Hi Andrii,
On 4/20/22 10:07, Andrii Nakryiko wrote:
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 128028efda64..5a64cece09f3 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -723,10 +723,8 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
pl->link = NULL;
err = update_effective_progs(cgrp, atype);
- if (err)
- goto cleanup;
- /* now can actually delete it from this cgroup list */
+ /* now can delete it from this cgroup list */
list_del(&pl->node);
kfree(pl);
if (list_empty(progs))
@@ -735,12 +733,55 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
if (old_prog)
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key[atype]);
- return 0;
+
+ if (!err)
+ return 0;
cleanup:
- /* restore back prog or link */
- pl->prog = old_prog;
- pl->link = link;
+ /*
+ * If compute_effective_progs failed with -ENOMEM, i.e. alloc for
+ * cgrp->bpf.inactive table failed, we can recover by removing
+ * the detached prog from effective table and rearranging it.
+ */
+ if (err == -ENOMEM) {
+ struct bpf_prog_array_item *item;
+ struct bpf_prog *prog_tmp, *prog_detach, *prog_last;
+ struct bpf_prog_array *array;
+ int index = 0, index_detach = -1;
+
+ array = cgrp->bpf.effective[atype];
+ item = &array->items[0];
+
+ if (prog)
+ prog_detach = prog;
+ else
+ prog_detach = link->link.prog;
+
+ if (!prog_detach)
+ return -EINVAL;
+
+ while ((prog_tmp = READ_ONCE(item->prog))) {
+ if (prog_tmp == prog_detach)
+ index_detach = index;
+ item++;
+ index++;
+ prog_last = prog_tmp;
+ }
+
+ /* Check if we found what's needed for removing the prog */
+ if (index_detach == -1 || index_detach == index-1)
+ return -EINVAL;
+
+ /* Remove the last program in the array */
+ if (bpf_prog_array_delete_safe_at(array, index-1))
+ return -EINVAL;
+
+ /* and update the detached with the last just removed */
+ if (bpf_prog_array_update_at(array, index_detach, prog_last))
+ return -EINVAL;
+
+ err = 0;
+ }
Thanks for feedback, and sorry for delay. I got pulled into something else.
There are a bunch of problems with this implementation.
1. We should do this fallback right after update_effective_progs()
returns error, before we get to list_del(&pl->node) and subsequent
code that does some additional things (like clearing flags and stuff).
This additional code needs to run even if update_effective_progs()
fails. So I suggest to extract the logic of removing program from
effective prog arrays into a helper function and doing
err = update_effective_progs(...);
if (err)
purge_effective_progs();
where purge_effective_progs() will be the logic you are adding. And it
will be void function because it can't fail.
I have implemented that in v3, will send that out soon.
2. We have to update not just cgrp->bpf.effective array, but all the
descendants' lists as well. See what update_effective_progs() is
doing, it has css_for_each_descendant_pre() iteration. You need to do
it here as well. But instead of doing compute_effective_progs() which
allocates a new copy of an array we'll need to update existing array
in place.
3. Not clear why you need to do both bpf_prog_array_delete_safe_at()
and bpf_prog_array_update_at(), isn't delete_safe_at() enought?
I thought that we need to reshuffle the table and move the progs around,
but your are right, delete_safe_at() is enough.
--
Thanks,
Tadeusz
