
+	bpf_dynptr_set_rdonly(ptr__uninit);
+
+	return 0;
+}
+
+BTF_SET8_START(bpf_kfunc_check_set_skb)
+BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
+BTF_SET8_END(bpf_kfunc_check_set_skb)
+
+BTF_SET8_START(bpf_kfunc_check_set_xdp)
+BTF_ID_FLAGS(func, bpf_dynptr_from_xdp)
+BTF_SET8_END(bpf_kfunc_check_set_xdp)
+
+static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_skb,
+};
+
+static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_xdp,
+};
+
+static int __init bpf_kfunc_init(void)
+{
+	int ret;
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
+	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
+}
+late_initcall(bpf_kfunc_init);

tools/include/uapi/linux/bpf.h

@@ -5325,11 +5325,22 @@ union bpf_attr {
  *	Description
  *		Write *len* bytes from *src* into *dst*, starting from *offset*
  *		into *dst*.
- *		*flags* is currently unused.
+ *
+ *		*flags* must be 0 except for skb-type dynptrs.
+ *
+ *		For skb-type dynptrs:
+ *		    *  All data slices of the dynptr are automatically
+ *		       invalidated after **bpf_dynptr_write**\ (). This is
+ *		       because writing may pull the skb and change the
+ *		       underlying packet buffer.
+ *
+ *		    *  For *flags*, please see the flags accepted by
+ *		       **bpf_skb_store_bytes**\ ().
  *	Return
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
- *		is a read-only dynptr or if *flags* is not 0.
+ *		is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
+ *		other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
  *
  * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
  *	Description
@@ -5337,6 +5348,9 @@ union bpf_attr {
  *
  *		*len* must be a statically known value. The returned data slice
  *		is invalidated whenever the dynptr is invalidated.
+ *
+ *		skb and xdp type dynptrs may not use bpf_dynptr_data. They should
+ *		instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
  *	Return
  *		Pointer to the underlying dynptr data, NULL if the dynptr is
  *		read-only, if the dynptr is invalid, or if the offset and length

tools/testing/selftests/bpf/DENYLIST.s390x

@@ -4,6 +4,8 @@ bloom_filter_map                         # failed to find kernel BTF type ID of
 bpf_cookie                               # failed to open_and_load program: -524 (trampoline)
 bpf_loop                                 # attaches to __x64_sys_nanosleep
 cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
+dynptr/test_dynptr_skb_data
+dynptr/test_skb_readonly
 fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
 kprobe_multi_bench_attach                # bpf_program__attach_kprobe_multi_opts unexpected error: -95

tools/testing/selftests/bpf/bpf_kfuncs.h

+#ifndef __BPF_KFUNCS__
+#define __BPF_KFUNCS__
+
+/* Description
+ *  Initializes an skb-type dynptr
+ * Returns
+ *  Error code
+ */
+extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
+    struct bpf_dynptr *ptr__uninit) __ksym;
+
+/* Description
+ *  Initializes an xdp-type dynptr
+ * Returns
+ *  Error code
+ */
+extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags,
+			       struct bpf_dynptr *ptr__uninit) __ksym;
+
+/* Description
+ *  Obtain a read-only pointer to the dynptr's data
+ * Returns
+ *  Either a direct pointer to the dynptr data or a pointer to the user-provided
+ *  buffer if unable to obtain a direct pointer
+ */
+extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset,
+			      void *buffer, __u32 buffer__szk) __ksym;
+
+/* Description
+ *  Obtain a read-write pointer to the dynptr's data
+ * Returns
+ *  Either a direct pointer to the dynptr data or a pointer to the user-provided
+ *  buffer if unable to obtain a direct pointer
+ */
+extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset,
+			      void *buffer, __u32 buffer__szk) __ksym;
+
+#endif

tools/testing/selftests/bpf/prog_tests/cls_redirect.c

@@ -13,6 +13,7 @@
 
 #include "progs/test_cls_redirect.h"
 #include "test_cls_redirect.skel.h"
+#include "test_cls_redirect_dynptr.skel.h"
 #include "test_cls_redirect_subprogs.skel.h"
 
 #define ENCAP_IP INADDR_LOOPBACK
@@ -446,6 +447,28 @@ static void test_cls_redirect_common(struct bpf_program *prog)
 	close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0]));
 }
 
+static void test_cls_redirect_dynptr(void)
+{
+	struct test_cls_redirect_dynptr *skel;
+	int err;
+
+	skel = test_cls_redirect_dynptr__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+	err = test_cls_redirect_dynptr__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	test_cls_redirect_common(skel->progs.cls_redirect);
+
+cleanup:
+	test_cls_redirect_dynptr__destroy(skel);
+}
+
 static void test_cls_redirect_inlined(void)
 {
 	struct test_cls_redirect *skel;
@@ -496,4 +519,6 @@ void test_cls_redirect(void)
 		test_cls_redirect_inlined();
 	if (test__start_subtest("cls_redirect_subprogs"))
 		test_cls_redirect_subprogs();
+	if (test__start_subtest("cls_redirect_dynptr"))
+		test_cls_redirect_dynptr();
 }

tools/testing/selftests/bpf/prog_tests/dynptr.c

@@ -2,20 +2,32 @@
 /* Copyright (c) 2022 Facebook */
 
 #include <test_progs.h>
+#include <network_helpers.h>
 #include "dynptr_fail.skel.h"
 #include "dynptr_success.skel.h"
 
-static const char * const success_tests[] = {
-	"test_read_write",
-	"test_data_slice",
-	"test_ringbuf",
+enum test_setup_type {
+	SETUP_SYSCALL_SLEEP,
+	SETUP_SKB_PROG,
 };
 
-static void verify_success(const char *prog_name)
+static struct {
+	const char *prog_name;
+	enum test_setup_type type;
+} success_tests[] = {
+	{"test_read_write", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_data", SETUP_SYSCALL_SLEEP},
+	{"test_ringbuf", SETUP_SYSCALL_SLEEP},
+	{"test_skb_readonly", SETUP_SKB_PROG},
+	{"test_dynptr_skb_data", SETUP_SKB_PROG},
+};
+
+static void verify_success(const char *prog_name, enum test_setup_type setup_type)
 {
 	struct dynptr_success *skel;
 	struct bpf_program *prog;
 	struct bpf_link *link;
+       int err;
 
 	skel = dynptr_success__open();
 	if (!ASSERT_OK_PTR(skel, "dynptr_success__open"))
@@ -23,23 +35,53 @@ static void verify_success(const char *prog_name)
 
 	skel->bss->pid = getpid();
 
-	dynptr_success__load(skel);
-	if (!ASSERT_OK_PTR(skel, "dynptr_success__load"))
-		goto cleanup;
-
 	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
 	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 		goto cleanup;
 
+       bpf_program__set_autoload(prog, true);
+
+	err = dynptr_success__load(skel);
+	if (!ASSERT_OK(err, "dynptr_success__load"))
+		goto cleanup;
+
+	switch (setup_type) {
+	case SETUP_SYSCALL_SLEEP:
 		link = bpf_program__attach(prog);
 		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
 			goto cleanup;
 
 		usleep(1);
 
-	ASSERT_EQ(skel->bss->err, 0, "err");
-
 		bpf_link__destroy(link);
+		break;
+	case SETUP_SKB_PROG:
+	{
+		int prog_fd;
+		char buf[64];
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .data_in = &pkt_v4,
+			    .data_size_in = sizeof(pkt_v4),
+			    .data_out = buf,
+			    .data_size_out = sizeof(buf),
+			    .repeat = 1,
+		);
+
+		prog_fd = bpf_program__fd(prog);
+		if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+			goto cleanup;
+
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
+	}
+
+	ASSERT_EQ(skel->bss->err, 0, "err");
 
 cleanup:
 	dynptr_success__destroy(skel);
@@ -50,10 +92,10 @@ void test_dynptr(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(success_tests); i++) {
-		if (!test__start_subtest(success_tests[i]))
+		if (!test__start_subtest(success_tests[i].prog_name))
 			continue;
 
-		verify_success(success_tests[i]);
+		verify_success(success_tests[i].prog_name, success_tests[i].type);
 	}
 
