bpf: Implement verifier support for rqspinlock

kkdwvd · Alexei Starovoitov · commit 0de2046137f9 · 2025-03-19T08:03:06.000-07:00
Introduce verifier-side support for rqspinlock kfuncs. The first step is allowing bpf_res_spin_lock type to be defined in map values and allocated objects, so BTF-side is updated with a new BPF_RES_SPIN_LOCK field to recognize and validate. Any object cannot have both bpf_spin_lock and bpf_res_spin_lock, only one of them (and at most one of them per-object, like before) must be present. The bpf_res_spin_lock can also be used to protect objects that require lock protection for their kfuncs, like BPF rbtree and linked list. The verifier plumbing to simulate success and failure cases when calling the kfuncs is done by pushing a new verifier state to the verifier state stack which will verify the failure case upon calling the kfunc. The path where success is indicated creates all lock reference state and IRQ state (if necessary for irqsave variants). In the case of failure, the state clears the registers r0-r5, sets the return value, and skips kfunc processing, proceeding to the next instruction. When marking the return value for success case, the value is marked as 0, and for the failure case as [-MAX_ERRNO, -1]. Then, in the program, whenever user checks the return value as 'if (ret)' or 'if (ret < 0)' the verifier never traverses such branches for success cases, and would be aware that the lock is not held in such cases. We push the kfunc state in check_kfunc_call whenever rqspinlock kfuncs are invoked. We introduce a kfunc_class state to avoid mixing lock irqrestore kfuncs with IRQ state created by bpf_local_irq_save. With all this infrastructure, these kfuncs become usable in programs while satisfying all safety properties required by the kernel. Acked-by: Eduard Zingerman <eddyz87@gmail.com> Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20250316040541.108729-24-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
@@ -205,6 +205,7 @@ enum btf_field_type {
 	BPF_REFCOUNT   = (1 << 9),
 	BPF_WORKQUEUE  = (1 << 10),
 	BPF_UPTR       = (1 << 11),
+	BPF_RES_SPIN_LOCK = (1 << 12),
 };
 
 typedef void (*btf_dtor_kfunc_t)(void *);
@@ -240,6 +241,7 @@ struct btf_record {
 	u32 cnt;
 	u32 field_mask;
 	int spin_lock_off;
+	int res_spin_lock_off;
 	int timer_off;
 	int wq_off;
 	int refcount_off;
@@ -315,6 +317,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return "bpf_spin_lock";
+	case BPF_RES_SPIN_LOCK:
+		return "bpf_res_spin_lock";
 	case BPF_TIMER:
 		return "bpf_timer";
 	case BPF_WORKQUEUE:
@@ -347,6 +351,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return sizeof(struct bpf_spin_lock);
+	case BPF_RES_SPIN_LOCK:
+		return sizeof(struct bpf_res_spin_lock);
 	case BPF_TIMER:
 		return sizeof(struct bpf_timer);
 	case BPF_WORKQUEUE:
@@ -377,6 +383,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return __alignof__(struct bpf_spin_lock);
+	case BPF_RES_SPIN_LOCK:
+		return __alignof__(struct bpf_res_spin_lock);
 	case BPF_TIMER:
 		return __alignof__(struct bpf_timer);
 	case BPF_WORKQUEUE:
@@ -420,6 +428,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
 	case BPF_RB_ROOT:
 		/* RB_ROOT_CACHED 0-inits, no need to do anything after memset */
 	case BPF_SPIN_LOCK:
+	case BPF_RES_SPIN_LOCK:
 	case BPF_TIMER:
 	case BPF_WORKQUEUE:
 	case BPF_KPTR_UNREF:
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
@@ -115,6 +115,14 @@ struct bpf_reg_state {
 			int depth:30;
 		} iter;
 
+		/* For irq stack slots */
+		struct {
+			enum {
+				IRQ_NATIVE_KFUNC,
+				IRQ_LOCK_KFUNC,
+			} kfunc_class;
+		} irq;
+
 		/* Max size from any of the above. */
 		struct {
 			unsigned long raw1;
@@ -255,9 +263,11 @@ struct bpf_reference_state {
 	 * default to pointer reference on zero initialization of a state.
 	 */
 	enum ref_state_type {
-		REF_TYPE_PTR	= 1,
-		REF_TYPE_IRQ	= 2,
-		REF_TYPE_LOCK	= 3,
+		REF_TYPE_PTR		= (1 << 1),
+		REF_TYPE_IRQ		= (1 << 2),
+		REF_TYPE_LOCK		= (1 << 3),
+		REF_TYPE_RES_LOCK 	= (1 << 4),
+		REF_TYPE_RES_LOCK_IRQ	= (1 << 5),
 	} type;
 	/* Track each reference created with a unique id, even if the same
 	 * instruction creates the reference multiple times (eg, via CALL).
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
@@ -3481,6 +3481,15 @@ static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_
 			goto end;
 		}
 	}
+	if (field_mask & BPF_RES_SPIN_LOCK) {
+		if (!strcmp(name, "bpf_res_spin_lock")) {
+			if (*seen_mask & BPF_RES_SPIN_LOCK)
+				return -E2BIG;
+			*seen_mask |= BPF_RES_SPIN_LOCK;
+			type = BPF_RES_SPIN_LOCK;
+			goto end;
+		}
+	}
 	if (field_mask & BPF_TIMER) {
 		if (!strcmp(name, "bpf_timer")) {
 			if (*seen_mask & BPF_TIMER)
@@ -3659,6 +3668,7 @@ static int btf_find_field_one(const struct btf *btf,
 
