sched_ext: Provide a sysfs enable_seq counter

As discussed during the distro-centric session within the sched_ext
Microconference at LPC 2024, introduce a sequence counter that is
incremented every time a BPF scheduler is loaded.

This feature can help distributions in diagnosing potential performance
regressions by identifying systems where users are running (or have ran)
custom BPF schedulers.

Example:

 arighi@virtme-ng~> cat /sys/kernel/sched_ext/enable_seq
 0
 arighi@virtme-ng~> sudo scx_simple
 local=1 global=0
 ^CEXIT: unregistered from user space
 arighi@virtme-ng~> cat /sys/kernel/sched_ext/enable_seq
 1

In this way user-space tools (such as Ubuntu's apport and similar) are
able to gather and include this information in bug reports.

Cc: Giovanni Gherdovich <giovanni.gherdovich@suse.com>
Cc: Kleber Sacilotto de Souza <kleber.souza@canonical.com>
Cc: Marcelo Henrique Cerri <marcelo.cerri@canonical.com>
Cc: Phil Auld <pauld@redhat.com>
Signed-off-by: Andrea Righi <andrea.righi@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index a707d2181a77d7655fbc88c7cf13f1f2402b8668..6c0d70e2e27df5af29dd82ff8d382ac6d0926246 100644 (file)
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -83,6 +83,15 @@ The current status of the BPF scheduler can be determined as follows:
     # cat /sys/kernel/sched_ext/root/ops
     simple
 
+You can check if any BPF scheduler has ever been loaded since boot by examining
+this monotonically incrementing counter (a value of zero indicates that no BPF
+scheduler has been loaded):
+
+.. code-block:: none
+
+    # cat /sys/kernel/sched_ext/enable_seq
+    1
+
 ``tools/sched_ext/scx_show_state.py`` is a drgn script which shows more
 detailed information:
 
@@ -96,6 +105,7 @@ detailed information:
     enable_state  : enabled (2)
     bypass_depth  : 0
     nr_rejected   : 0
+    enable_seq    : 1
 
 If ``CONFIG_SCHED_DEBUG`` is set, whether a given task is on sched_ext can
 be determined as follows:

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 7c320dcd72d52fa815f8106a22570a7037d17111..c09e3dc38c343b7a69fe3bcbdce01248f6aedb7a 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -874,6 +874,13 @@ static struct scx_exit_info *scx_exit_info;
 static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0);
 static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0);
 
+/*
+ * A monotically increasing sequence number that is incremented every time a
+ * scheduler is enabled. This can be used by to check if any custom sched_ext
+ * scheduler has ever been used in the system.
+ */
+static atomic_long_t scx_enable_seq = ATOMIC_LONG_INIT(0);
+
 /*
  * The maximum amount of time in jiffies that a task may be runnable without
  * being scheduled on a CPU. If this timeout is exceeded, it will trigger
@@ -4154,11 +4161,19 @@ static ssize_t scx_attr_hotplug_seq_show(struct kobject *kobj,
 }
 SCX_ATTR(hotplug_seq);
 
+static ssize_t scx_attr_enable_seq_show(struct kobject *kobj,
+                                       struct kobj_attribute *ka, char *buf)
+{
+       return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_enable_seq));
+}
+SCX_ATTR(enable_seq);
+
 static struct attribute *scx_global_attrs[] = {
        &scx_attr_state.attr,
        &scx_attr_switch_all.attr,
        &scx_attr_nr_rejected.attr,
        &scx_attr_hotplug_seq.attr,
+       &scx_attr_enable_seq.attr,
        NULL,
 };
 
@@ -5177,6 +5192,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
        kobject_uevent(scx_root_kobj, KOBJ_ADD);
        mutex_unlock(&scx_ops_enable_mutex);
 
+       atomic_long_inc(&scx_enable_seq);
+
        return 0;
 
 err_del:

diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py
index d457d2a74e1efec884ae1348e257c5d890f1e8cf..8bc626ede1c485e19d0ad1b75cc2fb9bc56e0305 100644 (file)
--- a/tools/sched_ext/scx_show_state.py
+++ b/tools/sched_ext/scx_show_state.py
@@ -37,3 +37,4 @@ print(f'switched_all  : {read_static_key("__scx_switched_all")}')
 print(f'enable_state  : {ops_state_str(enable_state)} ({enable_state})')
 print(f'bypass_depth  : {read_atomic("scx_ops_bypass_depth")}')
 print(f'nr_rejected   : {read_atomic("scx_nr_rejected")}')
+print(f'enable_seq    : {read_atomic("scx_enable_seq")}')