sched_ext: Make qmap dump operation non-destructive

The qmap dump operation was destructively consuming queue entries while
displaying them. As dump can be triggered anytime, this can easily lead to
stalls. Add a temporary dump_store queue and modify the dump logic to pop
entries, display them, and then restore them back to the original queue.
This allows dump operations to be performed without affecting the
scheduler's queue state.

Note that if racing against new enqueues during dump, ordering can get
mixed up, but this is acceptable for debugging purposes.

Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 69d877501cb727fc315d2619af1a430f26da5d9e..cd50a94326e3a929bbe7dc439d62348ec34e26b2 100644 (file)
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -56,7 +56,8 @@ struct qmap {
   queue1 SEC(".maps"),
   queue2 SEC(".maps"),
   queue3 SEC(".maps"),
-  queue4 SEC(".maps");
+  queue4 SEC(".maps"),
+  dump_store SEC(".maps");
 
 struct {
        __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
@@ -578,11 +579,26 @@ void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx)
                        return;
 
                scx_bpf_dump("QMAP FIFO[%d]:", i);
+
+               /*
+                * Dump can be invoked anytime and there is no way to iterate in
+                * a non-destructive way. Pop and store in dump_store and then
+                * restore afterwards. If racing against new enqueues, ordering
+                * can get mixed up.
+                */
                bpf_repeat(4096) {
                        if (bpf_map_pop_elem(fifo, &pid))
                                break;
+                       bpf_map_push_elem(&dump_store, &pid, 0);
                        scx_bpf_dump(" %d", pid);
                }
+
+               bpf_repeat(4096) {
+                       if (bpf_map_pop_elem(&dump_store, &pid))
+                               break;
+                       bpf_map_push_elem(fifo, &pid, 0);
+               }
+
                scx_bpf_dump("\n");
        }
 }