diff mbox series

[bpf-next,v3,11/24] bpf: Recognize bpf_{spin_lock,list_head,list_node} in local kptrs

Message ID 20221102202658.963008-12-memxor@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Local kptrs, BPF linked lists | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-1 pending Logs for ${{ matrix.test }} on ${{ matrix.arch }} with ${{ matrix.toolchain }}
bpf/vmtest-bpf-next-VM_Test-2 pending Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 fail Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-4 fail Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 fail Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-6 success Logs for llvm-toolchain
bpf/vmtest-bpf-next-VM_Test-7 success Logs for set-matrix
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count fail Series longer than 15 patches (and no cover letter)
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit fail Errors and warnings before: 1341 this patch: 1374
netdev/cc_maintainers warning 8 maintainers not CCed: sdf@google.com john.fastabend@gmail.com yhs@fb.com haoluo@google.com jolsa@kernel.org kpsingh@kernel.org song@kernel.org martin.lau@linux.dev
netdev/build_clang success Errors and warnings before: 159 this patch: 159
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn fail Errors and warnings before: 1352 this patch: 1367
netdev/checkpatch warning CHECK: Comparison to NULL could be written "bsearch" CHECK: Please use a blank line after function/struct/union/enum declarations WARNING: Missing a blank line after declarations WARNING: labels should not be indented WARNING: line length of 101 exceeds 80 columns WARNING: line length of 103 exceeds 80 columns WARNING: line length of 106 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: line length of 93 exceeds 80 columns WARNING: line length of 94 exceeds 80 columns WARNING: static const char * array should probably be static const char * const
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Kumar Kartikeya Dwivedi Nov. 2, 2022, 8:26 p.m. UTC
Allow specifying bpf_spin_lock, bpf_list_head, bpf_list_node fields in a
local kptr.

A bpf_list_head allows implementing map-in-map style use cases, where
local kptr with bpf_list_head is linked into a list in a map value. This
would require embedding a bpf_list_node, support for which is also
included.

Lastly, while we strictly don't require to hold a bpf_spin_lock while
manipulating the bpf_list_head of a local kptr, as when have access to
it, we have complete ownership of the object, the locking constraint is
still kept and may be conditionally lifted in the future.

Note that the specification of such types can be done just like map
values, e.g.:

struct bar {
	struct bpf_list_node node;
};

struct foo {
	struct bpf_spin_lock lock;
	struct bpf_list_head head __contains(bar, node);
	struct bpf_list_node node;
};

struct map_value {
	struct bpf_spin_lock lock;
	struct bpf_list_head head __contains(foo, node);
};

To recognize such types in user BTF, we build a btf_struct_metas array
of metadata items corresponding to each BTF ID. This is done once during
the btf_parse stage to avoid having to do it each time during the
verification process's requirement to inspect the metadata.

Moreover, the computed metadata needs to be passed to some helpers in
future patches which requires allocating them and storing them in the
BTF that is pinned by the program itself, so that valid access can be
assumed to such data during program runtime.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 include/linux/bpf.h  |   7 ++
 include/linux/btf.h  |  35 ++++++++
 kernel/bpf/btf.c     | 196 +++++++++++++++++++++++++++++++++++++++----
 kernel/bpf/syscall.c |   4 +
 4 files changed, 224 insertions(+), 18 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5d627161fbab..ba7781b8922e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -176,6 +176,7 @@  enum btf_field_type {
 	BPF_KPTR_REF   = (1 << 3),
 	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
 	BPF_LIST_HEAD  = (1 << 4),
+	BPF_LIST_NODE  = (1 << 5),
 };
 
 struct btf_field_kptr {
@@ -276,6 +277,8 @@  static inline const char *btf_field_type_name(enum btf_field_type type)
 		return "kptr";
 	case BPF_LIST_HEAD:
 		return "bpf_list_head";
+	case BPF_LIST_NODE:
+		return "bpf_list_node";
 	default:
 		WARN_ON_ONCE(1);
 		return "unknown";
@@ -294,6 +297,8 @@  static inline u32 btf_field_type_size(enum btf_field_type type)
 		return sizeof(u64);
 	case BPF_LIST_HEAD:
 		return sizeof(struct bpf_list_head);
+	case BPF_LIST_NODE:
+		return sizeof(struct bpf_list_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -312,6 +317,8 @@  static inline u32 btf_field_type_align(enum btf_field_type type)
 		return __alignof__(u64);
 	case BPF_LIST_HEAD:
 		return __alignof__(struct bpf_list_head);
+	case BPF_LIST_NODE:
+		return __alignof__(struct bpf_list_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
diff --git a/include/linux/btf.h b/include/linux/btf.h
index d80345fa566b..a01a8da20021 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -6,6 +6,8 @@ 
 
 #include <linux/types.h>
 #include <linux/bpfptr.h>
+#include <linux/bsearch.h>
+#include <linux/btf_ids.h>
 #include <uapi/linux/btf.h>
 #include <uapi/linux/bpf.h>
 
@@ -78,6 +80,17 @@  struct btf_id_dtor_kfunc {
 	u32 kfunc_btf_id;
 };
 
+struct btf_struct_meta {
+	u32 btf_id;
+	struct btf_record *record;
+	struct btf_field_offs *field_offs;
+};
+
+struct btf_struct_metas {
+	u32 cnt;
+	struct btf_struct_meta types[];
+};
+
 typedef void (*btf_dtor_kfunc_t)(void *);
 
 extern const struct file_operations btf_fops;
@@ -408,6 +421,23 @@  static inline struct btf_param *btf_params(const struct btf_type *t)
 	return (struct btf_param *)(t + 1);
 }
 
+static inline int btf_id_cmp_func(const void *a, const void *b)
+{
+	const int *pa = a, *pb = b;
+
+	return *pa - *pb;
+}
+
+static inline bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
+{
+	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
+}
+
+static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id)
+{
+	return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func);
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 struct bpf_prog;
 
@@ -423,6 +453,7 @@  int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
 s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
+struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
@@ -454,6 +485,10 @@  static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dt
 {
 	return 0;
 }
+static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id)
+{
+	return NULL;
+}
 #endif
 
 static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 242ba75f990a..bd78fc67a922 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -237,6 +237,7 @@  struct btf {
 	struct rcu_head rcu;
 	struct btf_kfunc_set_tab *kfunc_set_tab;
 	struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab;
+	struct btf_struct_metas *struct_meta_tab;
 
 	/* split BTF support */
 	struct btf *base_btf;
@@ -1642,8 +1643,30 @@  static void btf_free_dtor_kfunc_tab(struct btf *btf)
 	btf->dtor_kfunc_tab = NULL;
 }
 
+static void btf_struct_metas_free(struct btf_struct_metas *tab)
+{
+	int i;
+
+	if (!tab)
+		return;
+	for (i = 0; i < tab->cnt; i++) {
+		btf_record_free(tab->types[i].record);
+		kfree(tab->types[i].field_offs);
+	}
+	kfree(tab);
+}
+
+static void btf_free_struct_meta_tab(struct btf *btf)
+{
+	struct btf_struct_metas *tab = btf->struct_meta_tab;
+
+	btf_struct_metas_free(tab);
+	btf->struct_meta_tab = NULL;
+}
+
 static void btf_free(struct btf *btf)
 {
+	btf_free_struct_meta_tab(btf);
 	btf_free_dtor_kfunc_tab(btf);
 	btf_free_kfunc_set_tab(btf);
 	kvfree(btf->types);
@@ -3356,6 +3379,12 @@  static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask,
 			goto end;
 		}
 	}
+	if (field_mask & BPF_LIST_NODE) {
+		if (!strcmp(name, "bpf_list_node")) {
+			type = BPF_LIST_NODE;
+			goto end;
+		}
+	}
 	/* Only return BPF_KPTR when all other types with matchable names fail */
 	if (field_mask & BPF_KPTR) {
 		type = BPF_KPTR_REF;
@@ -3401,6 +3430,7 @@  static int btf_find_struct_field(const struct btf *btf,
 		switch (field_type) {
 		case BPF_SPIN_LOCK:
 		case BPF_TIMER:
+		case BPF_LIST_NODE:
 			ret = btf_find_struct(btf, member_type, off, sz, field_type,
 					      idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
@@ -3463,6 +3493,7 @@  static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 		switch (field_type) {
 		case BPF_SPIN_LOCK:
 		case BPF_TIMER:
+		case BPF_LIST_NODE:
 			ret = btf_find_struct(btf, var_type, off, sz, field_type,
 					      idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
@@ -3670,6 +3701,8 @@  struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 			if (ret < 0)
 				goto end;
 			break;
+		case BPF_LIST_NODE:
+			break;
 		default:
 			ret = -EFAULT;
 			goto end;
@@ -5135,6 +5168,118 @@  static int btf_parse_hdr(struct btf_verifier_env *env)
 	return btf_check_sec_info(env, btf_data_size);
 }
 
+static const char *local_kptr_fields[] = {
+	"bpf_spin_lock",
+	"bpf_list_head",
+	"bpf_list_node",
+};
+
+static struct btf_struct_metas *
+btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
+{
+	union {
+		struct btf_id_set set;
+		struct {
+			u32 _cnt;
+			u32 _ids[ARRAY_SIZE(local_kptr_fields)];
+		} _arr;
+	} lkf;
+	struct btf_struct_metas *tab = NULL;
+	int i, n, id, ret;
+
+	memset(&lkf, 0, sizeof(lkf));
+
+	for (i = 0; i < ARRAY_SIZE(local_kptr_fields); i++) {
+		/* Try to find whether this special type exists in user BTF, and
+		 * if so remember its ID so we can easily find it among members
+		 * of structs that we iterate in the next loop.
+		 */
+		id = btf_find_by_name_kind(btf, local_kptr_fields[i], BTF_KIND_STRUCT);
+		if (id < 0)
+			continue;
+		lkf.set.ids[lkf.set.cnt++] = id;
+	}
+
+	if (!lkf.set.cnt)
+		return NULL;
+	sort(&lkf.set.ids, lkf.set.cnt, sizeof(lkf.set.ids[0]), btf_id_cmp_func, NULL);
+
+	n = btf_nr_types(btf);
+	for (i = 1; i < n; i++) {
+		const struct btf_member *member;
+		struct btf_field_offs *foffs;
+		struct btf_struct_meta *type;
+		struct btf_record *record;
+		const struct btf_type *t;
+		int j;
+
+		t = btf_type_by_id(btf, i);
+		if (!t) {
+			ret = -EINVAL;
+			goto free;
+		}
+		if (!__btf_type_is_struct(t))
+			continue;
+
+		cond_resched();
+
+		for_each_member(j, t, member) {
+			if (btf_id_set_contains(&lkf.set, member->type))
+				goto parse;
+		}
+		continue;
+	parse:
+		if (!tab) {
+			tab = kzalloc(offsetof(struct btf_struct_metas, types[1]),
+				      GFP_KERNEL | __GFP_NOWARN);
+			if (!tab)
+				return ERR_PTR(-ENOMEM);
+		} else {
+			struct btf_struct_metas *new_tab;
+
+			new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab->cnt + 1]),
+					   GFP_KERNEL | __GFP_NOWARN);
+			if (!new_tab) {
+				ret = -ENOMEM;
+				goto free;
+			}
+			tab = new_tab;
+		}
+		type = &tab->types[tab->cnt];
+
+		type->btf_id = i;
+		record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size);
+		if (IS_ERR_OR_NULL(record)) {
+			ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT;
+			goto free;
+		}
+		foffs = btf_parse_field_offs(record);
+		if (WARN_ON_ONCE(IS_ERR_OR_NULL(foffs))) {
+			btf_record_free(record);
+			ret = -EFAULT;
+			goto free;
+		}
+		type->record = record;
+		type->field_offs = foffs;
+		tab->cnt++;
+	}
+	return tab;
+free:
+	btf_struct_metas_free(tab);
+	return ERR_PTR(ret);
+}
+
+struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id)
+{
+	struct btf_struct_metas *tab;
+
+	BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0);
+	tab = btf->struct_meta_tab;
+	if (!tab)
+		return NULL;
+	return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func);
+}
+
 static int btf_check_type_tags(struct btf_verifier_env *env,
 			       struct btf *btf, int start_id)
 {
@@ -5185,6 +5330,7 @@  static int btf_check_type_tags(struct btf_verifier_env *env,
 static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 			     u32 log_level, char __user *log_ubuf, u32 log_size)
 {
+	struct btf_struct_metas *struct_meta_tab;
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
@@ -5253,15 +5399,24 @@  static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 	if (err)
 		goto errout;
 
+	struct_meta_tab = btf_parse_struct_metas(log, btf);
+	if (IS_ERR(struct_meta_tab)) {
+		err = PTR_ERR(struct_meta_tab);
+		goto errout;
+	}
+	btf->struct_meta_tab = struct_meta_tab;
+
 	if (log->level && bpf_verifier_log_full(log)) {
 		err = -ENOSPC;
-		goto errout;
+		goto errout_meta;
 	}
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
 	return btf;
 
+errout_meta:
+	btf_free_struct_meta_tab(btf);
 errout:
 	btf_verifier_env_free(env);
 	if (btf)
@@ -6022,6 +6177,28 @@  int btf_struct_access(struct bpf_verifier_log *log,
 	u32 id = reg->btf_id;
 	int err;
 
+	while (type_is_local_kptr(reg->type)) {
+		struct btf_struct_meta *meta;
+		struct btf_record *rec;
+		int i;
+
+		meta = btf_find_struct_meta(btf, id);
+		if (!meta)
+			break;
+		rec = meta->record;
+		for (i = 0; i < rec->cnt; i++) {
+			struct btf_field *field = &rec->fields[i];
+			u32 offset = field->offset;
+			if (off < offset + btf_field_type_size(field->type) && offset < off + size) {
+				bpf_log(log,
+					"direct access to %s is disallowed\n",
+					btf_field_type_name(field->type));
+				return -EACCES;
+			}
+		}
+		break;
+	}
+
 	t = btf_type_by_id(btf, id);
 	do {
 		err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag);
@@ -7263,23 +7440,6 @@  bool btf_is_module(const struct btf *btf)
 	return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0;
 }
 
-static int btf_id_cmp_func(const void *a, const void *b)
-{
-	const int *pa = a, *pb = b;
-
-	return *pa - *pb;
-}
-
-bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
-{
-	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
-}
-
-static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id)
-{
-	return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func);
-}
-
 enum {
 	BTF_MODULE_F_LIVE = (1 << 0),
 };
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fdbae52f463f..c96039a4e57f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -537,6 +537,7 @@  void btf_record_free(struct btf_record *rec)
 			btf_put(rec->fields[i].kptr.btf);
 			break;
 		case BPF_LIST_HEAD:
+		case BPF_LIST_NODE:
 			/* Nothing to release for bpf_list_head */
 			break;
 		default:
@@ -582,6 +583,7 @@  struct btf_record *btf_record_dup(const struct btf_record *rec)
 			}
 			break;
 		case BPF_LIST_HEAD:
+		case BPF_LIST_NODE:
 			/* Nothing to acquire for bpf_list_head */
 			break;
 		default:
@@ -648,6 +650,8 @@  void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 				continue;
 			bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off);
 			break;
+		case BPF_LIST_NODE:
+			break;
 		default:
 			WARN_ON_ONCE(1);
 			continue;