bpf: Do not invoke the XDP dispatcher for PROG_RUN with single repeat

We have a unit test that invokes an XDP program with 1m different
inputs, aka 1m BPF_PROG_RUN syscalls. We run this test concurrently
with slight variations in how we generated the input.

Since commit f23c4b3924d2 ("bpf: Start using the BPF dispatcher in BPF_TEST_RUN")
the unit test has slowed down significantly. Digging deeper reveals that
the concurrent tests are serialised in the kernel on the XDP dispatcher.
This is a global resource that is protected by a mutex, on which we contend.

Fix this by not calling into the XDP dispatcher if we only want to perform
a single run of the BPF program.

See: https://lore.kernel.org/bpf/CACAyw9_y4QumOW35qpgTbLsJ532uGq-kVW-VESJzGyiZkypnvw@mail.gmail.com/

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210928093100.27124-1-lmb@cloudflare.com

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fcb2f493f710a418549e7cff1b3f24766eb9234c..6593a71dba5f07d865f3ca64862003622f0cebe0 100644 (file)
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -803,7 +803,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
        if (ret)
                goto free_data;
 
-       bpf_prog_change_xdp(NULL, prog);
+       if (repeat > 1)
+               bpf_prog_change_xdp(NULL, prog);
        ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
        /* We convert the xdp_buff back to an xdp_md before checking the return
         * code so the reference count of any held netdevice will be decremented
@@ -824,7 +825,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
                                     sizeof(struct xdp_md));
 
 out:
-       bpf_prog_change_xdp(prog, NULL);
+       if (repeat > 1)
+               bpf_prog_change_xdp(prog, NULL);
 free_data:
        kfree(data);
 free_ctx: