Merge branch 'bpf-prog-map-ID'
Martin KaFai Lau says:
====================
Introduce bpf ID
This patch series:
1) Introduce ID for both bpf_prog and bpf_map.
2) Add bpf commands to iterate the prog IDs and map
IDs of the system.
3) Add bpf commands to get a prog/map fd from an ID
4) Add bpf command to get prog/map info from a fd.
The prog/map info is a jump start in this patchset
and it is not meant to be a complete list. They can
be extended in the future patches.
v3:
- I suspect v2 may not have applied cleanly.
In particular, patch 1 has conflict with a recent
change in struct bpf_prog_aux introduced at a similar time frame:
8726679a0fa3 ("bpf: teach verifier to track stack depth")
v3 should have fixed it.
v2:
Compiler warning fixes:
- Remove lockdep_is_held() usage. Add comment
to explain the lock situation instead.
- Add static for idr related variables
- Add __user to the uattr param in bpf_prog_get_info_by_fd()
and bpf_map_get_info_by_fd().
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index b1d38ee..4f95873 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -900,6 +900,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)ctx.image;
prog->jited = 1;
+ prog->jited_len = image_size;
out_off:
kfree(ctx.offset);
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index a013665..861c5af 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1052,6 +1052,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
fp->bpf_func = (void *)image;
fp->jited = 1;
+ fp->jited_len = alloclen;
bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 42ad383..01c6fbc 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1329,6 +1329,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
bpf_jit_binary_lock_ro(header);
fp->bpf_func = (void *) jit.prg_buf;
fp->jited = 1;
+ fp->jited_len = jit.size;
free_addrs:
kfree(jit.addrs);
out:
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 098874a..8799ae9 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1560,6 +1560,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
prog->bpf_func = (void *)ctx.image;
prog->jited = 1;
+ prog->jited_len = image_size;
out_off:
kfree(ctx.offset);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 617eac9..e1324f2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1167,6 +1167,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)image;
prog->jited = 1;
+ prog->jited_len = proglen;
} else {
prog = orig_prog;
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fcc80ca..c32bace 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,6 +46,7 @@ struct bpf_map {
u32 max_entries;
u32 map_flags;
u32 pages;
+ u32 id;
struct user_struct *user;
const struct bpf_map_ops *ops;
struct work_struct work;
@@ -172,6 +173,7 @@ struct bpf_prog_aux {
u32 used_map_cnt;
u32 max_ctx_offset;
u32 stack_depth;
+ u32 id;
struct latch_tree_node ksym_tnode;
struct list_head ksym_lnode;
const struct bpf_verifier_ops *ops;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a20ba40..1fa26dc 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -69,8 +69,6 @@ struct bpf_prog_aux;
/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK 512
-#define BPF_TAG_SIZE 8
-
/* Helper macros for filter block array initializers. */
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
@@ -432,6 +430,7 @@ struct bpf_prog {
kmemcheck_bitfield_end(meta);
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
+ u32 jited_len; /* Size of jited insns in bytes */
u8 tag[BPF_TAG_SIZE];
struct bpf_prog_aux *aux; /* Auxiliary fields */
struct sock_fprog_kern *orig_prog; /* Original BPF program */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e78aece..9b2c10b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -82,6 +82,11 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
};
enum bpf_map_type {
@@ -209,6 +214,21 @@ union bpf_attr {
__u32 repeat;
__u32 duration;
} test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ };
+ __u32 next_id;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -673,4 +693,25 @@ struct xdp_md {
__u32 data_end;
};
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+} __attribute__((aligned(8)));
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 59da103..8942c82 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -22,8 +22,13 @@
#include <linux/filter.h>
#include <linux/version.h>
#include <linux/kernel.h>
+#include <linux/idr.h>
DEFINE_PER_CPU(int, bpf_prog_active);
+static DEFINE_IDR(prog_idr);
+static DEFINE_SPINLOCK(prog_idr_lock);
+static DEFINE_IDR(map_idr);
+static DEFINE_SPINLOCK(map_idr_lock);
int sysctl_unprivileged_bpf_disabled __read_mostly;
@@ -114,6 +119,37 @@ static void bpf_map_uncharge_memlock(struct bpf_map *map)
free_uid(user);
}
+static int bpf_map_alloc_id(struct bpf_map *map)
+{
+ int id;
+
+ spin_lock_bh(&map_idr_lock);
+ id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ map->id = id;
+ spin_unlock_bh(&map_idr_lock);
+
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
+{
+ if (do_idr_lock)
+ spin_lock_bh(&map_idr_lock);
+ else
+ __acquire(&map_idr_lock);
+
+ idr_remove(&map_idr, map->id);
+
+ if (do_idr_lock)
+ spin_unlock_bh(&map_idr_lock);
+ else
+ __release(&map_idr_lock);
+}
+
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
@@ -135,14 +171,21 @@ static void bpf_map_put_uref(struct bpf_map *map)
/* decrement map refcnt and schedule it for freeing via workqueue
* (unrelying map implementation ops->map_free() might sleep)
*/
-void bpf_map_put(struct bpf_map *map)
+static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
{
if (atomic_dec_and_test(&map->refcnt)) {
+ /* bpf_map_free_id() must be called first */
+ bpf_map_free_id(map, do_idr_lock);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
}
+void bpf_map_put(struct bpf_map *map)
+{
+ __bpf_map_put(map, true);
+}
+
void bpf_map_put_with_uref(struct bpf_map *map)
{
bpf_map_put_uref(map);
@@ -236,11 +279,22 @@ static int map_create(union bpf_attr *attr)
if (err)
goto free_map_nouncharge;
- err = bpf_map_new_fd(map);
- if (err < 0)
- /* failed to allocate fd */
+ err = bpf_map_alloc_id(map);
+ if (err)
goto free_map;
+ err = bpf_map_new_fd(map);
+ if (err < 0) {
+ /* failed to allocate fd.
+ * bpf_map_put() is needed because the above
+ * bpf_map_alloc_id() has published the map
+ * to the userspace and the userspace may
+ * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
+ */
+ bpf_map_put(map);
+ return err;
+ }
+
trace_bpf_map_create(map, err);
return err;
@@ -295,6 +349,28 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
return map;
}
+/* map_idr_lock should have been held */
+static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
+ bool uref)
+{
+ int refold;
+
+ refold = __atomic_add_unless(&map->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_map_put(map, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ if (uref)
+ atomic_inc(&map->usercnt);
+
+ return map;
+}
+
int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
return -ENOTSUPP;
@@ -650,6 +726,42 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
free_uid(user);
}
+static int bpf_prog_alloc_id(struct bpf_prog *prog)
+{
+ int id;
+
+ spin_lock_bh(&prog_idr_lock);
+ id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ prog->aux->id = id;
+ spin_unlock_bh(&prog_idr_lock);
+
+ /* id is in [1, INT_MAX) */
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+{
+ /* cBPF to eBPF migrations are currently not in the idr store. */
+ if (!prog->aux->id)
+ return;
+
+ if (do_idr_lock)
+ spin_lock_bh(&prog_idr_lock);
+ else
+ __acquire(&prog_idr_lock);
+
+ idr_remove(&prog_idr, prog->aux->id);
+
+ if (do_idr_lock)
+ spin_unlock_bh(&prog_idr_lock);
+ else
+ __release(&prog_idr_lock);
+}
+
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
@@ -659,14 +771,21 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
bpf_prog_free(aux->prog);
}
-void bpf_prog_put(struct bpf_prog *prog)
+static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
trace_bpf_prog_put_rcu(prog);
+ /* bpf_prog_free_id() must be called first */
+ bpf_prog_free_id(prog, do_idr_lock);
bpf_prog_kallsyms_del(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
}
+
+void bpf_prog_put(struct bpf_prog *prog)
+{
+ __bpf_prog_put(prog, true);
+}
EXPORT_SYMBOL_GPL(bpf_prog_put);
static int bpf_prog_release(struct inode *inode, struct file *filp)
@@ -748,6 +867,24 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
}
EXPORT_SYMBOL_GPL(bpf_prog_inc);
+/* prog_idr_lock should have been held */
+static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
+{
+ int refold;
+
+ refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_prog_put(prog, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ return prog;
+}
+
static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
{
struct fd f = fdget(ufd);
@@ -857,11 +994,22 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- err = bpf_prog_new_fd(prog);
- if (err < 0)
- /* failed to allocate fd */
+ err = bpf_prog_alloc_id(prog);
+ if (err)
goto free_used_maps;
+ err = bpf_prog_new_fd(prog);
+ if (err < 0) {
+ /* failed to allocate fd.
+ * bpf_prog_put() is needed because the above
+ * bpf_prog_alloc_id() has published the prog
+ * to the userspace and the userspace may
+ * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
+ */
+ bpf_prog_put(prog);
+ return err;
+ }
+
bpf_prog_kallsyms_add(prog);
trace_bpf_prog_load(prog, err);
return err;
@@ -999,6 +1147,237 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
return ret;
}
+#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id
+
+static int bpf_obj_get_next_id(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ struct idr *idr,
+ spinlock_t *lock)
+{
+ u32 next_id = attr->start_id;
+ int err = 0;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ next_id++;
+ spin_lock_bh(lock);
+ if (!idr_get_next(idr, &next_id))
+ err = -ENOENT;
+ spin_unlock_bh(lock);
+
+ if (!err)
+ err = put_user(next_id, &uattr->next_id);
+
+ return err;
+}
+
+#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
+
+static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ u32 id = attr->prog_id;
+ int fd;
+
+ if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ spin_lock_bh(&prog_idr_lock);
+ prog = idr_find(&prog_idr, id);
+ if (prog)
+ prog = bpf_prog_inc_not_zero(prog);
+ else
+ prog = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&prog_idr_lock);
+
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ fd = bpf_prog_new_fd(prog);
+ if (fd < 0)
+ bpf_prog_put(prog);
+
+ return fd;
+}
+
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
+
+static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_map *map;
+ u32 id = attr->map_id;
+ int fd;
+
+ if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ spin_lock_bh(&map_idr_lock);
+ map = idr_find(&map_idr, id);
+ if (map)
+ map = bpf_map_inc_not_zero(map, true);
+ else
+ map = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&map_idr_lock);
+
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ fd = bpf_map_new_fd(map);
+ if (fd < 0)
+ bpf_map_put(map);
+
+ return fd;
+}
+
+static int check_uarg_tail_zero(void __user *uaddr,
+ size_t expected_size,
+ size_t actual_size)
+{
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+ int err;
+
+ if (actual_size <= expected_size)
+ return 0;
+
+ addr = uaddr + expected_size;
+ end = uaddr + actual_size;
+
+ for (; addr < end; addr++) {
+ err = get_user(val, addr);
+ if (err)
+ return err;
+ if (val)
+ return -E2BIG;
+ }
+
+ return 0;
+}
+
+static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_prog_info info = {};
+ u32 info_len = attr->info.info_len;
+ char __user *uinsns;
+ u32 ulen;
+ int err;
+
+ err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ if (copy_from_user(&info, uinfo, info_len))
+ return err;
+
+ info.type = prog->type;
+ info.id = prog->aux->id;
+
+ memcpy(info.tag, prog->tag, sizeof(prog->tag));
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ info.jited_prog_len = 0;
+ info.xlated_prog_len = 0;
+ goto done;
+ }
+
+ ulen = info.jited_prog_len;
+ info.jited_prog_len = prog->jited_len;
+ if (info.jited_prog_len && ulen) {
+ uinsns = u64_to_user_ptr(info.jited_prog_insns);
+ ulen = min_t(u32, info.jited_prog_len, ulen);
+ if (copy_to_user(uinsns, prog->bpf_func, ulen))
+ return -EFAULT;
+ }
+
+ ulen = info.xlated_prog_len;
+ info.xlated_prog_len = bpf_prog_size(prog->len);
+ if (info.xlated_prog_len && ulen) {
+ uinsns = u64_to_user_ptr(info.xlated_prog_insns);
+ ulen = min_t(u32, info.xlated_prog_len, ulen);
+ if (copy_to_user(uinsns, prog->insnsi, ulen))
+ return -EFAULT;
+ }
+
+done:
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int bpf_map_get_info_by_fd(struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_map_info info = {};
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ info.type = map->map_type;
+ info.id = map->id;
+ info.key_size = map->key_size;
+ info.value_size = map->value_size;
+ info.max_entries = map->max_entries;
+ info.map_flags = map->map_flags;
+
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
+
+static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ int ufd = attr->info.bpf_fd;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ if (!f.file)
+ return -EBADFD;
+
+ if (f.file->f_op == &bpf_prog_fops)
+ err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+ uattr);
+ else if (f.file->f_op == &bpf_map_fops)
+ err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+ uattr);
+ else
+ err = -EINVAL;
+
+ fdput(f);
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1018,23 +1397,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
* user-space does not rely on any kernel feature
* extensions we dont know about yet.
*/
- if (size > sizeof(attr)) {
- unsigned char __user *addr;
- unsigned char __user *end;
- unsigned char val;
-
- addr = (void __user *)uattr + sizeof(attr);
- end = (void __user *)uattr + size;
-
- for (; addr < end; addr++) {
- err = get_user(val, addr);
- if (err)
- return err;
- if (val)
- return -E2BIG;
- }
- size = sizeof(attr);
- }
+ err = check_uarg_tail_zero(uattr, sizeof(attr), size);
+ if (err)
+ return err;
+ size = min_t(u32, size, sizeof(attr));
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
if (copy_from_user(&attr, uattr, size) != 0)
@@ -1076,6 +1442,23 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
+ case BPF_PROG_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &prog_idr, &prog_idr_lock);
+ break;
+ case BPF_MAP_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &map_idr, &map_idr_lock);
+ break;
+ case BPF_PROG_GET_FD_BY_ID:
+ err = bpf_prog_get_fd_by_id(&attr);
+ break;
+ case BPF_MAP_GET_FD_BY_ID:
+ err = bpf_map_get_fd_by_id(&attr);
+ break;
+ case BPF_OBJ_GET_INFO_BY_FD:
+ err = bpf_obj_get_info_by_fd(&attr, uattr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e78aece..9b2c10b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -82,6 +82,11 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
};
enum bpf_map_type {
@@ -209,6 +214,21 @@ union bpf_attr {
__u32 repeat;
__u32 duration;
} test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ };
+ __u32 next_id;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -673,4 +693,25 @@ struct xdp_md {
__u32 data_end;
};
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+} __attribute__((aligned(8)));
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 6e17898..7e0405e 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -257,3 +257,71 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
*duration = attr.test.duration;
return ret;
}
+
+int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ attr.start_id = start_id;
+
+ err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
+ if (!err)
+ *next_id = attr.next_id;
+
+ return err;
+}
+
+int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ attr.start_id = start_id;
+
+ err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
+ if (!err)
+ *next_id = attr.next_id;
+
+ return err;
+}
+
+int bpf_prog_get_fd_by_id(__u32 id)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.prog_id = id;
+
+ return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_map_get_fd_by_id(__u32 id)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_id = id;
+
+ return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
+{
+ union bpf_attr attr;
+ int err;
+
+ bzero(&attr, sizeof(attr));
+ bzero(info, *info_len);
+ attr.info.bpf_fd = prog_fd;
+ attr.info.info_len = *info_len;
+ attr.info.info = ptr_to_u64(info);
+
+ err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
+ if (!err)
+ *info_len = attr.info.info_len;
+
+ return err;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 972bd83..16de44a 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -54,5 +54,10 @@ int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
void *data_out, __u32 *size_out, __u32 *retval,
__u32 *duration);
+int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
+int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+int bpf_prog_get_fd_by_id(__u32 id);
+int bpf_map_get_fd_by_id(__u32 id);
+int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
#endif
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f389b02..9f0e07b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -14,7 +14,7 @@
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align
-TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
+TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o
TEST_PROGS := test_kmod.sh
diff --git a/tools/testing/selftests/bpf/test_obj_id.c b/tools/testing/selftests/bpf/test_obj_id.c
new file mode 100644
index 0000000..d8723aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_obj_id.c
@@ -0,0 +1,35 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+/* It is a dumb bpf program such that it must have no
+ * issue to be loaded since testing the verifier is
+ * not the focus here.
+ */
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") test_map_id = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 1,
+};
+
+SEC("test_prog_id")
+int test_prog_id(struct __sk_buff *skb)
+{
+ __u32 key = 0;
+ __u64 *value;
+
+ value = bpf_map_lookup_elem(&test_map_id, &key);
+
+ return TC_ACT_OK;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index b59f5ed..8189bfc 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -22,6 +22,8 @@ typedef __u16 __sum16;
#include <sys/wait.h>
#include <sys/resource.h>
+#include <sys/types.h>
+#include <pwd.h>
#include <linux/bpf.h>
#include <linux/err.h>
@@ -70,6 +72,7 @@ static struct {
pass_cnt++; \
printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
} \
+ __ret; \
})
static int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -283,6 +286,193 @@ static void test_tcp_estats(void)
bpf_object__close(obj);
}
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
+static void test_bpf_obj_id(void)
+{
+ const __u64 array_magic_value = 0xfaceb00c;
+ const __u32 array_key = 0;
+ const int nr_iters = 2;
+ const char *file = "./test_obj_id.o";
+
+ struct bpf_object *objs[nr_iters];
+ int prog_fds[nr_iters], map_fds[nr_iters];
+ /* +1 to test for the info_len returned by kernel */
+ struct bpf_prog_info prog_infos[nr_iters + 1];
+ struct bpf_map_info map_infos[nr_iters + 1];
+ char jited_insns[128], xlated_insns[128];
+ __u32 i, next_id, info_len, nr_id_found, duration = 0;
+ int err = 0;
+ __u64 array_value;
+
+ err = bpf_prog_get_fd_by_id(0);
+ CHECK(err >= 0 || errno != ENOENT,
+ "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+
+ err = bpf_map_get_fd_by_id(0);
+ CHECK(err >= 0 || errno != ENOENT,
+ "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+
+ for (i = 0; i < nr_iters; i++)
+ objs[i] = NULL;
+
+ /* Check bpf_obj_get_info_by_fd() */
+ for (i = 0; i < nr_iters; i++) {
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
+ &objs[i], &prog_fds[i]);
+ /* test_obj_id.o is a dumb prog. It should never fail
+ * to load.
+ */
+ assert(!err);
+
+ /* Check getting prog info */
+ info_len = sizeof(struct bpf_prog_info) * 2;
+ prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
+ prog_infos[i].jited_prog_len = sizeof(jited_insns);
+ prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
+ prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+ err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
+ &info_len);
+ if (CHECK(err ||
+ prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
+ info_len != sizeof(struct bpf_prog_info) ||
+ !prog_infos[i].jited_prog_len ||
+ !prog_infos[i].xlated_prog_len,
+ "get-prog-info(fd)",
+ "err %d errno %d i %d type %d(%d) info_len %u(%lu) jited_prog_len %u xlated_prog_len %u\n",
+ err, errno, i,
+ prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
+ info_len, sizeof(struct bpf_prog_info),
+ prog_infos[i].jited_prog_len,
+ prog_infos[i].xlated_prog_len))
+ goto done;
+
+ map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
+ assert(map_fds[i] >= 0);
+ err = bpf_map_update_elem(map_fds[i], &array_key,
+ &array_magic_value, 0);
+ assert(!err);
+
+ /* Check getting map info */
+ info_len = sizeof(struct bpf_map_info) * 2;
+ err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+ &info_len);
+ if (CHECK(err ||
+ map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+ map_infos[i].key_size != sizeof(__u32) ||
+ map_infos[i].value_size != sizeof(__u64) ||
+ map_infos[i].max_entries != 1 ||
+ map_infos[i].map_flags != 0 ||
+ info_len != sizeof(struct bpf_map_info),
+ "get-map-info(fd)",
+ "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
+ err, errno,
+ map_infos[i].type, BPF_MAP_TYPE_ARRAY,
+ info_len, sizeof(struct bpf_map_info),
+ map_infos[i].key_size,
+ map_infos[i].value_size,
+ map_infos[i].max_entries,
+ map_infos[i].map_flags))
+ goto done;
+ }
+
+ /* Check bpf_prog_get_next_id() */
+ nr_id_found = 0;
+ next_id = 0;
+ while (!bpf_prog_get_next_id(next_id, &next_id)) {
+ struct bpf_prog_info prog_info;
+ int prog_fd;
+
+ info_len = sizeof(prog_info);
+
+ prog_fd = bpf_prog_get_fd_by_id(next_id);
+ if (prog_fd < 0 && errno == ENOENT)
+ /* The bpf_prog is in the dead row */
+ continue;
+ if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
+ "prog_fd %d next_id %d errno %d\n",
+ prog_fd, next_id, errno))
+ break;
+
+ for (i = 0; i < nr_iters; i++)
+ if (prog_infos[i].id == next_id)
+ break;
+
+ if (i == nr_iters)
+ continue;
+
+ nr_id_found++;
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+ CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
+ memcmp(&prog_info, &prog_infos[i], info_len),
+ "get-prog-info(next_id->fd)",
+ "err %d errno %d info_len %u(%lu) memcmp %d\n",
+ err, errno, info_len, sizeof(struct bpf_prog_info),
+ memcmp(&prog_info, &prog_infos[i], info_len));
+
+ close(prog_fd);
+ }
+ CHECK(nr_id_found != nr_iters,
+ "check total prog id found by get_next_id",
+ "nr_id_found %u(%u)\n",
+ nr_id_found, nr_iters);
+
+ /* Check bpf_map_get_next_id() */
+ nr_id_found = 0;
+ next_id = 0;
+ while (!bpf_map_get_next_id(next_id, &next_id)) {
+ struct bpf_map_info map_info;
+ int map_fd;
+
+ info_len = sizeof(map_info);
+
+ map_fd = bpf_map_get_fd_by_id(next_id);
+ if (map_fd < 0 && errno == ENOENT)
+ /* The bpf_map is in the dead row */
+ continue;
+ if (CHECK(map_fd < 0, "get-map-fd(next_id)",
+ "map_fd %d next_id %u errno %d\n",
+ map_fd, next_id, errno))
+ break;
+
+ for (i = 0; i < nr_iters; i++)
+ if (map_infos[i].id == next_id)
+ break;
+
+ if (i == nr_iters)
+ continue;
+
+ nr_id_found++;
+
+ err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
+ assert(!err);
+
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ CHECK(err || info_len != sizeof(struct bpf_map_info) ||
+ memcmp(&map_info, &map_infos[i], info_len) ||
+ array_value != array_magic_value,
+ "check get-map-info(next_id->fd)",
+ "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n",
+ err, errno, info_len, sizeof(struct bpf_map_info),
+ memcmp(&map_info, &map_infos[i], info_len),
+ array_value, array_magic_value);
+
+ close(map_fd);
+ }
+ CHECK(nr_id_found != nr_iters,
+ "check total map id found by get_next_id",
+ "nr_id_found %u(%u)\n",
+ nr_id_found, nr_iters);
+
+done:
+ for (i = 0; i < nr_iters; i++)
+ bpf_object__close(objs[i]);
+}
+
int main(void)
{
struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -293,6 +483,7 @@ int main(void)
test_xdp();
test_l4lb();
test_tcp_estats();
+ test_bpf_obj_id();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return 0;