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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-07-09

We've added 94 non-merge commits during the last 19 day(s) which contain
a total of 125 files changed, 5141 insertions(+), 6701 deletions(-).

The main changes are:

1) Add new way for performing BTF type queries to BPF, from Daniel Müller.

2) Add inlining of calls to bpf_loop() helper when its function callback is
   statically known, from Eduard Zingerman.

3) Implement BPF TCP CC framework usability improvements, from Jörn-Thorben Hinz.

4) Add LSM flavor for attaching per-cgroup BPF programs to existing LSM
   hooks, from Stanislav Fomichev.

5) Remove all deprecated libbpf APIs in prep for 1.0 release, from Andrii Nakryiko.

6) Add benchmarks around local_storage to BPF selftests, from Dave Marchevsky.

7) AF_XDP sample removal (given move to libxdp) and various improvements around AF_XDP
   selftests, from Magnus Karlsson & Maciej Fijalkowski.

8) Add bpftool improvements for memcg probing and bash completion, from Quentin Monnet.

9) Add arm64 JIT support for BPF-2-BPF coupled with tail calls, from Jakub Sitnicki.

10) Sockmap optimizations around throughput of UDP transmissions which have been
    improved by 61%, from Cong Wang.

11) Rework perf's BPF prologue code to remove deprecated functions, from Jiri Olsa.

12) Fix sockmap teardown path to avoid sleepable sk_psock_stop, from John Fastabend.

13) Fix libbpf's cleanup around legacy kprobe/uprobe on error case, from Chuang Wang.

14) Fix libbpf's bpf_helpers.h to work with gcc for the case of its sec/pragma
    macro, from James Hilliard.

15) Fix libbpf's pt_regs macros for riscv to use a0 for RC register, from Yixun Lan.

16) Fix bpftool to show the name of type BPF_OBJ_LINK, from Yafang Shao.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (94 commits)
  selftests/bpf: Fix xdp_synproxy build failure if CONFIG_NF_CONNTRACK=m/n
  bpf: Correctly propagate errors up from bpf_core_composites_match
  libbpf: Disable SEC pragma macro on GCC
  bpf: Check attach_func_proto more carefully in check_return_code
  selftests/bpf: Add test involving restrict type qualifier
  bpftool: Add support for KIND_RESTRICT to gen min_core_btf command
  MAINTAINERS: Add entry for AF_XDP selftests files
  selftests, xsk: Rename AF_XDP testing app
  bpf, docs: Remove deprecated xsk libbpf APIs description
  selftests/bpf: Add benchmark for local_storage RCU Tasks Trace usage
  libbpf, riscv: Use a0 for RC register
  libbpf: Remove unnecessary usdt_rel_ip assignments
  selftests/bpf: Fix few more compiler warnings
  selftests/bpf: Fix bogus uninitialized variable warning
  bpftool: Remove zlib feature test from Makefile
  libbpf: Cleanup the legacy uprobe_event on failed add/attach_event()
  libbpf: Fix wrong variable used in perf_event_uprobe_open_legacy()
  libbpf: Cleanup the legacy kprobe_event on failed add/attach_event()
  selftests/bpf: Add type match test against kernel's task_struct
  selftests/bpf: Add nested type to type based tests
  ...
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/bpf/instruction-set.rst

@@ -351,7 +351,7 @@ These instructions have seven implicit operands:
  * Register R0 is an implicit output which contains the data fetched from
    the packet.
  * Registers R1-R5 are scratch registers that are clobbered after a call to
-   ``BPF_ABS | BPF_LD`` or ``BPF_IND`` | BPF_LD instructions.
+   ``BPF_ABS | BPF_LD`` or ``BPF_IND | BPF_LD`` instructions.
 
 These instructions have an implicit program exit condition as well. When an
 eBPF program is trying to access the data beyond the packet boundary, the

Documentation/bpf/libbpf/libbpf_naming_convention.rst

@@ -9,8 +9,8 @@ described here. It's recommended to follow these conventions whenever a
 new function or type is added to keep libbpf API clean and consistent.
 
 All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
-``btf_dump_``, ``ring_buffer_``, ``perf_buffer_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``btf_dump_``,
+``ring_buffer_``, ``perf_buffer_``.
 
