aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/bpf/prog_cgroup_sockopt.rst
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/bpf/prog_cgroup_sockopt.rst')
-rw-r--r--Documentation/bpf/prog_cgroup_sockopt.rst69
1 files changed, 69 insertions, 0 deletions
diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst
index c47d974629ae..1226a94af07a 100644
--- a/Documentation/bpf/prog_cgroup_sockopt.rst
+++ b/Documentation/bpf/prog_cgroup_sockopt.rst
@@ -86,8 +86,77 @@ then the next program in the chain (A) will see those changes,
*not* the original input ``setsockopt`` arguments. The potentially
modified values will be then passed down to the kernel.
+Large optval
+============
+When the ``optval`` is greater than the ``PAGE_SIZE``, the BPF program
+can access only the first ``PAGE_SIZE`` of that data. So it has to options:
+
+* Set ``optlen`` to zero, which indicates that the kernel should
+ use the original buffer from the userspace. Any modifications
+ done by the BPF program to the ``optval`` are ignored.
+* Set ``optlen`` to the value less than ``PAGE_SIZE``, which
+ indicates that the kernel should use BPF's trimmed ``optval``.
+
+When the BPF program returns with the ``optlen`` greater than
+``PAGE_SIZE``, the userspace will receive original kernel
+buffers without any modifications that the BPF program might have
+applied.
+
Example
=======
+Recommended way to handle BPF programs is as follows:
+
+.. code-block:: c
+
+ SEC("cgroup/getsockopt")
+ int getsockopt(struct bpf_sockopt *ctx)
+ {
+ /* Custom socket option. */
+ if (ctx->level == MY_SOL && ctx->optname == MY_OPTNAME) {
+ ctx->retval = 0;
+ optval[0] = ...;
+ ctx->optlen = 1;
+ return 1;
+ }
+
+ /* Modify kernel's socket option. */
+ if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+ ctx->retval = 0;
+ optval[0] = ...;
+ ctx->optlen = 1;
+ return 1;
+ }
+
+ /* optval larger than PAGE_SIZE use kernel's buffer. */
+ if (ctx->optlen > PAGE_SIZE)
+ ctx->optlen = 0;
+
+ return 1;
+ }
+
+ SEC("cgroup/setsockopt")
+ int setsockopt(struct bpf_sockopt *ctx)
+ {
+ /* Custom socket option. */
+ if (ctx->level == MY_SOL && ctx->optname == MY_OPTNAME) {
+ /* do something */
+ ctx->optlen = -1;
+ return 1;
+ }
+
+ /* Modify kernel's socket option. */
+ if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+ optval[0] = ...;
+ return 1;
+ }
+
+ /* optval larger than PAGE_SIZE use kernel's buffer. */
+ if (ctx->optlen > PAGE_SIZE)
+ ctx->optlen = 0;
+
+ return 1;
+ }
+
See ``tools/testing/selftests/bpf/progs/sockopt_sk.c`` for an example
of BPF program that handles socket options.