bpf: Support input xdp_md context in BPF_PROG_TEST_RUN

Support passing a xdp_md via ctx_in/ctx_out in bpf_attr for
BPF_PROG_TEST_RUN.

The intended use case is to pass some XDP meta data to the test runs of
XDP programs that are used as tail calls.

For programs that use bpf_prog_test_run_xdp, support xdp_md input and
output. Unlike with an actual xdp_md during a non-test run, data_meta must
be 0 because it must point to the start of the provided user data. From
the initial xdp_md, use data and data_end to adjust the pointers in the
generated xdp_buff. All other non-zero fields are prohibited (with
EINVAL). If the user has set ctx_out/ctx_size_out, copy the (potentially
different) xdp_md back to the userspace.

We require all fields of input xdp_md except the ones we explicitly
support to be set to zero. The expectation is that in the future we might
add support for more fields and we want to fail explicitly if the user
runs the program on the kernel where we don't yet support them.

Co-developed-by: Cody Haas <chaas@riotgames.com>
Co-developed-by: Lisa Watanabe <lwatanabe@riotgames.com>
Signed-off-by: Cody Haas <chaas@riotgames.com>
Signed-off-by: Lisa Watanabe <lwatanabe@riotgames.com>
Signed-off-by: Zvi Effron <zeffron@riotgames.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210707221657.3985075-3-zeffron@riotgames.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bf9252c..b46a383 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -324,9 +324,6 @@ union bpf_iter_link_info {
  *             **BPF_PROG_TYPE_SK_LOOKUP**
  *                     *data_in* and *data_out* must be NULL.
  *
- *             **BPF_PROG_TYPE_XDP**
- *                     *ctx_in* and *ctx_out* must be NULL.
- *
  *             **BPF_PROG_TYPE_RAW_TRACEPOINT**,
  *             **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
  *

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af3..229c5de 100644 (file)
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -15,6 +15,7 @@
 #include <linux/error-injection.h>
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
+#include <net/xdp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -687,6 +688,22 @@ out:
        return ret;
 }
 
+static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
+{
+       if (!xdp_md)
+               return 0;
+
+       if (xdp_md->egress_ifindex != 0)
+               return -EINVAL;
+
+       if (xdp_md->ingress_ifindex != 0 || xdp_md->rx_queue_index != 0)
+               return -EINVAL;
+
+       xdp->data = xdp->data_meta + xdp_md->data;
+
+       return 0;
+}
+
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
                          union bpf_attr __user *uattr)
 {
@@ -697,35 +714,69 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
        struct netdev_rx_queue *rxqueue;
        struct xdp_buff xdp = {};
        u32 retval, duration;
+       struct xdp_md *ctx;
        u32 max_data_sz;
        void *data;
-       int ret;
+       int ret = -EINVAL;
 
-       if (kattr->test.ctx_in || kattr->test.ctx_out)
-               return -EINVAL;
+       ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
+       if (IS_ERR(ctx))
+               return PTR_ERR(ctx);
+
+       if (ctx) {
+               /* There can't be user provided data before the meta data */
+               if (ctx->data_meta || ctx->data_end != size ||
+                   ctx->data > ctx->data_end ||
+                   unlikely(xdp_metalen_invalid(ctx->data)))
+                       goto free_ctx;
+               /* Meta data is allocated from the headroom */
+               headroom -= ctx->data;
+       }
 
        /* XDP have extra tailroom as (most) drivers use full page */
        max_data_sz = 4096 - headroom - tailroom;
 
        data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
-       if (IS_ERR(data))
-               return PTR_ERR(data);
+       if (IS_ERR(data)) {
+               ret = PTR_ERR(data);
+               goto free_ctx;
+       }
 
        rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
        xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
                      &rxqueue->xdp_rxq);
        xdp_prepare_buff(&xdp, data, headroom, size, true);
 
+       ret = xdp_convert_md_to_buff(ctx, &xdp);
+       if (ret)
+               goto free_data;
+
        bpf_prog_change_xdp(NULL, prog);
        ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
        if (ret)
                goto out;
-       if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
-               size = xdp.data_end - xdp.data;
-       ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+
+       if (xdp.data_meta != data + headroom ||
+           xdp.data_end != xdp.data_meta + size)
+               size = xdp.data_end - xdp.data_meta;
+
+       if (ctx) {
+               ctx->data = xdp.data - xdp.data_meta;
+               ctx->data_end = xdp.data_end - xdp.data_meta;
+       }
+
+       ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
+                             duration);
+       if (!ret)
+               ret = bpf_ctx_finish(kattr, uattr, ctx,
+                                    sizeof(struct xdp_md));
+
 out:
        bpf_prog_change_xdp(prog, NULL);
+free_data:
        kfree(data);
+free_ctx:
+       kfree(ctx);
        return ret;
 }