From: thinker.li@gmail.com
To: bpf@vger.kernel.org, ast@kernel.org, martin.lau@linux.dev,
song@kernel.org, kernel-team@meta.com, andrii@kernel.org,
drosen@google.com
Cc: sinquersw@gmail.com, kuifeng@meta.com,
Kui-Feng Lee <thinker.li@gmail.com>
Subject: [PATCH bpf-next v17 08/14] bpf: pass attached BTF to the bpf_struct_ops subsystem
Date: Fri, 19 Jan 2024 14:49:59 -0800 [thread overview]
Message-ID: <20240119225005.668602-9-thinker.li@gmail.com> (raw)
In-Reply-To: <20240119225005.668602-1-thinker.li@gmail.com>
From: Kui-Feng Lee <thinker.li@gmail.com>
Pass the fd of a btf from the userspace to the bpf() syscall, and then
convert the fd into a btf. The btf is generated from the module that
defines the target BPF struct_ops type.
In order to inform the kernel about the module that defines the target
struct_ops type, the userspace program needs to provide a btf fd for the
respective module's btf. This btf contains essential information on the
types defined within the module, including the target struct_ops type.
A btf fd must be provided to the kernel for struct_ops maps and for the bpf
programs attached to those maps.
In the case of the bpf programs, the attach_btf_obj_fd parameter is passed
as part of the bpf_attr and is converted into a btf. This btf is then
stored in the prog->aux->attach_btf field. Here, it just let the verifier
access attach_btf directly.
In the case of struct_ops maps, a btf fd is passed as value_type_btf_obj_fd
of bpf_attr. The bpf_struct_ops_map_alloc() function converts the fd to a
btf and stores it as st_map->btf. A flag BPF_F_VTYPE_BTF_OBJ_FD is added
for map_flags to indicate that the value of value_type_btf_obj_fd is set.
Signed-off-by: Kui-Feng Lee <thinker.li@gmail.com>
---
include/uapi/linux/bpf.h | 8 +++++
kernel/bpf/bpf_struct_ops.c | 65 ++++++++++++++++++++++++----------
kernel/bpf/syscall.c | 2 +-
kernel/bpf/verifier.c | 9 +++--
tools/include/uapi/linux/bpf.h | 8 +++++
5 files changed, 70 insertions(+), 22 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8eb949b52102..adb4dc8582f7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1330,6 +1330,9 @@ enum {
/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
BPF_F_PATH_FD = (1U << 14),
+
+/* Flag for value_type_btf_obj_fd, the fd is available */
+ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15),
};
/* Flags for BPF_PROG_QUERY. */
@@ -1403,6 +1406,11 @@ union bpf_attr {
* to using 5 hash functions).
*/
__u64 map_extra;
+
+ __s32 value_type_btf_obj_fd; /* fd pointing to a BTF
+ * type data for
+ * btf_vmlinux_value_type_id.
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 7505f515aac3..3b8d689ece5d 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -641,6 +641,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
bpf_jit_uncharge_modmem(PAGE_SIZE);
}
bpf_map_area_free(st_map->uvalue);
+ btf_put(st_map->btf);
bpf_map_area_free(st_map);
}
@@ -669,7 +670,8 @@ static void bpf_struct_ops_map_free(struct bpf_map *map)
static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
{
if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 ||
- (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id)
+ (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) ||
+ !attr->btf_vmlinux_value_type_id)
return -EINVAL;
return 0;
}
@@ -681,15 +683,36 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
struct bpf_map *map;
+ struct btf *btf;
int ret;
- st_ops_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id);
- if (!st_ops_desc)
- return ERR_PTR(-ENOTSUPP);
+ if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) {
+ /* The map holds btf for its whole life time. */
+ btf = btf_get_by_fd(attr->value_type_btf_obj_fd);
+ if (IS_ERR(btf))
+ return ERR_CAST(btf);
+ if (!btf_is_module(btf)) {
+ btf_put(btf);
+ return ERR_PTR(-EINVAL);
+ }
+ } else {
+ btf = bpf_get_btf_vmlinux();
+ if (IS_ERR(btf))
+ return ERR_CAST(btf);
+ btf_get(btf);
+ }
+
+ st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id);
+ if (!st_ops_desc) {
+ ret = -ENOTSUPP;
+ goto errout;
+ }
vt = st_ops_desc->value_type;
- if (attr->value_size != vt->size)
- return ERR_PTR(-EINVAL);
+ if (attr->value_size != vt->size) {
+ ret = -EINVAL;
+ goto errout;
+ }
t = st_ops_desc->type;
@@ -700,17 +723,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
(vt->size - sizeof(struct bpf_struct_ops_value));
st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
- if (!st_map)
- return ERR_PTR(-ENOMEM);
+ if (!st_map) {
+ ret = -ENOMEM;
+ goto errout;
+ }
st_map->st_ops_desc = st_ops_desc;
map = &st_map->map;
ret = bpf_jit_charge_modmem(PAGE_SIZE);
- if (ret) {
- __bpf_struct_ops_map_free(map);
- return ERR_PTR(ret);
- }
+ if (ret)
+ goto errout_free;
st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE);
if (!st_map->image) {
@@ -719,24 +742,30 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
* here.
*/
bpf_jit_uncharge_modmem(PAGE_SIZE);
- __bpf_struct_ops_map_free(map);
- return ERR_PTR(-ENOMEM);
+ ret = -ENOMEM;
+ goto errout_free;
}
st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
st_map->links =
bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
NUMA_NO_NODE);
if (!st_map->uvalue || !st_map->links) {
- __bpf_struct_ops_map_free(map);
- return ERR_PTR(-ENOMEM);
+ ret = -ENOMEM;
+ goto errout_free;
}
-
- st_map->btf = btf_vmlinux;
+ st_map->btf = btf;
mutex_init(&st_map->lock);
bpf_map_init_from_attr(map, attr);
return map;
+
+errout_free:
+ __bpf_struct_ops_map_free(map);
+errout:
+ btf_put(btf);
+
+ return ERR_PTR(ret);
}
static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 05fe78ecc441..00b294ce0a61 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1123,7 +1123,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
return ret;
}
-#define BPF_MAP_CREATE_LAST_FIELD map_extra
+#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0744a1f194fa..ff41f7736618 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20234,6 +20234,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
const struct btf_member *member;
struct bpf_prog *prog = env->prog;
u32 btf_id, member_idx;
+ struct btf *btf;
const char *mname;
if (!prog->gpl_compatible) {
@@ -20241,8 +20242,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
}
+ btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux();
+
btf_id = prog->aux->attach_btf_id;
- st_ops_desc = bpf_struct_ops_find(btf_vmlinux, btf_id);
+ st_ops_desc = bpf_struct_ops_find(btf, btf_id);
if (!st_ops_desc) {
verbose(env, "attach_btf_id %u is not a supported struct\n",
btf_id);
@@ -20259,8 +20262,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
}
member = &btf_type_member(t)[member_idx];
- mname = btf_name_by_offset(btf_vmlinux, member->name_off);
- func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
+ mname = btf_name_by_offset(btf, member->name_off);
+ func_proto = btf_type_resolve_func_ptr(btf, member->type,
NULL);
if (!func_proto) {
verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1949d881f230..7f64865bf455 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1330,6 +1330,9 @@ enum {
/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
BPF_F_PATH_FD = (1U << 14),
+
+/* Flag for value_type_btf_obj_fd, the fd is available */
+ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15),
};
/* Flags for BPF_PROG_QUERY. */
@@ -1403,6 +1406,11 @@ union bpf_attr {
* to using 5 hash functions).
*/
__u64 map_extra;
+
+ __s32 value_type_btf_obj_fd; /* fd pointing to a BTF
+ * type data for
+ * btf_vmlinux_value_type_id.
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
--
2.34.1
next prev parent reply other threads:[~2024-01-19 22:50 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-19 22:49 [PATCH bpf-next v17 00/14] Registrating struct_ops types from modules thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 01/14] bpf: refactory struct_ops type initialization to a function thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 02/14] bpf: get type information with BTF_ID_LIST thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 03/14] bpf, net: introduce bpf_struct_ops_desc thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 04/14] bpf: add struct_ops_tab to btf thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 05/14] bpf: make struct_ops_map support btfs other than btf_vmlinux thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 06/14] bpf: pass btf object id in bpf_map_info thinker.li
2024-01-19 22:49 ` [PATCH bpf-next v17 07/14] bpf: lookup struct_ops types from a given module BTF thinker.li
2024-01-19 22:49 ` thinker.li [this message]
2024-01-19 22:50 ` [PATCH bpf-next v17 09/14] bpf: hold module refcnt in bpf_struct_ops map creation and prog verification thinker.li
2024-01-19 22:50 ` [PATCH bpf-next v17 10/14] bpf: validate value_type thinker.li
2024-01-19 22:50 ` [PATCH bpf-next v17 11/14] bpf, net: switch to dynamic registration thinker.li
2024-01-23 7:11 ` Martin KaFai Lau
2024-01-19 22:50 ` [PATCH bpf-next v17 12/14] libbpf: Find correct module BTFs for struct_ops maps and progs thinker.li
2024-01-19 22:50 ` [PATCH bpf-next v17 13/14] bpf: export btf_ctx_access to modules thinker.li
2024-01-19 22:50 ` [PATCH bpf-next v17 14/14] selftests/bpf: test case for register_bpf_struct_ops() thinker.li
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=20240119225005.668602-9-thinker.li@gmail.com \
--to=thinker.li@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=drosen@google.com \
--cc=kernel-team@meta.com \
--cc=kuifeng@meta.com \
--cc=martin.lau@linux.dev \
--cc=sinquersw@gmail.com \
--cc=song@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