 	switch (field_type) {
 	case BPF_SPIN_LOCK:
+	case BPF_RES_SPIN_LOCK:
 	case BPF_TIMER:
 	case BPF_WORKQUEUE:
 	case BPF_LIST_NODE:
@@ -3952,6 +3962,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 		return ERR_PTR(-ENOMEM);
 
 	rec->spin_lock_off = -EINVAL;
+	rec->res_spin_lock_off = -EINVAL;
 	rec->timer_off = -EINVAL;
 	rec->wq_off = -EINVAL;
 	rec->refcount_off = -EINVAL;
@@ -3979,6 +3990,11 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 			/* Cache offset for faster lookup at runtime */
 			rec->spin_lock_off = rec->fields[i].offset;
 			break;
+		case BPF_RES_SPIN_LOCK:
+			WARN_ON_ONCE(rec->spin_lock_off >= 0);
+			/* Cache offset for faster lookup at runtime */
+			rec->res_spin_lock_off = rec->fields[i].offset;
+			break;
 		case BPF_TIMER:
 			WARN_ON_ONCE(rec->timer_off >= 0);
 			/* Cache offset for faster lookup at runtime */
@@ -4022,9 +4038,15 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 		rec->cnt++;
 	}
 
+	if (rec->spin_lock_off >= 0 && rec->res_spin_lock_off >= 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
 	/* bpf_{list_head, rb_node} require bpf_spin_lock */
 	if ((btf_record_has_field(rec, BPF_LIST_HEAD) ||
-	     btf_record_has_field(rec, BPF_RB_ROOT)) && rec->spin_lock_off < 0) {
+	     btf_record_has_field(rec, BPF_RB_ROOT)) &&
+		 (rec->spin_lock_off < 0 && rec->res_spin_lock_off < 0)) {
 		ret = -EINVAL;
 		goto end;
 	}
@@ -5637,7 +5659,7 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
 
 		type = &tab->types[tab->cnt];
 		type->btf_id = i;
-		record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE |
+		record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE |
 						  BPF_RB_ROOT | BPF_RB_NODE | BPF_REFCOUNT |
 						  BPF_KPTR, t->size);
 		/* The record cannot be unset, treat it as an error if so */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
@@ -648,6 +648,7 @@ void btf_record_free(struct btf_record *rec)
 		case BPF_RB_ROOT:
 		case BPF_RB_NODE:
 		case BPF_SPIN_LOCK:
+		case BPF_RES_SPIN_LOCK:
 		case BPF_TIMER:
 		case BPF_REFCOUNT:
 		case BPF_WORKQUEUE:
@@ -700,6 +701,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
 		case BPF_RB_ROOT:
 		case BPF_RB_NODE:
 		case BPF_SPIN_LOCK:
+		case BPF_RES_SPIN_LOCK:
 		case BPF_TIMER:
 		case BPF_REFCOUNT:
 		case BPF_WORKQUEUE:
@@ -777,6 +779,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 
 		switch (fields[i].type) {
 		case BPF_SPIN_LOCK:
+		case BPF_RES_SPIN_LOCK:
 			break;
 		case BPF_TIMER:
 			bpf_timer_cancel_and_free(field_ptr);
@@ -1212,7 +1215,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
 		return -EINVAL;
 
 	map->record = btf_parse_fields(btf, value_type,
-				       BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
+				       BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
 				       BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR,
 				       map->value_size);
 	if (!IS_ERR_OR_NULL(map->record)) {
@@ -1231,6 +1234,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
 			case 0:
 				continue;
 			case BPF_SPIN_LOCK:
+			case BPF_RES_SPIN_LOCK:
 				if (map->map_type != BPF_MAP_TYPE_HASH &&
 				    map->map_type != BPF_MAP_TYPE_ARRAY &&
 				    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
