Daniel Borkmann says:

====================
bpf-next 2022-11-25

We've added 101 non-merge commits during the last 11 day(s) which contain
a total of 109 files changed, 8827 insertions(+), 1129 deletions(-).

The main changes are:

1) Support for user defined BPF objects: the use case is to allocate own
   objects, build own object hierarchies and use the building blocks to
   build own data structures flexibly, for example, linked lists in BPF,
   from Kumar Kartikeya Dwivedi.

2) Add bpf_rcu_read_{,un}lock() support for sleepable programs,
   from Yonghong Song.

3) Add support storing struct task_struct objects as kptrs in maps,
   from David Vernet.

4) Batch of BPF map documentation improvements, from Maryam Tahhan
   and Donald Hunter.

5) Improve BPF verifier to propagate nullness information for branches
   of register to register comparisons, from Eduard Zingerman.

6) Fix cgroup BPF iter infra to hold reference on the start cgroup,
   from Hou Tao.

7) Fix BPF verifier to not mark fentry/fexit program arguments as trusted
   given it is not the case for them, from Alexei Starovoitov.

8) Improve BPF verifier's realloc handling to better play along with dynamic
   runtime analysis tools like KASAN and friends, from Kees Cook.

9) Remove legacy libbpf mode support from bpftool,
   from Sahid Orentino Ferdjaoui.

10) Rework zero-len skb redirection checks to avoid potentially breaking
    existing BPF test infra users, from Stanislav Fomichev.

11) Two small refactorings which are independent and have been split out
    of the XDP queueing RFC series, from Toke Høiland-Jørgensen.

12) Fix a memory leak in LSM cgroup BPF selftest, from Wang Yufen.

13) Documentation on how to run BPF CI without patch submission,
    from Daniel Müller.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
====================

Link: https://lore.kernel.org/r/20221125012450.441-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 107 insertions, 47 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c577e4c7c84b..67452103bb86 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -54,6 +54,8 @@ struct cgroup;
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
+extern struct bpf_mem_alloc bpf_global_ma;
+extern bool bpf_global_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -85,7 +87,8 @@ struct bpf_map_ops {
 	int (*map_lookup_and_delete_batch)(struct bpf_map *map,
 					   const union bpf_attr *attr,
 					   union bpf_attr __user *uattr);
-	int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr,
+	int (*map_update_batch)(struct bpf_map *map, struct file *map_file,
+				const union bpf_attr *attr,
 				union bpf_attr __user *uattr);
 	int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
 				union bpf_attr __user *uattr);
@@ -135,7 +138,7 @@ struct bpf_map_ops {
 	struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
 
 	/* Misc helpers.*/
-	int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
+	int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags);
 
 	/* map_meta_equal must be implemented for maps that can be
 	 * used as an inner map.  It is a runtime check to ensure
@@ -165,9 +168,8 @@ struct bpf_map_ops {
 };
 
 enum {
-	/* Support at most 8 pointers in a BTF type */
-	BTF_FIELDS_MAX	      = 10,
-	BPF_MAP_OFF_ARR_MAX   = BTF_FIELDS_MAX,
+	/* Support at most 10 fields in a BTF type */
+	BTF_FIELDS_MAX	   = 10,
 };
 
 enum btf_field_type {
@@ -176,6 +178,8 @@ enum btf_field_type {
 	BPF_KPTR_UNREF = (1 << 2),
 	BPF_KPTR_REF   = (1 << 3),
 	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
+	BPF_LIST_HEAD  = (1 << 4),
+	BPF_LIST_NODE  = (1 << 5),
 };
 
 struct btf_field_kptr {
@@ -185,11 +189,19 @@ struct btf_field_kptr {
 	u32 btf_id;
 };
 
+struct btf_field_list_head {
+	struct btf *btf;
+	u32 value_btf_id;
+	u32 node_offset;
+	struct btf_record *value_rec;
+};
+
 struct btf_field {
 	u32 offset;
 	enum btf_field_type type;
 	union {
 		struct btf_field_kptr kptr;
+		struct btf_field_list_head list_head;
 	};
 };
 
@@ -203,8 +215,8 @@ struct btf_record {
 
 struct btf_field_offs {
 	u32 cnt;
-	u32 field_off[BPF_MAP_OFF_ARR_MAX];
-	u8 field_sz[BPF_MAP_OFF_ARR_MAX];
+	u32 field_off[BTF_FIELDS_MAX];
+	u8 field_sz[BTF_FIELDS_MAX];
 };
 
 struct bpf_map {
@@ -267,6 +279,10 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return "kptr";
+	case BPF_LIST_HEAD:
+		return "bpf_list_head";
+	case BPF_LIST_NODE:
+		return "bpf_list_node";
 	default:
 		WARN_ON_ONCE(1);
 		return "unknown";
@@ -283,6 +299,10 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return sizeof(u64);
+	case BPF_LIST_HEAD:
+		return sizeof(struct bpf_list_head);
+	case BPF_LIST_NODE:
+		return sizeof(struct bpf_list_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -299,6 +319,10 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return __alignof__(u64);
+	case BPF_LIST_HEAD:
+		return __alignof__(struct bpf_list_head);
+	case BPF_LIST_NODE:
+		return __alignof__(struct bpf_list_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -312,16 +336,19 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f
 	return rec->field_mask & type;
 }
 
-static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
+static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj)
 {
-	if (!IS_ERR_OR_NULL(map->record)) {
-		struct btf_field *fields = map->record->fields;
-		u32 cnt = map->record->cnt;
-		int i;
+	int i;
 
-		for (i = 0; i < cnt; i++)
-			memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type));
-	}
+	if (!foffs)
+		return;
+	for (i = 0; i < foffs->cnt; i++)
+		memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]);
+}
+
+static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
+{
+	bpf_obj_init(map->field_offs, dst);
 }
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
@@ -361,7 +388,7 @@ static inline void bpf_obj_memcpy(struct btf_field_offs *foffs,
 		u32 sz = next_off - curr_off;
 
 		memcpy(dst + curr_off, src + curr_off, sz);
-		curr_off = next_off + foffs->field_sz[i];
+		curr_off += foffs->field_sz[i] + sz;
 	}
 	memcpy(dst + curr_off, src + curr_off, size - curr_off);
 }
@@ -391,7 +418,7 @@ static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32
 		u32 sz = next_off - curr_off;
 
 		memset(dst + curr_off, 0, sz);
-		curr_off = next_off + foffs->field_sz[i];
+		curr_off += foffs->field_sz[i] + sz;
 	}
 	memset(dst + curr_off, 0, size - curr_off);
 }
@@ -404,6 +431,9 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
 void bpf_timer_cancel_and_free(void *timer);
+void bpf_list_head_free(const struct btf_field *field, void *list_head,
+			struct bpf_spin_lock *spin_lock);
+
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 
 struct bpf_offload_dev;
@@ -472,10 +502,8 @@ enum bpf_type_flag {
 	 */
 	MEM_RDONLY		= BIT(1 + BPF_BASE_TYPE_BITS),
 
-	/* MEM was "allocated" from a different helper, and cannot be mixed
-	 * with regular non-MEM_ALLOC'ed MEM types.
-	 */
-	MEM_ALLOC		= BIT(2 + BPF_BASE_TYPE_BITS),
+	/* MEM points to BPF ring buffer reservation. */
+	MEM_RINGBUF		= BIT(2 + BPF_BASE_TYPE_BITS),
 
 	/* MEM is in user address space. */
 	MEM_USER		= BIT(3 + BPF_BASE_TYPE_BITS),
@@ -510,6 +538,43 @@ enum bpf_type_flag {
 	/* Size is known at compile time. */
 	MEM_FIXED_SIZE		= BIT(10 + BPF_BASE_TYPE_BITS),
 
