bpf: Add kfunc bpf_rcu_read_lock/unlock()

Add two kfunc's bpf_rcu_read_lock() and bpf_rcu_read_unlock(). These two kfunc's
can be used for all program types. The following is an example about how
rcu pointer are used w.r.t. bpf_rcu_read_lock()/bpf_rcu_read_unlock().

  struct task_struct {
    ...
    struct task_struct              *last_wakee;
    struct task_struct __rcu        *real_parent;
    ...
  };

Let us say prog does 'task = bpf_get_current_task_btf()' to get a
'task' pointer. The basic rules are:
  - 'real_parent = task->real_parent' should be inside bpf_rcu_read_lock
    region. This is to simulate rcu_dereference() operation. The
    'real_parent' is marked as MEM_RCU only if (1). task->real_parent is
    inside bpf_rcu_read_lock region, and (2). task is a trusted ptr. So
    MEM_RCU marked ptr can be 'trusted' inside the bpf_rcu_read_lock region.
  - 'last_wakee = real_parent->last_wakee' should be inside bpf_rcu_read_lock
    region since it tries to access rcu protected memory.
  - the ptr 'last_wakee' will be marked as PTR_UNTRUSTED since in general
    it is not clear whether the object pointed by 'last_wakee' is valid or
    not even inside bpf_rcu_read_lock region.

The verifier will reset all rcu pointer register states to untrusted
at bpf_rcu_read_unlock() kfunc call site, so any such rcu pointer
won't be trusted any more outside the bpf_rcu_read_lock() region.

The current implementation does not support nested rcu read lock
region in the prog.
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221124053217.2373910-1-yhs@fb.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -572,6 +572,9 @@ enum bpf_type_flag {
 	 */
 	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,
 };

include/linux/bpf_verifier.h

@@ -344,6 +344,7 @@ struct bpf_verifier_state {
 		u32 id;
 	} active_lock;
 	bool speculative;
+	bool active_rcu_lock;
 
 	/* first and last insn idx of this verifier state */
 	u32 first_insn_idx;
@@ -445,6 +446,7 @@ struct bpf_insn_aux_data {
 	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
 	bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
 	bool zext_dst; /* this insn zero extends dst reg */
+	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
 	u8 alu_state; /* used in combination with alu_limit */
 
 	/* below fields are initialized once */
@@ -534,6 +536,7 @@ struct bpf_verifier_env {
 	bool bypass_spec_v1;
 	bool bypass_spec_v4;
 	bool seen_direct_write;
+	bool rcu_tag_supported;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
@@ -680,7 +683,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	}
 }
 
-#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED)
+#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | MEM_RCU | PTR_TRUSTED)
 
 static inline bool bpf_type_has_unsafe_modifiers(u32 type)
 {

kernel/bpf/btf.c

@@ -6238,6 +6238,9 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 				/* check __percpu tag */
 				if (strcmp(tag_value, "percpu") == 0)
 					tmp_flag = MEM_PERCPU;
+				/* check __rcu tag */
+				if (strcmp(tag_value, "rcu") == 0)
+					tmp_flag = MEM_RCU;
 			}
 
 			stype = btf_type_skip_modifiers(btf, mtype->type, &id);

kernel/bpf/helpers.c

@@ -1990,6 +1990,16 @@ void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k)
 	return obj__ign;
 }
 
+void bpf_rcu_read_lock(void)
+{
+	rcu_read_lock();
+}
+
+void bpf_rcu_read_unlock(void)
+{
+	rcu_read_unlock();
+}
+
 __diag_pop();
 
 BTF_SET8_START(generic_btf_ids)
@@ -2031,6 +2041,8 @@ BTF_ID(func, bpf_cgroup_release)
 BTF_SET8_START(common_btf_ids)
 BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx)
 BTF_ID_FLAGS(func, bpf_rdonly_cast)
+BTF_ID_FLAGS(func, bpf_rcu_read_lock)
+BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
 BTF_SET8_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {