Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-07-08

The following pull-request contains BPF updates for your *net-next* tree.

We've added 102 non-merge commits during the last 28 day(s) which contain
a total of 127 files changed, 4606 insertions(+), 980 deletions(-).

The main changes are:

1) Support resilient split BTF which cuts down on duplication and makes BTF
   as compact as possible wrt BTF from modules, from Alan Maguire & Eduard Zingerman.

2) Add support for dumping kfunc prototypes from BTF which enables both detecting
   as well as dumping compilable prototypes for kfuncs, from Daniel Xu.

3) Batch of s390x BPF JIT improvements to add support for BPF arena and to implement
   support for BPF exceptions, from Ilya Leoshkevich.

4) Batch of riscv64 BPF JIT improvements in particular to add 12-argument support
   for BPF trampolines and to utilize bpf_prog_pack for the latter, from Pu Lehui.

5) Extend BPF test infrastructure to add a CHECKSUM_COMPLETE validation option
   for skbs and add coverage along with it, from Vadim Fedorenko.

6) Inline bpf_get_current_task/_btf() helpers in the arm64 BPF JIT which gives
   a small 1% performance improvement in micro-benchmarks, from Puranjay Mohan.

7) Extend the BPF verifier to track the delta between linked registers in order
   to better deal with recent LLVM code optimizations, from Alexei Starovoitov.

8) Fix bpf_wq_set_callback_impl() kfunc signature where the third argument should
   have been a pointer to the map value, from Benjamin Tissoires.

9) Extend BPF selftests to add regular expression support for test output matching
   and adjust some of the selftest when compiled under gcc, from Cupertino Miranda.

10) Simplify task_file_seq_get_next() and remove an unnecessary loop which always
    iterates exactly once anyway, from Dan Carpenter.

11) Add the capability to offload the netfilter flowtable in XDP layer through
    kfuncs, from Florian Westphal & Lorenzo Bianconi.

12) Various cleanups in networking helpers in BPF selftests to shave off a few
    lines of open-coded functions on client/server handling, from Geliang Tang.

13) Properly propagate prog->aux->tail_call_reachable out of BPF verifier, so
    that x86 JIT does not need to implement detection, from Leon Hwang.

14) Fix BPF verifier to add a missing check_func_arg_reg_off() to prevent an
    out-of-bounds memory access for dynpointers, from Matt Bobrowski.

15) Fix bpf_session_cookie() kfunc to return __u64 instead of long pointer as
    it might lead to problems on 32-bit archs, from Jiri Olsa.

16) Enhance traffic validation and dynamic batch size support in xsk selftests,
    from Tushar Vyavahare.

bpf-next-for-netdev

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (102 commits)
  selftests/bpf: DENYLIST.aarch64: Remove fexit_sleep
  selftests/bpf: amend for wrong bpf_wq_set_callback_impl signature
  bpf: helpers: fix bpf_wq_set_callback_impl signature
  libbpf: Add NULL checks to bpf_object__{prev_map,next_map}
  selftests/bpf: Remove exceptions tests from DENYLIST.s390x
  s390/bpf: Implement exceptions
  s390/bpf: Change seen_reg to a mask
  bpf: Remove unnecessary loop in task_file_seq_get_next()
  riscv, bpf: Optimize stack usage of trampoline
  bpf, devmap: Add .map_alloc_check
  selftests/bpf: Remove arena tests from DENYLIST.s390x
  selftests/bpf: Add UAF tests for arena atomics
  selftests/bpf: Introduce __arena_global
  s390/bpf: Support arena atomics
  s390/bpf: Enable arena
  s390/bpf: Support address space cast instruction
  s390/bpf: Support BPF_PROBE_MEM32
  s390/bpf: Land on the next JITed instruction after exception
  s390/bpf: Introduce pre- and post- probe functions
  s390/bpf: Get rid of get_probe_mem_regno()
  ...
====================

Link: https://patch.msgid.link/20240708221438.10974-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

7 files changed, 101 insertions, 9 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f5c6bc9093a6..4f1d4a97b9d1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2931,8 +2931,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 	return ret;
 }
 
-void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
-			  struct btf_mod_pair *used_btfs, u32 len);
+void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len);
 
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
 						 enum bpf_prog_type type)
@@ -3263,8 +3262,8 @@ 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);
+int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+			       struct bpf_dynptr *ptr);
 #else
 static inline bool bpf_sock_common_is_valid_access(int off, int size,
 						   enum bpf_access_type type,
@@ -3286,8 +3285,8 @@ 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)
+static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+					     struct bpf_dynptr *ptr)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e4070fb02b11..e98ba5a5cf79 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -73,7 +73,10 @@ enum bpf_iter_state {
 struct bpf_reg_state {
 	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
-	/* Fixed part of pointer offset, pointer types only */
+	/*
+	 * Fixed part of pointer offset, pointer types only.
+	 * Or constant delta between "linked" scalars with the same ID.
+	 */
 	s32 off;
 	union {
 		/* valid when type == PTR_TO_PACKET */
@@ -167,6 +170,13 @@ struct bpf_reg_state {
 	 * Similarly to dynptrs, we use ID to track "belonging" of a reference
 	 * to a specific instance of bpf_iter.
 	 */
+	/*
+	 * Upper bit of ID is used to remember relationship between "linked"
+	 * registers. Example:
+	 * r1 = r2;    both will have r1->id == r2->id == N
+	 * r1 += 10;   r1->id == N | BPF_ADD_CONST and r1->off == 10
+	 */
+#define BPF_ADD_CONST (1U << 31)
 	u32 id;
 	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
 	 * from a pointer-cast helper, bpf_sk_fullsock() and
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 7c3e40c3295e..cffb43133c68 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -140,6 +140,7 @@ extern const struct file_operations btf_fops;
 const char *btf_get_name(const struct btf *btf);
 void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
+const struct btf_header *btf_header(const struct btf *btf);
 int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz);
 struct btf *btf_get_by_fd(int fd);
 int btf_get_info_by_fd(const struct btf *btf,
@@ -212,8 +213,10 @@ int btf_get_fd_by_id(u32 id);
 u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
 bool btf_is_module(const struct btf *btf);
+bool btf_is_vmlinux(const struct btf *btf);
 struct module *btf_try_get_module(const struct btf *btf);
 u32 btf_nr_types(const struct btf *btf);
+struct btf *btf_base_btf(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
@@ -339,6 +342,11 @@ static inline u8 btf_int_offset(const struct btf_type *t)
 	return BTF_INT_OFFSET(*(u32 *)(t + 1));
 }
 
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
 static inline bool btf_type_is_scalar(const struct btf_type *t)
 {
 	return btf_type_is_int(t) || btf_type_is_enum(t);
@@ -478,6 +486,11 @@ static inline struct btf_param *btf_params(const struct btf_type *t)
 	return (struct btf_param *)(t + 1);
 }
 
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
+
 static inline int btf_id_cmp_func(const void *a, const void *b)
 {
 	const int *pa = a, *pb = b;
@@ -515,9 +528,38 @@ static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *
 }
 #endif
 
+enum btf_field_iter_kind {
+	BTF_FIELD_ITER_IDS,
+	BTF_FIELD_ITER_STRS,
+};
+
+struct btf_field_desc {
+	/* once-per-type offsets */
+	int t_off_cnt, t_offs[2];
+	/* member struct size, or zero, if no members */
+	int m_sz;
+	/* repeated per-member offsets */
+	int m_off_cnt, m_offs[1];
+};
+
+struct btf_field_iter {
+	struct btf_field_desc desc;
+	void *p;
+	int m_idx;
+	int off_idx;
+	int vlen;
+};
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids);
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+			enum btf_field_iter_kind iter_kind);
+__u32 *btf_field_iter_next(struct btf_field_iter *it);
+
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
+const char *btf_str_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);
 u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id,
@@ -531,6 +573,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
+bool btf_is_projection_of(const char *pname, const char *tname);
 bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 			   const struct btf_type *t, enum bpf_prog_type prog_type,
 			   int arg);
@@ -543,6 +586,28 @@ static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 {
 	return NULL;
 }
+
+static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
+{
+}
+
+static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf,
+			       __u32 **map_ids)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+				      enum btf_field_iter_kind iter_kind)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline __u32 *btf_field_iter_next(struct btf_field_iter *it)
+{
+	return NULL;
+}
+
 static inline const char *btf_name_by_offset(const struct btf *btf,
 					     u32 offset)
 {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0bbd2585e6de..b6672ff61407 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1234,8 +1234,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image,
 			  struct bpf_binary_header **rw_hdr,
 			  u8 **rw_image,
 			  bpf_jit_fill_hole_t bpf_fill_ill_insns);
-int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
-				 struct bpf_binary_header *ro_header,
+int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header,
 				 struct bpf_binary_header *rw_header);
 void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 			      struct bpf_binary_header *rw_header);
diff --git a/include/linux/module.h b/include/linux/module.h
index 330ffb59efe5..4213d8993cd8 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -509,7 +509,9 @@ struct module {
 #endif
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 	unsigned int btf_data_size;
+	unsigned int btf_base_data_size;
 	void *btf_data;
+	void *btf_base_data;
 #endif
 #ifdef CONFIG_JUMP_LABEL
 	struct jump_entry *jump_entries;
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 9abb7ee40d72..b63d53bb9dd6 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -305,11 +305,26 @@ struct flow_ports {
 	__be16 source, dest;
 };
 
+struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev);
+int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable,
+			      struct net_device *dev,
+			      enum flow_block_command cmd);
+
 unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 				     const struct nf_hook_state *state);
 unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				       const struct nf_hook_state *state);
 
+#if (IS_BUILTIN(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+    (IS_MODULE(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES))
+extern int nf_flow_register_bpf(void);
+#else
+static inline int nf_flow_register_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #define MODULE_ALIAS_NF_FLOWTABLE(family)	\
 	MODULE_ALIAS("nf-flowtable-" __stringify(family))
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 25ea393cf084..35bcf52dbc65 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1425,6 +1425,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {