From: Dave Marchevsky <davemarchevsky@fb.com>
To: <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Kernel Team <kernel-team@fb.com>, Tejun Heo <tj@kernel.org>,
Dave Marchevsky <davemarchevsky@fb.com>
Subject: [RFC PATCH bpf-next 08/11] bpf: Add OBJ_NON_OWNING_REF type flag
Date: Fri, 22 Jul 2022 11:34:35 -0700 [thread overview]
Message-ID: <20220722183438.3319790-9-davemarchevsky@fb.com> (raw)
In-Reply-To: <20220722183438.3319790-1-davemarchevsky@fb.com>
Consider a pointer to a type that would normally need acquire / release
semantics to be safely held. There may be scenarios where such a pointer
can be safely held without the need to acquire a reference.
For example, although a PTR_TO_BTF_ID for a rbtree_map node is released
via bpf_rbtree_add helper, the helper doesn't change the address of the
node and must be called with the rbtree_map's spinlock held. Since the
only way to remove a node from the rbtree - bpf_rbtree_remove helper -
requires the same lock, the newly-added node cannot be removed by a
concurrently-running program until the lock is released. Therefore it is
safe to hold a reference to this node until bpf_rbtree_unlock is called.
This patch introduces a new type flag and associated verifier logic to
handle such "non-owning" references.
Currently the only usecase I have is the rbtree example above, so the
verifier logic is straightforward:
* Tag return types of bpf_rbtree_{add,find} with OBJ_NON_OWNING_REF
* These both require the rbtree lock to be held to return anything
non-NULL
* Since ret type for both is PTR_TO_BTF_ID_OR_NULL, if lock is not
held and NULL is returned, existing mark_ptr_or_null_reg logic
will clear reg type.
* So if mark_ptr_or_null_reg logic turns the returned reg into a
PTR_TO_BTF_ID | OBJ_NON_OWNING_REF, verifier knows lock is held.
* When the lock is released the verifier invalidates any regs holding
non owning refs similarly to existing release_reference logic - but no
need to clear ref_obj_id as an 'owning' reference was never acquired.
[ TODO: Currently the invalidation logic in
clear_rbtree_node_non_owning_refs is not parametrized by map so
unlocking any rbtree lock will invalidate all non-owning refs ]
Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
---
include/linux/bpf.h | 1 +
kernel/bpf/rbtree.c | 4 +--
kernel/bpf/verifier.c | 63 +++++++++++++++++++++++++++++++++++++++----
3 files changed, 61 insertions(+), 7 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eb8c550db0e2..c9c4b4fb019c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -412,6 +412,7 @@ enum bpf_type_flag {
/* Size is known at compile time. */
MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS),
+ OBJ_NON_OWNING_REF = BIT(11 + BPF_BASE_TYPE_BITS),
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
diff --git a/kernel/bpf/rbtree.c b/kernel/bpf/rbtree.c
index 5b1ab73e164f..34864fc83209 100644
--- a/kernel/bpf/rbtree.c
+++ b/kernel/bpf/rbtree.c
@@ -111,7 +111,7 @@ BPF_CALL_3(bpf_rbtree_add, struct bpf_map *, map, void *, value, void *, cb)
const struct bpf_func_proto bpf_rbtree_add_proto = {
.func = bpf_rbtree_add,
.gpl_only = true,
- .ret_type = RET_PTR_TO_BTF_ID_OR_NULL,
+ .ret_type = RET_PTR_TO_BTF_ID_OR_NULL | OBJ_NON_OWNING_REF,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_BTF_ID | OBJ_RELEASE,
.arg2_btf_id = &bpf_rbtree_btf_ids[0],
@@ -133,7 +133,7 @@ BPF_CALL_3(bpf_rbtree_find, struct bpf_map *, map, void *, key, void *, cb)
const struct bpf_func_proto bpf_rbtree_find_proto = {
.func = bpf_rbtree_find,
.gpl_only = true,
- .ret_type = RET_PTR_TO_BTF_ID_OR_NULL,
+ .ret_type = RET_PTR_TO_BTF_ID_OR_NULL | OBJ_NON_OWNING_REF,
.ret_btf_id = &bpf_rbtree_btf_ids[0],
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_ANYTHING,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 174a355d97fd..4f46b2dfbc4b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -467,6 +467,11 @@ static bool type_is_rdonly_mem(u32 type)
return type & MEM_RDONLY;
}
+static bool type_is_non_owning_ref(u32 type)
+{
+ return type & OBJ_NON_OWNING_REF;
+}
+
static bool type_may_be_null(u32 type)
{
return type & PTR_MAYBE_NULL;
@@ -555,7 +560,9 @@ static bool function_returns_rbtree_node(enum bpf_func_id func_id)
static const char *reg_type_str(struct bpf_verifier_env *env,
enum bpf_reg_type type)
{
- char postfix[16] = {0}, prefix[32] = {0};
+ char postfix[32] = {0}, prefix[32] = {0};
+ unsigned int postfix_idx = 0;
+
static const char * const str[] = {
[NOT_INIT] = "?",
[SCALAR_VALUE] = "scalar",
@@ -579,11 +586,18 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
[PTR_TO_MAP_KEY] = "map_key",
};
- if (type & PTR_MAYBE_NULL) {
+ if (type_may_be_null(type)) {
if (base_type(type) == PTR_TO_BTF_ID)
- strncpy(postfix, "or_null_", 16);
+ postfix_idx += strlcpy(postfix + postfix_idx, "or_null_", 32 - postfix_idx);
else
- strncpy(postfix, "_or_null", 16);
+ postfix_idx += strlcpy(postfix + postfix_idx, "_or_null", 32 - postfix_idx);
+ }
+
+ if (type_is_non_owning_ref(type)) {
+ if (base_type(type) == PTR_TO_BTF_ID)
+ postfix_idx += strlcpy(postfix + postfix_idx, "non_own_", 32 - postfix_idx);
+ else
+ postfix_idx += strlcpy(postfix + postfix_idx, "_non_own", 32 - postfix_idx);
}
if (type & MEM_RDONLY)
@@ -5684,12 +5698,18 @@ static const struct bpf_reg_types int_ptr_types = {
},
};
+static const struct bpf_reg_types btf_ptr_types = {
+ .types = {
+ PTR_TO_BTF_ID,
+ PTR_TO_BTF_ID | OBJ_NON_OWNING_REF,
+ },
+};
+
static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } };
static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
-static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU } };
static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
@@ -6635,6 +6655,33 @@ static int release_reference(struct bpf_verifier_env *env,
return 0;
}
+static void clear_non_owning_ref_regs(struct bpf_verifier_env *env,
+ struct bpf_func_state *state)
+{
+ struct bpf_reg_state *regs = state->regs, *reg;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (type_is_non_owning_ref(regs[i].type))
+ mark_reg_unknown(env, regs, i);
+
+ bpf_for_each_spilled_reg(i, state, reg) {
+ if (!reg)
+ continue;
+ if (type_is_non_owning_ref(reg->type))
+ __mark_reg_unknown(env, reg);
+ }
+}
+
+static void clear_rbtree_node_non_owning_refs(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ int i;
+
+ for (i = 0; i <= vstate->curframe; i++)
+ clear_non_owning_ref_regs(env, vstate->frame[i]);
+}
+
static void clear_caller_saved_regs(struct bpf_verifier_env *env,
struct bpf_reg_state *regs)
{
@@ -7436,6 +7483,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
}
}
break;
+ case BPF_FUNC_rbtree_unlock:
+ /* TODO clear_rbtree_node_non_owning_refs calls should be
+ * parametrized by base_type or ideally by owning map
+ */
+ clear_rbtree_node_non_owning_refs(env);
+ break;
}
if (err)
--
2.30.2
next prev parent reply other threads:[~2022-07-22 18:35 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-22 18:34 [RFC PATCH bpf-next 00/11] bpf: Introduce rbtree map Dave Marchevsky
2022-07-22 18:34 ` [RFC PATCH bpf-next 01/11] bpf: Pull repeated reg access bounds check into helper fn Dave Marchevsky
2022-07-22 18:34 ` [RFC PATCH bpf-next 02/11] bpf: Add verifier support for custom callback return range Dave Marchevsky
2022-07-22 18:34 ` [RFC PATCH bpf-next 03/11] bpf: Add rb_node_off to bpf_map Dave Marchevsky
2022-08-01 22:19 ` Alexei Starovoitov
2022-07-22 18:34 ` [RFC PATCH bpf-next 04/11] bpf: Add rbtree map Dave Marchevsky
2022-08-01 21:49 ` Alexei Starovoitov
2022-07-22 18:34 ` [RFC PATCH bpf-next 05/11] bpf: Add bpf_spin_lock member to rbtree Dave Marchevsky
2022-08-01 22:17 ` Alexei Starovoitov
2022-08-02 13:59 ` Kumar Kartikeya Dwivedi
2022-08-02 15:30 ` Alexei Starovoitov
2022-08-10 21:46 ` Kumar Kartikeya Dwivedi
2022-08-10 22:06 ` Alexei Starovoitov
2022-08-10 23:16 ` Kumar Kartikeya Dwivedi
2022-08-15 5:33 ` Yonghong Song
2022-08-15 5:37 ` Kumar Kartikeya Dwivedi
2022-07-22 18:34 ` [RFC PATCH bpf-next 06/11] bpf: Add bpf_rbtree_{lock,unlock} helpers Dave Marchevsky
2022-08-01 21:58 ` Alexei Starovoitov
2022-07-22 18:34 ` [RFC PATCH bpf-next 07/11] bpf: Enforce spinlock hold for bpf_rbtree_{add,remove,find} Dave Marchevsky
2022-07-22 18:34 ` Dave Marchevsky [this message]
2022-08-01 22:41 ` [RFC PATCH bpf-next 08/11] bpf: Add OBJ_NON_OWNING_REF type flag Alexei Starovoitov
2022-07-22 18:34 ` [RFC PATCH bpf-next 09/11] bpf: Add CONDITIONAL_RELEASE " Dave Marchevsky
2022-08-01 22:23 ` Alexei Starovoitov
2022-07-22 18:34 ` [RFC PATCH bpf-next 10/11] bpf: Introduce PTR_ITER and PTR_ITER_END type flags Dave Marchevsky
2022-07-29 16:31 ` Tejun Heo
2022-08-01 22:44 ` Alexei Starovoitov
2022-08-02 13:05 ` Kumar Kartikeya Dwivedi
2022-08-02 15:10 ` Alexei Starovoitov
2022-08-10 17:56 ` Dave Marchevsky
2022-07-22 18:34 ` [RFC PATCH bpf-next 11/11] selftests/bpf: Add rbtree map tests Dave Marchevsky
2022-07-28 7:18 ` Yonghong Song
2022-08-10 17:48 ` Dave Marchevsky
2022-07-28 7:04 ` [RFC PATCH bpf-next 00/11] bpf: Introduce rbtree map Yonghong Song
2022-08-10 17:54 ` Dave Marchevsky
2022-08-01 21:27 ` Alexei Starovoitov
2022-08-10 18:11 ` Dave Marchevsky
2022-08-02 22:02 ` Andrii Nakryiko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220722183438.3319790-9-davemarchevsky@fb.com \
--to=davemarchevsky@fb.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).