bpf: Add bpf_dynptr_slice and bpf_dynptr_slice_rdwr

Two new kfuncs are added, bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
The user must pass in a buffer to store the contents of the data slice
if a direct pointer to the data cannot be obtained.

For skb and xdp type dynptrs, these two APIs are the only way to obtain
a data slice. However, for other types of dynptrs, there is no
difference between bpf_dynptr_slice(_rdwr) and bpf_dynptr_data.

For skb type dynptrs, the data is copied into the user provided buffer
if any of the data is not in the linear portion of the skb. For xdp type
dynptrs, the data is copied into the user provided buffer if the data is
between xdp frags.

If the skb is cloned and a call to bpf_dynptr_data_rdwr is made, then
the skb will be uncloned (see bpf_unclone_prologue()).

Please note that any bpf_dynptr_write() automatically invalidates any prior
data slices of the skb dynptr. This is because the skb may be cloned or
may need to pull its paged buffer into the head. As such, any
bpf_dynptr_write() will automatically have its prior data slices
invalidated, even if the write is to data in the skb head of an uncloned
skb. Please note as well that any other helper calls that change the
underlying packet buffer (eg bpf_skb_pull_data()) invalidates any data
slices of the skb dynptr as well, for the same reasons.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://lore.kernel.org/r/20230301154953.641654-10-joannelkoong@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 123 insertions, 4 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5e42946e53ab..a856896e835a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -759,6 +759,22 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 	}
 }
 
+static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type)
+{
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+		return DYNPTR_TYPE_LOCAL;
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		return DYNPTR_TYPE_RINGBUF;
+	case BPF_DYNPTR_TYPE_SKB:
+		return DYNPTR_TYPE_SKB;
+	case BPF_DYNPTR_TYPE_XDP:
+		return DYNPTR_TYPE_XDP;
+	default:
+		return 0;
+	}
+}
+
 static bool dynptr_type_refcounted(enum bpf_dynptr_type type)
 {
 	return type == BPF_DYNPTR_TYPE_RINGBUF;
@@ -1681,6 +1697,12 @@ static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
 	       reg->type == PTR_TO_PACKET_END;
 }
 
+static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg)
+{
+	return base_type(reg->type) == PTR_TO_MEM &&
+		(reg->type & DYNPTR_TYPE_SKB || reg->type & DYNPTR_TYPE_XDP);
+}
+
 /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
 static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
 				    enum bpf_reg_type which)
@@ -7429,6 +7451,9 @@ static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 
 /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
  * are now invalid, so turn them into unknown SCALAR_VALUE.
+ *
+ * This also applies to dynptr slices belonging to skb and xdp dynptrs,
+ * since these slices point to packet data.
  */
 static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 {
@@ -7436,7 +7461,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 	struct bpf_reg_state *reg;
 
 	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
-		if (reg_is_pkt_pointer_any(reg))
+		if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg))
 			mark_reg_invalid(env, reg);
 	}));
 }
@@ -8688,6 +8713,11 @@ struct bpf_kfunc_call_arg_meta {
 	struct {
 		struct btf_field *field;
 	} arg_rbtree_root;
+	struct {
+		enum bpf_dynptr_type type;
+		u32 id;
+	} initialized_dynptr;
+	u64 mem_size;
 };
 
 static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta)
@@ -8761,6 +8791,19 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf,
 	return __kfunc_param_match_suffix(btf, arg, "__sz");
 }
 
+static bool is_kfunc_arg_const_mem_size(const struct btf *btf,
+					const struct btf_param *arg,
+					const struct bpf_reg_state *reg)
+{
+	const struct btf_type *t;
+
+	t = btf_type_skip_modifiers(btf, arg->type, NULL);
+	if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE)
+		return false;
+
+	return __kfunc_param_match_suffix(btf, arg, "__szk");
+}
+
 static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg)
 {
 	return __kfunc_param_match_suffix(btf, arg, "__k");
@@ -8949,6 +8992,8 @@ enum special_kfunc_type {
 	KF_bpf_rbtree_first,
 	KF_bpf_dynptr_from_skb,
 	KF_bpf_dynptr_from_xdp,
+	KF_bpf_dynptr_slice,
+	KF_bpf_dynptr_slice_rdwr,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -8965,6 +9010,8 @@ BTF_ID(func, bpf_rbtree_add)
 BTF_ID(func, bpf_rbtree_first)
 BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
+BTF_ID(func, bpf_dynptr_slice)
+BTF_ID(func, bpf_dynptr_slice_rdwr)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -8983,6 +9030,8 @@ BTF_ID(func, bpf_rbtree_add)
 BTF_ID(func, bpf_rbtree_first)
 BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
+BTF_ID(func, bpf_dynptr_slice)
+BTF_ID(func, bpf_dynptr_slice_rdwr)
 
 static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -9062,7 +9111,10 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_CALLBACK;
 
-	if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]))
+
+	if (argno + 1 < nargs &&
+	    (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
+	     is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1])))
 		arg_mem_size = true;
 
 	/* This is the catch all argument type of register types supported by
@@ -9745,6 +9797,18 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type);
 			if (ret < 0)
 				return ret;
+
+			if (!(dynptr_arg_type & MEM_UNINIT)) {
+				int id = dynptr_id(env, reg);
+
+				if (id < 0) {
+					verbose(env, "verifier internal error: failed to obtain dynptr id\n");
+					return id;
+				}
+				meta->initialized_dynptr.id = id;
+				meta->initialized_dynptr.type = dynptr_get_type(env, reg);
+			}
+
 			break;
 		}
 		case KF_ARG_PTR_TO_LIST_HEAD:
@@ -9840,14 +9904,33 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				return ret;
 			break;
 		case KF_ARG_PTR_TO_MEM_SIZE:
-			ret = check_kfunc_mem_size_reg(env, &regs[regno + 1], regno + 1);
+		{
+			struct bpf_reg_state *size_reg = &regs[regno + 1];
+			const struct btf_param *size_arg = &args[i + 1];
+
+			ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
 			if (ret < 0) {
 				verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
 				return ret;
 			}
-			/* Skip next '__sz' argument */
+
+			if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) {
+				if (meta->arg_constant.found) {
+					verbose(env, "verifier internal error: only one constant argument permitted\n");
+					return -EFAULT;
+				}
+				if (!tnum_is_const(size_reg->var_off)) {
+					verbose(env, "R%d must be a known constant\n", regno + 1);
+					return -EINVAL;
+				}
+				meta->arg_constant.found = true;
+				meta->arg_constant.value = size_reg->var_off.value;
+			}
+
+			/* Skip next '__sz' or '__szk' argument */
 			i++;
 			break;
+		}
 		case KF_ARG_PTR_TO_CALLBACK:
 			meta->subprogno = reg->subprogno;
 			break;
@@ -10082,6 +10165,42 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
 				regs[BPF_REG_0].btf = desc_btf;
 				regs[BPF_REG_0].btf_id = meta.arg_constant.value;
+			} else if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice] ||
+				   meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) {
+				enum bpf_type_flag type_flag = get_dynptr_type_flag(meta.initialized_dynptr.type);
+
+				mark_reg_known_zero(env, regs, BPF_REG_0);
+
+				if (!meta.arg_constant.found) {
+					verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n");
+					return -EFAULT;
+				}
+
+				regs[BPF_REG_0].mem_size = meta.arg_constant.value;
+
+				/* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */
+				regs[BPF_REG_0].type = PTR_TO_MEM | type_flag;
+
+				if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice]) {
+					regs[BPF_REG_0].type |= MEM_RDONLY;
+				} else {
+					/* this will set env->seen_direct_write to true */
+					if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) {
+						verbose(env, "the prog does not allow writes to packet data\n");
+						return -EINVAL;
+					}
+				}
+
+				if (!meta.initialized_dynptr.id) {
+					verbose(env, "verifier internal error: no dynptr id\n");
+					return -EFAULT;
+				}
+				regs[BPF_REG_0].dynptr_id = meta.initialized_dynptr.id;
+
+				/* we don't need to set BPF_REG_0's ref obj id
+				 * because packet slices are not refcounted (see
+				 * dynptr_type_refcounted)
+				 */
 			} else {
 				verbose(env, "kernel function %s unhandled dynamic return type\n",
 					meta.func_name);