 	RUN_TESTS(dynptr_fail);

tools/testing/selftests/bpf/prog_tests/l4lb_all.c

@@ -93,4 +93,6 @@ void test_l4lb_all(void)
 		test_l4lb("test_l4lb.bpf.o");
 	if (test__start_subtest("l4lb_noinline"))
 		test_l4lb("test_l4lb_noinline.bpf.o");
+	if (test__start_subtest("l4lb_noinline_dynptr"))
+		test_l4lb("test_l4lb_noinline_dynptr.bpf.o");
 }

tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_parse_tcp_hdr_opt.skel.h"
+#include "test_parse_tcp_hdr_opt_dynptr.skel.h"
+#include "test_tcp_hdr_options.h"
+
+struct test_pkt {
+	struct ipv6_packet pk6_v6;
+	u8 options[16];
+} __packed;
+
+struct test_pkt pkt = {
+	.pk6_v6.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+	.pk6_v6.iph.nexthdr = IPPROTO_TCP,
+	.pk6_v6.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.pk6_v6.tcp.urg_ptr = 123,
+	.pk6_v6.tcp.doff = 9, /* 16 bytes of options */
+
+	.options = {
+		TCPOPT_MSS, 4, 0x05, 0xB4, TCPOPT_NOP, TCPOPT_NOP,
+		0, 6, 0xBB, 0xBB, 0xBB, 0xBB, TCPOPT_EOL
+	},
+};
+
+static void test_parse_opt(void)
+{
+	struct test_parse_tcp_hdr_opt *skel;
+	struct bpf_program *prog;
+	char buf[128];
+	int err;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt,
+		    .data_size_in = sizeof(pkt),
+		    .data_out = buf,
+		    .data_size_out = sizeof(buf),
+		    .repeat = 3,
+	);
+
+	skel = test_parse_tcp_hdr_opt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	pkt.options[6] = skel->rodata->tcp_hdr_opt_kind_tpr;
+	prog = skel->progs.xdp_ingress_v6;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+	ASSERT_OK(err, "ipv6 test_run");
+	ASSERT_EQ(topts.retval, XDP_PASS, "ipv6 test_run retval");
+	ASSERT_EQ(skel->bss->server_id, 0xBBBBBBBB, "server id");
+
+	test_parse_tcp_hdr_opt__destroy(skel);
+}
+
+static void test_parse_opt_dynptr(void)
+{
+	struct test_parse_tcp_hdr_opt_dynptr *skel;
+	struct bpf_program *prog;
+	char buf[128];
+	int err;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt,
+		    .data_size_in = sizeof(pkt),
+		    .data_out = buf,
+		    .data_size_out = sizeof(buf),
+		    .repeat = 3,
+	);
+
+	skel = test_parse_tcp_hdr_opt_dynptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	pkt.options[6] = skel->rodata->tcp_hdr_opt_kind_tpr;
+	prog = skel->progs.xdp_ingress_v6;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+	ASSERT_OK(err, "ipv6 test_run");
+	ASSERT_EQ(topts.retval, XDP_PASS, "ipv6 test_run retval");
+	ASSERT_EQ(skel->bss->server_id, 0xBBBBBBBB, "server id");
+
+	test_parse_tcp_hdr_opt_dynptr__destroy(skel);
+}
+
+void test_parse_tcp_hdr_opt(void)
+{
+	if (test__start_subtest("parse_tcp_hdr_opt"))
+		test_parse_opt();
+	if (test__start_subtest("parse_tcp_hdr_opt_dynptr"))
+		test_parse_opt_dynptr();
+}

tools/testing/selftests/bpf/prog_tests/xdp_attach.c

@@ -4,11 +4,10 @@
 #define IFINDEX_LO 1
 #define XDP_FLAGS_REPLACE		(1U << 4)
 
-void serial_test_xdp_attach(void)
+static void test_xdp_attach(const char *file)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, len;
 	struct bpf_object *obj1, *obj2, *obj3;
-	const char *file = "./test_xdp.bpf.o";
 	struct bpf_prog_info info = {};
 	int err, fd1, fd2, fd3;
 	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
@@ -85,3 +84,11 @@ void serial_test_xdp_attach(void)
 out_1:
 	bpf_object__close(obj1);
 }
+
+void serial_test_xdp_attach(void)
+{
+	if (test__start_subtest("xdp_attach"))
+		test_xdp_attach("./test_xdp.bpf.o");
+	if (test__start_subtest("xdp_attach_dynptr"))
+		test_xdp_attach("./test_xdp_dynptr.bpf.o");
+}

tools/testing/selftests/bpf/progs/dynptr_fail.c

@@ -5,7 +5,9 @@
 #include <string.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
 #include "bpf_misc.h"
+#include "bpf_kfuncs.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -244,6 +246,27 @@ int data_slice_out_of_bounds_ringbuf(void *ctx)
 	return 0;
 }
 
+/* A data slice can't be accessed out of bounds */
+SEC("?tc")
+__failure __msg("value is outside of the allowed memory range")
+int data_slice_out_of_bounds_skb(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	/* this should fail */
+	*(__u8*)(hdr + 1) = 1;
+
+	return SK_PASS;
+}
+
 SEC("?raw_tp")
 __failure __msg("value is outside of the allowed memory range")
 int data_slice_out_of_bounds_map_value(void *ctx)
@@ -399,7 +422,6 @@ int invalid_helper2(void *ctx)
 
 	/* this should fail */
 	bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0);
-
 	return 0;
 }
 
@@ -1044,6 +1066,193 @@ int dynptr_read_into_slot(void *ctx)
 	return 0;
 }
 
+/* bpf_dynptr_slice()s are read-only and cannot be written to */
+SEC("?tc")
+__failure __msg("R0 cannot write into rdonly_mem")
+int skb_invalid_slice_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return SK_PASS;
+}
+
+/* The read-write data slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice2(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 123;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever bpf_dynptr_write() is called */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice3(struct __sk_buff *skb)
+{
+	char write_data[64] = "hello there, world!!";
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return SK_PASS;
+}
+
+/* The read-write data slice is invalidated whenever bpf_dynptr_write() is called */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice4(struct __sk_buff *skb)
+{
+	char write_data[64] = "hello there, world!!";
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 123;
+
+	bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever a helper changes packet data */
+SEC("?xdp")
+__failure __msg("invalid mem access 'scalar'")
+int xdp_invalid_data_slice1(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr)))
+		return XDP_DROP;
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return XDP_PASS;
+}
+
+/* The read-write data slice is invalidated whenever a helper changes packet data */
+SEC("?xdp")
+__failure __msg("invalid mem access 'scalar'")
+int xdp_invalid_data_slice2(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 9;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr)))
+		return XDP_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return XDP_PASS;
+}
+
+/* Only supported prog type can create skb-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_skb is not allowed")
+int skb_invalid_ctx(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(ctx, 0, &ptr);
+
+	return 0;
+}
+
 /* Reject writes to dynptr slot for uninit arg */
 SEC("?raw_tp")
 __failure __msg("potential write to dynptr at off=-16")
@@ -1061,6 +1270,61 @@ int uninit_write_into_slot(void *ctx)
 	return 0;
 }
 
+/* Only supported prog type can create xdp-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_xdp is not allowed")
+int xdp_invalid_ctx(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_xdp(ctx, 0, &ptr);
+
+	return 0;
+}
+
+__u32 hdr_size = sizeof(struct ethhdr);
+/* Can't pass in variable-sized len to bpf_dynptr_slice */
+SEC("?tc")
+__failure __msg("unbounded memory access")
+int dynptr_slice_var_len1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	/* this should fail */
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, hdr_size);
+	if (!hdr)
+		return SK_DROP;
+
+	return SK_PASS;
+}
+
+/* Can't pass in variable-sized len to bpf_dynptr_slice */
+SEC("?tc")
+__failure __msg("must be a known constant")
+int dynptr_slice_var_len2(struct __sk_buff *skb)
+{
+	char buffer[sizeof(struct ethhdr)] = {};
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	if (hdr_size <= sizeof(buffer)) {
+		/* this should fail */
+		hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, hdr_size);
+		if (!hdr)
+			return SK_DROP;
+		hdr->h_proto = 12;
+	}
+
+	return SK_PASS;
+}
+
 static int callback(__u32 index, void *data)
 {
         *(__u32 *)data = 123;
@@ -1092,3 +1356,24 @@ int invalid_data_slices(void *ctx)
 
 	return 0;
 }
+
+/* Program types that don't allow writes to packet data should fail if
+ * bpf_dynptr_slice_rdwr is called
+ */
+SEC("cgroup_skb/ingress")
+__failure __msg("the prog does not allow writes to packet data")
+int invalid_slice_rdwr_rdonly(struct __sk_buff *skb)
+{
+	char buffer[sizeof(struct ethhdr)] = {};
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	/* this should fail since cgroup_skb doesn't allow
+	 * changing packet data
+	 */
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+
+	return 0;
+}

tools/testing/selftests/bpf/progs/dynptr_success.c

@@ -5,6 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
+#include "bpf_kfuncs.h"
 #include "errno.h"
 
 char _license[] SEC("license") = "GPL";
@@ -30,7 +31,7 @@ struct {
 	__type(value, __u32);
 } array_map SEC(".maps");
 
-SEC("tp/syscalls/sys_enter_nanosleep")
+SEC("?tp/syscalls/sys_enter_nanosleep")
 int test_read_write(void *ctx)
 {
 	char write_data[64] = "hello there, world!!";
@@ -61,8 +62,8 @@ int test_read_write(void *ctx)
 	return 0;
 }
 
-SEC("tp/syscalls/sys_enter_nanosleep")
-int test_data_slice(void *ctx)
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_data(void *ctx)
 {
 	__u32 key = 0, val = 235, *map_val;
 	struct bpf_dynptr ptr;
@@ -131,7 +132,7 @@ static int ringbuf_callback(__u32 index, void *data)
 	return 0;
 }
 
-SEC("tp/syscalls/sys_enter_nanosleep")
+SEC("?tp/syscalls/sys_enter_nanosleep")
 int test_ringbuf(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -163,3 +164,49 @@ int test_ringbuf(void *ctx)
 	bpf_ringbuf_discard_dynptr(&ptr, 0);
 	return 0;
 }
+
+SEC("?cgroup_skb/egress")
+int test_skb_readonly(struct __sk_buff *skb)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	__u64 *data;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* since cgroup skbs are read only, writes should fail */
+	ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+	if (ret != -EINVAL) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_data(struct __sk_buff *skb)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	__u64 *data;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This should return NULL. Must use bpf_dynptr_slice API */
+	data = bpf_dynptr_data(&ptr, 0, 1);
+	if (data) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}

tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c

+// SPDX-License-Identifier: GPL-2.0
+
+/* This parsing logic is taken from the open source library katran, a layer 4
+ * load balancer.
+ *
+ * This code logic using dynptrs can be found in test_parse_tcp_hdr_opt_dynptr.c
+ *
+ * https://github.com/facebookincubator/katran/blob/main/katran/lib/bpf/pckt_parsing.h
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/tcp.h>
+#include <stdbool.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+#include "test_tcp_hdr_options.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Kind number used for experiments */
+const __u32 tcp_hdr_opt_kind_tpr = 0xFD;
+/* Length of the tcp header option */
+const __u32 tcp_hdr_opt_len_tpr = 6;
+/* maximum number of header options to check to lookup server_id */
+const __u32 tcp_hdr_opt_max_opt_checks = 15;
+
+__u32 server_id;
+
+struct hdr_opt_state {
+	__u32 server_id;
+	__u8 byte_offset;
+	__u8 hdr_bytes_remaining;
+};
+
+static int parse_hdr_opt(const struct xdp_md *xdp, struct hdr_opt_state *state)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	__u8 *tcp_opt, kind, hdr_len;
+
+	tcp_opt = (__u8 *)(data + state->byte_offset);
+	if (tcp_opt + 1 > data_end)
+		return -1;
+
+	kind = tcp_opt[0];
+
+	if (kind == TCPOPT_EOL)
+		return -1;
+
+	if (kind == TCPOPT_NOP) {
+		state->hdr_bytes_remaining--;
+		state->byte_offset++;
+		return 0;
+	}
+
+	if (state->hdr_bytes_remaining < 2 ||
+	    tcp_opt + sizeof(__u8) + sizeof(__u8) > data_end)
+		return -1;
+
+	hdr_len = tcp_opt[1];
+	if (hdr_len > state->hdr_bytes_remaining)
+		return -1;
+
+	if (kind == tcp_hdr_opt_kind_tpr) {
+		if (hdr_len != tcp_hdr_opt_len_tpr)
+			return -1;
+
+		if (tcp_opt + tcp_hdr_opt_len_tpr > data_end)
+			return -1;
+
+		state->server_id = *(__u32 *)&tcp_opt[2];
+		return 1;
+	}
+
+	state->hdr_bytes_remaining -= hdr_len;
+	state->byte_offset += hdr_len;
+	return 0;
+}
+
+SEC("xdp")
+int xdp_ingress_v6(struct xdp_md *xdp)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	struct hdr_opt_state opt_state = {};
+	__u8 tcp_hdr_opt_len = 0;
+	struct tcphdr *tcp_hdr;
+	__u64 tcp_offset = 0;
+	__u32 off;
+	int err;
+
+	tcp_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+	tcp_hdr = (struct tcphdr *)(data + tcp_offset);
+	if (tcp_hdr + 1 > data_end)
+		return XDP_DROP;
+
+	tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr);
+	if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr)
+		return XDP_DROP;
+
+	opt_state.hdr_bytes_remaining = tcp_hdr_opt_len;
+	opt_state.byte_offset = sizeof(struct tcphdr) + tcp_offset;
+
+	/* max number of bytes of options in tcp header is 40 bytes */
+	for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) {
+		err = parse_hdr_opt(xdp, &opt_state);
+
+		if (err || !opt_state.hdr_bytes_remaining)
+			break;
+	}
+
+	if (!opt_state.server_id)
+		return XDP_DROP;
+
+	server_id = opt_state.server_id;
+
+	return XDP_PASS;
+}

tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c

+// SPDX-License-Identifier: GPL-2.0
+
+/* This logic is lifted from a real-world use case of packet parsing, used in
+ * the open source library katran, a layer 4 load balancer.
+ *
+ * This test demonstrates how to parse packet contents using dynptrs. The
+ * original code (parsing without dynptrs) can be found in test_parse_tcp_hdr_opt.c
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/tcp.h>
+#include <stdbool.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+#include "test_tcp_hdr_options.h"
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Kind number used for experiments */
+const __u32 tcp_hdr_opt_kind_tpr = 0xFD;
+/* Length of the tcp header option */
+const __u32 tcp_hdr_opt_len_tpr = 6;
+/* maximum number of header options to check to lookup server_id */
+const __u32 tcp_hdr_opt_max_opt_checks = 15;
+
+__u32 server_id;
+
+static int parse_hdr_opt(struct bpf_dynptr *ptr, __u32 *off, __u8 *hdr_bytes_remaining,
+			 __u32 *server_id)
+{
+	__u8 *tcp_opt, kind, hdr_len;
+	__u8 buffer[sizeof(kind) + sizeof(hdr_len) + sizeof(*server_id)];
+	__u8 *data;
+
+	__builtin_memset(buffer, 0, sizeof(buffer));
+
+	data = bpf_dynptr_slice(ptr, *off, buffer, sizeof(buffer));
+	if (!data)
+		return -1;
+
+	kind = data[0];
+
+	if (kind == TCPOPT_EOL)
+		return -1;
+
+	if (kind == TCPOPT_NOP) {
+		*off += 1;
+		*hdr_bytes_remaining -= 1;
+		return 0;
+	}
+
+	if (*hdr_bytes_remaining < 2)
+		return -1;
+
+	hdr_len = data[1];
+	if (hdr_len > *hdr_bytes_remaining)
+		return -1;
+
+	if (kind == tcp_hdr_opt_kind_tpr) {
+		if (hdr_len != tcp_hdr_opt_len_tpr)
+			return -1;
+
+		__builtin_memcpy(server_id, (__u32 *)(data + 2), sizeof(*server_id));
+		return 1;
+	}
+
+	*off += hdr_len;
+	*hdr_bytes_remaining -= hdr_len;
+	return 0;
+}
+
+SEC("xdp")
+int xdp_ingress_v6(struct xdp_md *xdp)
+{
+	__u8 buffer[sizeof(struct tcphdr)] = {};
+	__u8 hdr_bytes_remaining;
+	struct tcphdr *tcp_hdr;
+	__u8 tcp_hdr_opt_len;
+	int err = 0;
+	__u32 off;
+
+	struct bpf_dynptr ptr;
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+
+	off = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+
+	tcp_hdr = bpf_dynptr_slice(&ptr, off, buffer, sizeof(buffer));
+	if (!tcp_hdr)
+		return XDP_DROP;
+
+	tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr);
+	if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr)
+		return XDP_DROP;
+
+	hdr_bytes_remaining = tcp_hdr_opt_len;
+
+	off += sizeof(struct tcphdr);
+
+	/* max number of bytes of options in tcp header is 40 bytes */
+	for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) {
+		err = parse_hdr_opt(&ptr, &off, &hdr_bytes_remaining, &server_id);
+
+		if (err || !hdr_bytes_remaining)
+			break;
+	}
+
+	if (!server_id)
+		return XDP_DROP;
+
+	return XDP_PASS;
+}

