BPF_SYNCHRONIZE waits for any BPF programs active at the time of
BPF_SYNCHRONIZE to complete, allowing userspace to ensure atomicity of
RCU data structure operations with respect to active programs. For
example, userspace can update a map->map entry to point to a new map,
use BPF_SYNCHRONIZE to wait for any BPF programs using the old map to
complete, and then drain the old map without fear that BPF programs
may still be updating it.
Signed-off-by: Daniel Colascione <dan...@google.com>
---
include/uapi/linux/bpf.h | 1 +
kernel/bpf/syscall.c | 14 ++++++++++++++
2 files changed, 15 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b7db3261c62d..4365c50e8055 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -98,6 +98,7 @@ enum bpf_cmd {
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
+ BPF_SYNCHRONIZE,
};
enum bpf_map_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d10ecd78105f..60ec7811846e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2272,6 +2272,20 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *,
uattr, unsigned int, siz
if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (cmd == BPF_SYNCHRONIZE) {
+ if (uattr != NULL || size != 0)
+ return -EINVAL;
+ err = security_bpf(cmd, NULL, 0);
+ if (err < 0)
+ return err;
+ /* BPF programs are run with preempt disabled, so
+ * synchronize_sched is sufficient even with
+ * RCU_PREEMPT.
+ */
+ synchronize_sched();
+ return 0;
+ }
+
err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
if (err)
return err;
--
2.18.0.203.gfac676dfb9-goog
