bpf: Implement verifier support for rqspinlock

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>

1 files changed, 24 insertions, 2 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 519e3f5e9c10..f7a2bfb0c11a 100644
--- 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 */