tools/testing/selftests/bpf/progs/test_xdp_dynptr.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "test_iptunnel_common.h"
+#include "bpf_kfuncs.h"
+
+const size_t tcphdr_sz = sizeof(struct tcphdr);
+const size_t udphdr_sz = sizeof(struct udphdr);
+const size_t ethhdr_sz = sizeof(struct ethhdr);
+const size_t iphdr_sz = sizeof(struct iphdr);
+const size_t ipv6hdr_sz = sizeof(struct ipv6hdr);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");
+
+static __always_inline void count_tx(__u32 protocol)
+{
+	__u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, __u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
+{
+	__u8 eth_buffer[ethhdr_sz + iphdr_sz + ethhdr_sz];
+	__u8 iph_buffer_tcp[iphdr_sz + tcphdr_sz];
+	__u8 iph_buffer_udp[iphdr_sz + udphdr_sz];
+	struct bpf_dynptr new_xdp_ptr;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	__u32 transport_hdr_sz;
+	struct iphdr *iph;
+	__u16 *next_iph;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	__u32 csum = 0;
+	int i;
+
+	__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
+	__builtin_memset(iph_buffer_tcp, 0, sizeof(iph_buffer_tcp));
+	__builtin_memset(iph_buffer_udp, 0, sizeof(iph_buffer_udp));
+
+	if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
+		iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_udp, sizeof(iph_buffer_udp));
+	else
+		iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_tcp, sizeof(iph_buffer_tcp));
+
+	if (!iph)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = bpf_ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)iphdr_sz))
+		return XDP_DROP;
+
+	bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
+	new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
+	if (!new_eth)
+		return XDP_DROP;
+
+	iph = (struct iphdr *)(new_eth + 1);
+	old_eth = (struct ethhdr *)(iph + 1);
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
+
+	if (new_eth == eth_buffer)
+		bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
+
+	iph->version = 4;
+	iph->ihl = iphdr_sz >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = bpf_htons(payload_len + iphdr_sz);
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph = (__u16 *)iph;
+	for (i = 0; i < iphdr_sz >> 1; i++)
+		csum += *next_iph++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
+{
+	__u8 eth_buffer[ethhdr_sz + ipv6hdr_sz + ethhdr_sz];
+	__u8 ip6h_buffer_tcp[ipv6hdr_sz + tcphdr_sz];
+	__u8 ip6h_buffer_udp[ipv6hdr_sz + udphdr_sz];
+	struct bpf_dynptr new_xdp_ptr;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	__u32 transport_hdr_sz;
+	struct ipv6hdr *ip6h;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
+	__builtin_memset(ip6h_buffer_tcp, 0, sizeof(ip6h_buffer_tcp));
+	__builtin_memset(ip6h_buffer_udp, 0, sizeof(ip6h_buffer_udp));
+
+	if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
+		ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_udp, sizeof(ip6h_buffer_udp));
+	else
+		ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_tcp, sizeof(ip6h_buffer_tcp));
+
+	if (!ip6h)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)ipv6hdr_sz))
+		return XDP_DROP;
+
+	bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
+	new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
+	if (!new_eth)
+		return XDP_DROP;
+
+	ip6h = (struct ipv6hdr *)(new_eth + 1);
+	old_eth = (struct ethhdr *)(ip6h + 1);
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
+
+	if (new_eth == eth_buffer)
+		bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + ipv6hdr_sz);
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	__u8 buffer[ethhdr_sz];
+	struct bpf_dynptr ptr;
+	struct ethhdr *eth;
+	__u16 h_proto;
+
+	__builtin_memset(buffer, 0, sizeof(buffer));
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	eth = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!eth)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == bpf_htons(ETH_P_IP))
+		return handle_ipv4(xdp, &ptr);
+	else if (h_proto == bpf_htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp, &ptr);
+	else
+		return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcp_hdr_options.h

@@ -50,6 +50,7 @@ struct linum_err {
 
 #define TCPOPT_EOL		0
 #define TCPOPT_NOP		1
+#define TCPOPT_MSS		2
 #define TCPOPT_WINDOW		3
 #define TCPOPT_EXP		254