Merge branch 'next' into for-linus

Prepare input updates for 6.14 merge window.

1 files changed, 118 insertions, 26 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3b94ec161e8c..6e63dd3443b9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -203,6 +203,7 @@ enum btf_field_type {
 	BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD,
 	BPF_REFCOUNT   = (1 << 9),
 	BPF_WORKQUEUE  = (1 << 10),
+	BPF_UPTR       = (1 << 11),
 };
 
 typedef void (*btf_dtor_kfunc_t)(void *);
@@ -294,6 +295,7 @@ struct bpf_map {
 	 * same prog type, JITed flag and xdp_has_frags flag.
 	 */
 	struct {
+		const struct btf_type *attach_func_proto;
 		spinlock_t lock;
 		enum bpf_prog_type type;
 		bool jited;
@@ -321,6 +323,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 		return "kptr";
 	case BPF_KPTR_PERCPU:
 		return "percpu_kptr";
+	case BPF_UPTR:
+		return "uptr";
 	case BPF_LIST_HEAD:
 		return "bpf_list_head";
 	case BPF_LIST_NODE:
@@ -349,6 +353,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
 		return sizeof(u64);
 	case BPF_LIST_HEAD:
 		return sizeof(struct bpf_list_head);
@@ -378,6 +383,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
 		return __alignof__(u64);
 	case BPF_LIST_HEAD:
 		return __alignof__(struct bpf_list_head);
@@ -418,6 +424,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -506,6 +513,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src
 	bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
 }
 
+static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src)
+{
+	unsigned long *src_uptr, *dst_uptr;
+	const struct btf_field *field;
+	int i;
+
+	if (!btf_record_has_field(rec, BPF_UPTR))
+		return;
+
+	for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) {
+		if (field->type != BPF_UPTR)
+			continue;
+
+		src_uptr = src + field->offset;
+		dst_uptr = dst + field->offset;
+		swap(*src_uptr, *dst_uptr);
+	}
+}
+
 static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size)
 {
 	u32 curr_off = 0;
@@ -634,6 +660,7 @@ enum bpf_type_flag {
 	 */
 	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
 
+	/* MEM can be uninitialized. */
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
 	/* DYNPTR points to memory local to the bpf program. */
@@ -694,6 +721,18 @@ enum bpf_type_flag {
 	/* DYNPTR points to xdp_buff */
 	DYNPTR_TYPE_XDP		= BIT(16 + BPF_BASE_TYPE_BITS),
 
+	/* Memory must be aligned on some architectures, used in combination with
+	 * MEM_FIXED_SIZE.
+	 */
+	MEM_ALIGNED		= BIT(17 + BPF_BASE_TYPE_BITS),
+
+	/* MEM is being written to, often combined with MEM_UNINIT. Non-presence
+	 * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the
+	 * MEM_UNINIT means that memory needs to be initialized since it is also
+	 * read.
+	 */
+	MEM_WRITE		= BIT(18 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -731,8 +770,6 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
-	ARG_PTR_TO_INT,		/* pointer to int */
-	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_RINGBUF_MEM,	/* pointer to dynamically reserved ringbuf memory */
@@ -743,7 +780,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_STACK,	/* pointer to stack */
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
-	ARG_PTR_TO_KPTR,	/* pointer to referenced kptr */
+	ARG_KPTR_XCHG_DEST,	/* pointer to destination that kptrs are bpf_kptr_xchg'd into */
 	ARG_PTR_TO_DYNPTR,      /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
 	__BPF_ARG_TYPE_MAX,
 
@@ -754,10 +791,10 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
 	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
-	 * all bytes or clear them in error case.
+	/* Pointer to memory does not need to be initialized, since helper function
+	 * fills all bytes or clears them in error case.
 	 */
-	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM,
 	/* Pointer to valid memory of size known at compile time. */
 	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
@@ -807,6 +844,12 @@ struct bpf_func_proto {
 	bool gpl_only;
 	bool pkt_access;
 	bool might_sleep;
+	/* set to true if helper follows contract for llvm
+	 * attribute bpf_fastcall:
+	 * - void functions do not scratch r0
+	 * - functions taking N arguments scratch only registers r1-rN
+	 */
+	bool allow_fastcall;
 	enum bpf_return_type ret_type;
 	union {
 		struct {
@@ -889,10 +932,6 @@ enum bpf_reg_type {
 	 * additional context, assume the value is non-null.
 	 */
 	PTR_TO_BTF_ID,
-	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
-	 * been checked for null. Used primarily to inform the verifier
-	 * an explicit null check is required for this struct.
-	 */
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_ARENA,
 	PTR_TO_BUF,		 /* reg points to a read/write buffer */
@@ -905,6 +944,10 @@ enum bpf_reg_type {
 	PTR_TO_SOCKET_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_SOCKET,
 	PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
 	PTR_TO_TCP_SOCK_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
 	PTR_TO_BTF_ID_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
@@ -919,6 +962,7 @@ static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
  */
 struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
+	bool is_ldsx;
 	union {
 		int ctx_field_size;
 		struct {
@@ -927,6 +971,7 @@ struct bpf_insn_access_aux {
 		};
 	};
 	struct bpf_verifier_log *log; /* for verbose logs */
+	bool is_retval; /* is accessing function return value ? */
 };
 
 static inline void
@@ -965,6 +1010,8 @@ struct bpf_verifier_ops {
 				struct bpf_insn_access_aux *info);
 	int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
 			    const struct bpf_prog *prog);
+	int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog,
+			    s16 ctx_stack_off);
 	int (*gen_ld_abs)(const struct bpf_insn *orig,
 			  struct bpf_insn *insn_buf);
 	u32 (*convert_ctx_access)(enum bpf_access_type type,
@@ -1278,8 +1325,12 @@ void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len);
 bool __bpf_dynptr_is_rdonly(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);
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+			     struct bpf_trampoline *tr,
+			     struct bpf_prog *tgt_prog);
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+			       struct bpf_trampoline *tr,
+			       struct bpf_prog *tgt_prog);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -1351,7 +1402,8 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 				struct bpf_prog *to);
 /* Called only from JIT-enabled code, so there's no need for stubs. */
-void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym);
+void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym);
+void bpf_image_ksym_add(struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
@@ -1360,12 +1412,14 @@ void bpf_jit_uncharge_modmem(u32 size);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
 #else
 static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
-					   struct bpf_trampoline *tr)
+					   struct bpf_trampoline *tr,
+					   struct bpf_prog *tgt_prog)
 {
 	return -ENOTSUPP;
 }
 static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
-					     struct bpf_trampoline *tr)
+					     struct bpf_trampoline *tr,
+					     struct bpf_prog *tgt_prog)
 {
 	return -ENOTSUPP;
 }
@@ -1454,6 +1508,7 @@ struct bpf_prog_aux {
 	u32 max_rdwr_access;
 	struct btf *attach_btf;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
+	void __percpu *priv_stack_ptr;
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
 	struct bpf_trampoline *dst_trampoline;
@@ -1469,7 +1524,14 @@ struct bpf_prog_aux {
 	bool xdp_has_frags;
 	bool exception_cb;
 	bool exception_boundary;
+	bool is_extended; /* true if extended by freplace program */
+	bool jits_use_priv_stack;
+	bool priv_stack_requested;
+	bool changes_pkt_data;
+	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
+	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
+	void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -1584,6 +1646,11 @@ struct bpf_link {
 	enum bpf_link_type type;
 	const struct bpf_link_ops *ops;
 	struct bpf_prog *prog;
+	/* whether BPF link itself has "sleepable" semantics, which can differ
+	 * from underlying BPF program having a "sleepable" semantics, as BPF
+	 * link's semantics is determined by target attach hook
+	 */
+	bool sleepable;
 	/* rcu is used before freeing, work can be used to schedule that
 	 * RCU-based freeing before that, so they never overlap
 	 */
@@ -1600,8 +1667,10 @@ struct bpf_link_ops {
 	 */
 	void (*dealloc)(struct bpf_link *link);
 	/* deallocate link resources callback, called after RCU grace period;
-	 * if underlying BPF program is sleepable we go through tasks trace
-	 * RCU GP and then "classic" RCU GP
+	 * if either the underlying BPF program is sleepable or BPF link's
+	 * target hook is sleepable, we'll go through tasks trace RCU GP and
+	 * then "classic" RCU GP; this need for chaining tasks trace and
+	 * classic RCU GPs is designated by setting bpf_link->sleepable flag
 	 */
 	void (*dealloc_deferred)(struct bpf_link *link);
 	int (*detach)(struct bpf_link *link);
@@ -1795,6 +1864,7 @@ struct bpf_struct_ops_common_value {
 #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
 bool bpf_struct_ops_get(const void *kdata);
 void bpf_struct_ops_put(const void *kdata);
+int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff);
 int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 				       void *value);
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
@@ -1851,6 +1921,10 @@ static inline void bpf_module_put(const void *data, struct module *owner)
 {
 	module_put(owner);
 }
+static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff)
+{
+	return -ENOTSUPP;
+}
 static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
 						     void *key,
 						     void *value)
@@ -2120,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
 			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 	u32 ret = 1;
 
 	might_fault();
+	RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held");
+
+	if (unlikely(!array))
+		return ret;
 
-	rcu_read_lock_trace();
 	migrate_disable();
 
 	run_ctx.is_uprobe = true;
 
-	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
-	if (unlikely(!array))
-		goto out;
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
 	while ((prog = READ_ONCE(item->prog))) {
@@ -2154,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
 			rcu_read_unlock();
 	}
 	bpf_reset_run_ctx(old_run_ctx);
-out:
 	migrate_enable();
-	rcu_read_unlock_trace();
 	return ret;
 }
 
@@ -2227,7 +2298,16 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
 
 struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
-struct bpf_map *__bpf_map_get(struct fd f);
+
+static inline struct bpf_map *__bpf_map_get(struct fd f)
+{
+	if (fd_empty(f))
+		return ERR_PTR(-EBADF);
+	if (unlikely(fd_file(f)->f_op != &bpf_map_fops))
+		return ERR_PTR(-EINVAL);
+	return fd_file(f)->private_data;
+}
+
 void bpf_map_inc(struct bpf_map *map);
 void bpf_map_inc_with_uref(struct bpf_map *map);
 struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref);
@@ -2334,6 +2414,9 @@ int bpf_prog_new_fd(struct bpf_prog *prog);
 
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
+void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+			     const struct bpf_link_ops *ops, struct bpf_prog *prog,
+			     bool sleepable);
 int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
 int bpf_link_settle(struct bpf_link_primer *primer);
 void bpf_link_cleanup(struct bpf_link_primer *primer);
@@ -2689,6 +2772,12 @@ static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 {
 }
 
+static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+					   const struct bpf_link_ops *ops, struct bpf_prog *prog,
+					   bool sleepable)
+{
+}
+
 static inline int bpf_link_prime(struct bpf_link *link,
 				 struct bpf_link_primer *primer)
 {
@@ -3184,7 +3273,9 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
+extern const struct bpf_func_proto bpf_get_stack_sleepable_proto;
 extern const struct bpf_func_proto bpf_get_task_stack_proto;
+extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
 extern const struct bpf_func_proto bpf_get_stack_proto_pe;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
@@ -3192,6 +3283,7 @@ extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto;
+extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
 extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;