+	/* MEM is of an allocated object of type in program BTF. This is used to
+	 * tag PTR_TO_BTF_ID allocated using bpf_obj_new.
+	 */
+	MEM_ALLOC		= BIT(11 + BPF_BASE_TYPE_BITS),
+
+	/* PTR was passed from the kernel in a trusted context, and may be
+	 * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions.
+	 * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above.
+	 * PTR_UNTRUSTED refers to a kptr that was read directly from a map
+	 * without invoking bpf_kptr_xchg(). What we really need to know is
+	 * whether a pointer is safe to pass to a kfunc or BPF helper function.
+	 * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF
+	 * helpers, they do not cover all possible instances of unsafe
+	 * pointers. For example, a pointer that was obtained from walking a
+	 * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the
+	 * fact that it may be NULL, invalid, etc. This is due to backwards
+	 * compatibility requirements, as this was the behavior that was first
+	 * introduced when kptrs were added. The behavior is now considered
+	 * deprecated, and PTR_UNTRUSTED will eventually be removed.
+	 *
+	 * PTR_TRUSTED, on the other hand, is a pointer that the kernel
+	 * guarantees to be valid and safe to pass to kfuncs and BPF helpers.
+	 * For example, pointers passed to tracepoint arguments are considered
+	 * PTR_TRUSTED, as are pointers that are passed to struct_ops
+	 * callbacks. As alluded to above, pointers that are obtained from
+	 * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a
+	 * struct task_struct *task is PTR_TRUSTED, then accessing
+	 * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored
+	 * in a BPF register. Similarly, pointers passed to certain programs
+	 * types such as kretprobes are not guaranteed to be valid, as they may
+	 * for example contain an object that was recently freed.
+	 */
+	PTR_TRUSTED		= BIT(12 + BPF_BASE_TYPE_BITS),
+
+	/* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */
+	MEM_RCU			= BIT(13 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -549,7 +614,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
 	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
-	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
+	ARG_PTR_TO_RINGBUF_MEM,	/* pointer to dynamically reserved ringbuf memory */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
 	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
 	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
@@ -566,7 +631,6 @@ enum bpf_arg_type {
 	ARG_PTR_TO_MEM_OR_NULL		= PTR_MAYBE_NULL | ARG_PTR_TO_MEM,
 	ARG_PTR_TO_CTX_OR_NULL		= PTR_MAYBE_NULL | ARG_PTR_TO_CTX,
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
-	ARG_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
 	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
 	/* pointer to memory does not need to be initialized, helper function must fill
@@ -591,7 +655,7 @@ enum bpf_return_type {
 	RET_PTR_TO_SOCKET,		/* returns a pointer to a socket */
 	RET_PTR_TO_TCP_SOCK,		/* returns a pointer to a tcp_sock */
 	RET_PTR_TO_SOCK_COMMON,		/* returns a pointer to a sock_common */
-	RET_PTR_TO_ALLOC_MEM,		/* returns a pointer to dynamically allocated memory */
+	RET_PTR_TO_MEM,			/* returns a pointer to memory */
 	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 	RET_PTR_TO_BTF_ID,		/* returns a pointer to a btf_id */
 	__BPF_RET_TYPE_MAX,
@@ -601,9 +665,10 @@ enum bpf_return_type {
 	RET_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCKET,
 	RET_PTR_TO_TCP_SOCK_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
 	RET_PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
-	RET_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
-	RET_PTR_TO_DYNPTR_MEM_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
+	RET_PTR_TO_RINGBUF_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM,
+	RET_PTR_TO_DYNPTR_MEM_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_MEM,
 	RET_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
+	RET_PTR_TO_BTF_ID_TRUSTED	= PTR_TRUSTED	 | RET_PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
@@ -620,6 +685,7 @@ struct bpf_func_proto {
 	u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 	bool gpl_only;
 	bool pkt_access;
+	bool might_sleep;
 	enum bpf_return_type ret_type;
 	union {
 		struct {
@@ -758,6 +824,7 @@ struct bpf_prog_ops {
 			union bpf_attr __user *uattr);
 };
 
+struct bpf_reg_state;
 struct bpf_verifier_ops {
 	/* return eBPF function prototype for verification */
 	const struct bpf_func_proto *
@@ -779,9 +846,8 @@ struct bpf_verifier_ops {
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
 	int (*btf_struct_access)(struct bpf_verifier_log *log,
-				 const struct btf *btf,
-				 const struct btf_type *t, int off, int size,
-				 enum bpf_access_type atype,
+				 const struct bpf_reg_state *reg,
+				 int off, int size, enum bpf_access_type atype,
 				 u32 *next_btf_id, enum bpf_type_flag *flag);
 };
 
@@ -1794,7 +1860,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 int  generic_map_lookup_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,
 			      union bpf_attr __user *uattr);
-int  generic_map_update_batch(struct bpf_map *map,
+int  generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 			      const union bpf_attr *attr,
 			      union bpf_attr __user *uattr);
 int  generic_map_delete_batch(struct bpf_map *map,
@@ -2085,9 +2151,9 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size,
 	return btf_ctx_access(off, size, type, prog, info);
 }
 
-int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, int off, int size,
-		      enum bpf_access_type atype,
+int btf_struct_access(struct bpf_verifier_log *log,
+		      const struct bpf_reg_state *reg,
+		      int off, int size, enum bpf_access_type atype,
 		      u32 *next_btf_id, enum bpf_type_flag *flag);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  const struct btf *btf, u32 id, int off,
@@ -2100,22 +2166,11 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   const char *func_name,
 			   struct btf_func_model *m);
 
-struct bpf_kfunc_arg_meta {
-	u64 r0_size;
-	bool r0_rdonly;
-	int ref_obj_id;
-	u32 flags;
-};
-
 struct bpf_reg_state;
 int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 				struct bpf_reg_state *regs);
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
-int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
-			      const struct btf *btf, u32 func_id,
-			      struct bpf_reg_state *regs,
-			      struct bpf_kfunc_arg_meta *meta);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			  struct bpf_reg_state *reg);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
@@ -2338,9 +2393,8 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id)
 }
 
 static inline int btf_struct_access(struct bpf_verifier_log *log,
-				    const struct btf *btf,
-				    const struct btf_type *t, int off, int size,
-				    enum bpf_access_type atype,
+				    const struct bpf_reg_state *reg,
+				    int off, int size, enum bpf_access_type atype,
 				    u32 *next_btf_id, enum bpf_type_flag *flag)
 {
 	return -EACCES;
@@ -2797,4 +2851,10 @@ struct bpf_key {
 	bool has_ref;
 };
 #endif /* CONFIG_KEYS */
+
+static inline bool type_is_alloc(u32 type)
+{
+	return type & MEM_ALLOC;
+}
+
 #endif /* _LINUX_BPF_H */