summaryrefslogtreecommitdiffstats
path: root/Documentation/ABI/testing/debugfs-ec
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2026-09-14 22:12:34 -1000
committerTejun Heo <tj@kernel.org>2026-09-15 06:57:20 -1000
commita9e3760b0838299649c0d57cca44daaf40ba3c33 (patch)
tree95807ff0e511c05602ef34808cfc660303309057 /Documentation/ABI/testing/debugfs-ec
downloadlinux-stable-a9e3760b0838299649c0d57cca44daaf40ba3c33.tar.gz
linux-stable-a9e3760b0838299649c0d57cca44daaf40ba3c33.zip
sched_ext: Maintain an online cid mask in the scheduler arenagrafted
Schedulers on the default cid mapping treat [0, nr_online_cids) as the online set and restart on hotplug. Schedulers that install their own mapping with scx_bpf_cid_override() have no way to learn which cids are online: the count no longer identifies members and the CPU-form cpumask is unusable from cid programs. This is an obvious hole in the cid API. Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's arena, allocated alongside the per-CPU scratch masks and populated after the cid mapping is finalized and before ops.init(), for child schedulers too. The pointer stays valid through ops.exit() with no reference to take. It is the arena offset as a void pointer, the same form struct_ops arena arguments arrive in. The verifier types the void return as a scalar for the program's arena cast. The mask follows the SCX hotplug notifications: seeded from cpu_active_mask and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask only inside a hotplug transition. Updates walk the scheduler list under the lock that also serializes unlinking. Reads are live, not atomic snapshots. Root initialization excludes hotplug. v2: Reworded the getter kerneldoc (Andrea Righi). Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Andrea Righi <arighi@nvidia.com>
Diffstat (limited to 'Documentation/ABI/testing/debugfs-ec')
-rw-r--r--Documentation/ABI/testing/debugfs-ec21
1 files changed, 21 insertions, 0 deletions
diff --git a/Documentation/ABI/testing/debugfs-ec b/Documentation/ABI/testing/debugfs-ec
new file mode 100644
index 000000000..ab6099daa
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-ec
@@ -0,0 +1,21 @@
+What: /sys/kernel/debug/ec/*/{gpe,use_global_lock,io}
+Date: July 2010
+Contact: Thomas Renninger <trenn@suse.de>
+Description:
+
+General information like which GPE is assigned to the EC and whether
+the global lock should get used.
+Knowing the EC GPE one can watch the amount of HW events related to
+the EC here (XY -> GPE number from `/sys/kernel/debug/ec/*/gpe`):
+/sys/firmware/acpi/interrupts/gpeXY
+
+The io file is binary and a userspace tool located here:
+ftp://ftp.suse.com/pub/people/trenn/sources/ec/
+should get used to read out the 256 Embedded Controller registers
+or writing to them.
+
+CAUTION:
+ Do not write to the Embedded Controller if you don't know
+ what you are doing! Rebooting afterwards also is a good idea.
+ This can influence the way your machine is cooled and fans may
+ not get switched on again after you did a wrong write.