 System call wrappers
 --------------------
@@ -59,15 +59,6 @@ Auxiliary functions and types that don't fit well in any of categories
 described above should have ``libbpf_`` prefix, e.g.
 ``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
 
-AF_XDP functions
--------------------
-
-AF_XDP functions should have an ``xsk_`` prefix, e.g.
-``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
-of both low-level ring access functions and high-level configuration
-functions. These can be mixed and matched. Note that these functions
-are not reentrant for performance reasons.
-
 ABI
 ---
 

MAINTAINERS

@@ -21917,8 +21917,7 @@ F:	include/uapi/linux/if_xdp.h
 F:	include/uapi/linux/xdp_diag.h
 F:	include/net/netns/xdp.h
 F:	net/xdp/
-F:	samples/bpf/xdpsock*
-F:	tools/lib/bpf/xsk*
+F:	tools/testing/selftests/bpf/*xsk*
 
 XEN BLOCK SUBSYSTEM
 M:	Roger Pau Monné <[email protected]>

arch/arm64/net/bpf_jit_comp.c

@@ -246,6 +246,7 @@ static bool is_lsi_offset(int offset, int scale)
 static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
 	const struct bpf_prog *prog = ctx->prog;
+	const bool is_main_prog = prog->aux->func_idx == 0;
 	const u8 r6 = bpf2a64[BPF_REG_6];
 	const u8 r7 = bpf2a64[BPF_REG_7];
 	const u8 r8 = bpf2a64[BPF_REG_8];
@@ -299,7 +300,7 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
-	if (!ebpf_from_cbpf) {
+	if (!ebpf_from_cbpf && is_main_prog) {
 		/* Initialize tail_call_cnt */
 		emit(A64_MOVZ(1, tcc, 0, 0), ctx);
 
@@ -1530,3 +1531,9 @@ void bpf_jit_free_exec(void *addr)
 {
 	return vfree(addr);
 }
+
+/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
+bool bpf_jit_supports_subprog_tailcalls(void)
+{
+	return true;
+}

arch/x86/net/bpf_jit_comp.c

@@ -1771,6 +1771,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
 			   int run_ctx_off, bool save_ret)
 {
+	void (*exit)(struct bpf_prog *prog, u64 start,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit;
+	u64 (*enter)(struct bpf_prog *prog,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter;
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
 	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
@@ -1789,15 +1793,21 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	 */
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
 
+	if (p->aux->sleepable) {
+		enter = __bpf_prog_enter_sleepable;
+		exit = __bpf_prog_exit_sleepable;
+	} else if (p->expected_attach_type == BPF_LSM_CGROUP) {
+		enter = __bpf_prog_enter_lsm_cgroup;
+		exit = __bpf_prog_exit_lsm_cgroup;
+	}
+
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
 	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
-		      __bpf_prog_enter, prog))
-			return -EINVAL;
+	if (emit_call(&prog, enter, prog))
+		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
 
@@ -1841,10 +1851,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
 	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
-		      __bpf_prog_exit, prog))
-			return -EINVAL;
+	if (emit_call(&prog, exit, prog))
+		return -EINVAL;
 
 	*pprog = prog;
 	return 0;
@@ -2492,3 +2500,9 @@ void *bpf_arch_text_copy(void *dst, void *src, size_t len)
 		return ERR_PTR(-EINVAL);
 	return dst;
 }
+
+/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
+bool bpf_jit_supports_subprog_tailcalls(void)
+{
+	return true;
+}

include/linux/bpf-cgroup-defs.h

@@ -10,6 +10,13 @@
 
 struct bpf_prog_array;
 
+#ifdef CONFIG_BPF_LSM
+/* Maximum number of concurrently attachable per-cgroup LSM hooks. */
+#define CGROUP_LSM_NUM 10
+#else
+#define CGROUP_LSM_NUM 0
+#endif
+
 enum cgroup_bpf_attach_type {
 	CGROUP_BPF_ATTACH_TYPE_INVALID = -1,
 	CGROUP_INET_INGRESS = 0,
@@ -35,6 +42,8 @@ enum cgroup_bpf_attach_type {
 	CGROUP_INET4_GETSOCKNAME,
 	CGROUP_INET6_GETSOCKNAME,
 	CGROUP_INET_SOCK_RELEASE,
+	CGROUP_LSM_START,
+	CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1,
 	MAX_CGROUP_BPF_ATTACH_TYPE
 };
 
@@ -47,8 +56,8 @@ struct cgroup_bpf {
 	 * have either zero or one element
 	 * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
 	 */
-	struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
-	u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
+	struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
+	u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
 
 	/* list of cgroup shared storages */
 	struct list_head storages;

include/linux/bpf-cgroup.h

@@ -23,6 +23,13 @@ struct ctl_table;
 struct ctl_table_header;
 struct task_struct;
 
+unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
+				       const struct bpf_insn *insn);
+unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
+					 const struct bpf_insn *insn);
+unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
+					  const struct bpf_insn *insn);
+
 #ifdef CONFIG_CGROUP_BPF
 
 #define CGROUP_ATYPE(type) \
@@ -95,7 +102,7 @@ struct bpf_cgroup_link {
 };
 
 struct bpf_prog_list {
-	struct list_head node;
+	struct hlist_node node;
 	struct bpf_prog *prog;
 	struct bpf_cgroup_link *link;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE];

include/linux/bpf.h

@@ -56,6 +56,8 @@ typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
+typedef unsigned int (*bpf_func_t)(const void *,
+				   const struct bpf_insn *);
 struct bpf_iter_seq_info {
 	const struct seq_operations *seq_ops;
 	bpf_iter_init_seq_priv_t init_seq_private;
@@ -792,6 +794,10 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_
 u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
 				       struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
+					struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
+					struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
 void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
@@ -879,8 +885,7 @@ struct bpf_dispatcher {
 static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
-	unsigned int (*bpf_func)(const void *,
-				 const struct bpf_insn *))
+	bpf_func_t bpf_func)
 {
 	return bpf_func(ctx, insnsi);
 }
@@ -909,8 +914,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
-		unsigned int (*bpf_func)(const void *,			\
-					 const struct bpf_insn *))	\
+		bpf_func_t bpf_func)					\
 	{								\
 		return bpf_func(ctx, insnsi);				\
 	}								\
@@ -921,8 +925,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 	unsigned int bpf_dispatcher_##name##_func(			\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
-		unsigned int (*bpf_func)(const void *,			\
-					 const struct bpf_insn *));	\
+		bpf_func_t bpf_func);					\
 	extern struct bpf_dispatcher bpf_dispatcher_##name;
 #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
 #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
@@ -1061,6 +1064,7 @@ struct bpf_prog_aux {
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
 	u32 verified_insns;
+	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
 #ifdef CONFIG_SECURITY
@@ -1168,6 +1172,11 @@ struct bpf_tramp_link {
 	u64 cookie;
 };
 
+struct bpf_shim_tramp_link {
+	struct bpf_tramp_link link;
+	struct bpf_trampoline *trampoline;
+};
+
 struct bpf_tracing_link {
 	struct bpf_tramp_link link;
 	enum bpf_attach_type attach_type;
@@ -1246,6 +1255,9 @@ struct bpf_dummy_ops {
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 			    union bpf_attr __user *uattr);
 #endif
+int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+				    int cgroup_atype);
+void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog);
 #else
 static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
 {
@@ -1269,6 +1281,14 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
 {
 	return -EINVAL;
 }
+static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+						  int cgroup_atype)
+{
+	return -EOPNOTSUPP;
+}
+static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
+{
+}
 #endif
 
 struct bpf_array {
@@ -1286,6 +1306,9 @@ struct bpf_array {
 #define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 33
 
+/* Maximum number of loops for bpf_loop */
+#define BPF_MAX_LOOPS	BIT(23)
+
 #define BPF_F_ACCESS_MASK	(BPF_F_RDONLY |		\
 				 BPF_F_RDONLY_PROG |	\
 				 BPF_F_WRONLY |		\
@@ -2363,9 +2386,13 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
 extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
+extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto;
+extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
 extern const struct bpf_func_proto bpf_loop_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
+extern const struct bpf_func_proto bpf_set_retval_proto;
+extern const struct bpf_func_proto bpf_get_retval_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -2519,4 +2546,12 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
 void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
 int bpf_dynptr_check_size(u32 size);
 
+#ifdef CONFIG_BPF_LSM
+void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
+void bpf_cgroup_atype_put(int cgroup_atype);
+#else
+static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {}
+static inline void bpf_cgroup_atype_put(int cgroup_atype) {}
+#endif /* CONFIG_BPF_LSM */
+
 #endif /* _LINUX_BPF_H */

include/linux/bpf_lsm.h

@@ -42,6 +42,8 @@ extern const struct bpf_func_proto bpf_inode_storage_get_proto;
 extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
 void bpf_inode_storage_free(struct inode *inode);
 
+void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func);
+
 #else /* !CONFIG_BPF_LSM */
 
 static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
@@ -65,6 +67,11 @@ static inline void bpf_inode_storage_free(struct inode *inode)
 {
 }
 
+static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
+					   bpf_func_t *bpf_func)
+{
+}
+
 #endif /* CONFIG_BPF_LSM */
 
 #endif /* _LINUX_BPF_LSM_H */

include/linux/bpf_verifier.h

@@ -344,6 +344,14 @@ struct bpf_verifier_state_list {
 	int miss_cnt, hit_cnt;
 };
 
+struct bpf_loop_inline_state {
+	int initialized:1; /* set to true upon first entry */
+	int fit_for_inline:1; /* true if callback function is the same
+			       * at each call and flags are always zero
+			       */
+	u32 callback_subprogno; /* valid when fit_for_inline is true */
+};
+
 /* Possible states for alu_state member. */
 #define BPF_ALU_SANITIZE_SRC		(1U << 0)
 #define BPF_ALU_SANITIZE_DST		(1U << 1)
@@ -373,6 +381,10 @@ struct bpf_insn_aux_data {
 				u32 mem_size;	/* mem_size for non-struct typed var */
 			};
 		} btf_var;
+		/* if instruction is a call to bpf_loop this field tracks
+		 * the state of the relevant registers to make decision about inlining
+		 */
+		struct bpf_loop_inline_state loop_inline_state;
 	};
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */