bpf: Allow storing unreferenced kptr in map

This commit introduces a new pointer type 'kptr' which can be embedded
in a map value to hold a PTR_TO_BTF_ID stored by a BPF program during
its invocation. When storing such a kptr, BPF program's PTR_TO_BTF_ID
register must have the same type as in the map value's BTF, and loading
a kptr marks the destination register as PTR_TO_BTF_ID with the correct
kernel BTF and BTF ID.

Such kptr are unreferenced, i.e. by the time another invocation of the
BPF program loads this pointer, the object which the pointer points to
may not longer exist. Since PTR_TO_BTF_ID loads (using BPF_LDX) are
patched to PROBE_MEM loads by the verifier, it would safe to allow user
to still access such invalid pointer, but passing such pointers into
BPF helpers and kfuncs should not be permitted. A future patch in this
series will close this gap.

The flexibility offered by allowing programs to dereference such invalid
pointers while being safe at runtime frees the verifier from doing
complex lifetime tracking. As long as the user may ensure that the
object remains valid, it can ensure data read by it from the kernel
object is valid.

The user indicates that a certain pointer must be treated as kptr
capable of accepting stores of PTR_TO_BTF_ID of a certain type, by using
a BTF type tag 'kptr' on the pointed to type of the pointer. Then, this
information is recorded in the object BTF which will be passed into the
kernel by way of map's BTF information. The name and kind from the map
value BTF is used to look up the in-kernel type, and the actual BTF and
BTF ID is recorded in the map struct in a new kptr_off_tab member. For
now, only storing pointers to structs is permitted.

An example of this specification is shown below:

	#define __kptr __attribute__((btf_type_tag("kptr")))

	struct map_value {
		...
		struct task_struct __kptr *task;
		...
	};

Then, in a BPF program, user may store PTR_TO_BTF_ID with the type
task_struct into the map, and then load it later.

Note that the destination register is marked PTR_TO_BTF_ID_OR_NULL, as
the verifier cannot know whether the value is NULL or not statically, it
must treat all potential loads at that map value offset as loading a
possibly NULL pointer.

Only BPF_LDX, BPF_STX, and BPF_ST (with insn->imm = 0 to denote NULL)
are allowed instructions that can access such a pointer. On BPF_LDX, the
destination register is updated to be a PTR_TO_BTF_ID, and on BPF_STX,
it is checked whether the source register type is a PTR_TO_BTF_ID with
same BTF type as specified in the map BTF. The access size must always
be BPF_DW.

For the map in map support, the kptr_off_tab for outer map is copied
from the inner map's kptr_off_tab. It was chosen to do a deep copy
instead of introducing a refcount to kptr_off_tab, because the copy only
needs to be done when paramterizing using inner_map_fd in the map in map
case, hence would be unnecessary for all other users.

It is not permitted to use MAP_FREEZE command and mmap for BPF map
having kptrs, similar to the bpf_timer case. A kptr also requires that
BPF program has both read and write access to the map (hence both
BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG are disallowed).

Note that check_map_access must be called from both
check_helper_mem_access and for the BPF instructions, hence the kptr
check must distinguish between ACCESS_DIRECT and ACCESS_HELPER, and
reject ACCESS_HELPER cases. We rename stack_access_src to bpf_access_src
and reuse it for this purpose.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-2-memxor@gmail.com

1 files changed, 146 insertions, 21 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 0493310d981f..563ac61e6d6b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3166,9 +3166,16 @@ static void btf_struct_log(struct btf_verifier_env *env,
 enum btf_field_type {
 	BTF_FIELD_SPIN_LOCK,
 	BTF_FIELD_TIMER,
+	BTF_FIELD_KPTR,
+};
+
+enum {
+	BTF_FIELD_IGNORE = 0,
+	BTF_FIELD_FOUND  = 1,
 };
 
 struct btf_field_info {
+	u32 type_id;
 	u32 off;
 };
 
@@ -3176,29 +3183,57 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
 			   u32 off, int sz, struct btf_field_info *info)
 {
 	if (!__btf_type_is_struct(t))
-		return 0;
+		return BTF_FIELD_IGNORE;
 	if (t->size != sz)
-		return 0;
-	if (info->off != -ENOENT)
-		/* only one such field is allowed */
-		return -E2BIG;
+		return BTF_FIELD_IGNORE;
 	info->off = off;
-	return 0;
+	return BTF_FIELD_FOUND;
+}
+
+static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
+			 u32 off, int sz, struct btf_field_info *info)
+{
+	u32 res_id;
+
+	/* For PTR, sz is always == 8 */
+	if (!btf_type_is_ptr(t))
+		return BTF_FIELD_IGNORE;
+	t = btf_type_by_id(btf, t->type);
+
+	if (!btf_type_is_type_tag(t))
+		return BTF_FIELD_IGNORE;
+	/* Reject extra tags */
+	if (btf_type_is_type_tag(btf_type_by_id(btf, t->type)))
+		return -EINVAL;
+	if (strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
+		return -EINVAL;
+
+	/* Get the base type */
+	t = btf_type_skip_modifiers(btf, t->type, &res_id);
+	/* Only pointer to struct is allowed */
+	if (!__btf_type_is_struct(t))
+		return -EINVAL;
+
+	info->type_id = res_id;
+	info->off = off;
+	return BTF_FIELD_FOUND;
 }
 
 static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t,
 				 const char *name, int sz, int align,
 				 enum btf_field_type field_type,
-				 struct btf_field_info *info)
+				 struct btf_field_info *info, int info_cnt)
 {
 	const struct btf_member *member;
+	struct btf_field_info tmp;
+	int ret, idx = 0;
 	u32 i, off;
 
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								    member->type);
 
-		if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
+		if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
 			continue;
 
 		off = __btf_member_bit_offset(t, member);
@@ -3212,20 +3247,38 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 		switch (field_type) {
 		case BTF_FIELD_SPIN_LOCK:
 		case BTF_FIELD_TIMER:
-			return btf_find_struct(btf, member_type, off, sz, info);
+			ret = btf_find_struct(btf, member_type, off, sz,
+					      idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
+		case BTF_FIELD_KPTR:
+			ret = btf_find_kptr(btf, member_type, off, sz,
+					    idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
+
+		if (ret == BTF_FIELD_IGNORE)
+			continue;
+		if (idx >= info_cnt)
+			return -E2BIG;
+		++idx;
 	}
-	return 0;
+	return idx;
 }
 
 static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 				const char *name, int sz, int align,
 				enum btf_field_type field_type,
-				struct btf_field_info *info)
+				struct btf_field_info *info, int info_cnt)
 {
 	const struct btf_var_secinfo *vsi;
+	struct btf_field_info tmp;
+	int ret, idx = 0;
 	u32 i, off;
 
 	for_each_vsi(i, t, vsi) {
@@ -3234,7 +3287,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 
 		off = vsi->offset;
 
-		if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
+		if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
 			continue;
 		if (vsi->size != sz)
 			continue;
@@ -3244,17 +3297,33 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 		switch (field_type) {
 		case BTF_FIELD_SPIN_LOCK:
 		case BTF_FIELD_TIMER:
-			return btf_find_struct(btf, var_type, off, sz, info);
+			ret = btf_find_struct(btf, var_type, off, sz,
+					      idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
+		case BTF_FIELD_KPTR:
+			ret = btf_find_kptr(btf, var_type, off, sz,
+					    idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
+
+		if (ret == BTF_FIELD_IGNORE)
+			continue;
+		if (idx >= info_cnt)
+			return -E2BIG;
+		++idx;
 	}
-	return 0;
+	return idx;
 }
 
 static int btf_find_field(const struct btf *btf, const struct btf_type *t,
 			  enum btf_field_type field_type,
-			  struct btf_field_info *info)
+			  struct btf_field_info *info, int info_cnt)
 {
 	const char *name;
 	int sz, align;
@@ -3270,14 +3339,19 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t,
 		sz = sizeof(struct bpf_timer);
 		align = __alignof__(struct bpf_timer);
 		break;
+	case BTF_FIELD_KPTR:
+		name = NULL;
+		sz = sizeof(u64);
+		align = 8;
+		break;
 	default:
 		return -EFAULT;
 	}
 
 	if (__btf_type_is_struct(t))
-		return btf_find_struct_field(btf, t, name, sz, align, field_type, info);
+		return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt);
 	else if (btf_type_is_datasec(t))
-		return btf_find_datasec_var(btf, t, name, sz, align, field_type, info);
+		return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt);
 	return -EINVAL;
 }
 
@@ -3287,26 +3361,77 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t,
  */
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
 {
-	struct btf_field_info info = { .off = -ENOENT };
+	struct btf_field_info info;
 	int ret;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info);
+	ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1);
 	if (ret < 0)
 		return ret;
+	if (!ret)
+		return -ENOENT;
 	return info.off;
 }
 
 int btf_find_timer(const struct btf *btf, const struct btf_type *t)
 {
-	struct btf_field_info info = { .off = -ENOENT };
+	struct btf_field_info info;
 	int ret;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info);
+	ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1);
 	if (ret < 0)
 		return ret;
+	if (!ret)
+		return -ENOENT;
 	return info.off;
 }
 
+struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
+					  const struct btf_type *t)
+{
+	struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX];
+	struct bpf_map_value_off *tab;
+	struct btf *kernel_btf = NULL;
+	int ret, i, nr_off;
+
+	ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr));
+	if (ret < 0)
+		return ERR_PTR(ret);
+	if (!ret)
+		return NULL;
+
+	nr_off = ret;
+	tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN);
+	if (!tab)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < nr_off; i++) {
+		const struct btf_type *t;
+		s32 id;
+
+		/* Find type in map BTF, and use it to look up the matching type
+		 * in vmlinux or module BTFs, by name and kind.
+		 */
+		t = btf_type_by_id(btf, info_arr[i].type_id);
+		id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info),
+				     &kernel_btf);
+		if (id < 0) {
+			ret = id;
+			goto end;
+		}
+
+		tab->off[i].offset = info_arr[i].off;
+		tab->off[i].kptr.btf_id = id;
+		tab->off[i].kptr.btf = kernel_btf;
+	}
+	tab->nr_off = nr_off;
+	return tab;
+end:
+	while (i--)
+		btf_put(tab->off[i].kptr.btf);
+	kfree(tab);
+	return ERR_PTR(ret);
+}
+
 static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
 			      u32 type_id, void *data, u8 bits_offset,
 			      struct btf_show *show)