linux-kernel - [PATCH 15/17] cgroup/drm: Expose GPU utilisation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230712114605.519432-16-tvrtko.ursulin@linux.intel.com>
Date:   Wed, 12 Jul 2023 12:46:03 +0100
From:   Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>
To:     Intel-gfx@...ts.freedesktop.org, dri-devel@...ts.freedesktop.org
Cc:     cgroups@...r.kernel.org, linux-kernel@...r.kernel.org,
        Tejun Heo <tj@...nel.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Zefan Li <lizefan.x@...edance.com>,
        Dave Airlie <airlied@...hat.com>,
        Daniel Vetter <daniel.vetter@...ll.ch>,
        Rob Clark <robdclark@...omium.org>,
        Stéphane Marchesin <marcheu@...omium.org>,
        "T . J . Mercier" <tjmercier@...gle.com>, Kenny.Ho@....com,
        Christian König <christian.koenig@....com>,
        Brian Welty <brian.welty@...el.com>,
        Tvrtko Ursulin <tvrtko.ursulin@...el.com>,
        Eero Tamminen <eero.t.tamminen@...el.com>
Subject: [PATCH 15/17] cgroup/drm: Expose GPU utilisation

From: Tvrtko Ursulin <tvrtko.ursulin@...el.com>

To support container use cases where external orchestrators want to make
deployment and migration decisions based on GPU load and capacity, we can
expose the GPU load as seen by the controller in a new drm.active_us
field. This field contains a monotonic cumulative time cgroup has spent
executing GPU loads, as reported by the DRM drivers being used by group
members.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@...el.com>
Cc: Tejun Heo <tj@...nel.org>
Cc: Eero Tamminen <eero.t.tamminen@...el.com>
---
 Documentation/admin-guide/cgroup-v2.rst |  3 +++
 kernel/cgroup/drm.c                     | 26 ++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index da350858c59f..bbe986366f4a 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2445,6 +2445,9 @@ will be respected.
 DRM scheduling soft limits interface files
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+  drm.active_us
+	GPU time used by the group recursively including all child groups.
+
   drm.weight
 	Standard cgroup weight based control [1, 10000] used to configure the
 	relative distributing of GPU time between the sibling groups.
diff --git a/kernel/cgroup/drm.c b/kernel/cgroup/drm.c
index b244e3d828cc..7c20d4ebc634 100644
--- a/kernel/cgroup/drm.c
+++ b/kernel/cgroup/drm.c
@@ -25,6 +25,8 @@ struct drm_cgroup_state {
 	bool over;
 	bool over_budget;
 
+	u64 total_us;
+
 	u64 per_s_budget_us;
 	u64 prev_active_us;
 	u64 active_us;
@@ -117,6 +119,20 @@ drmcs_write_weight(struct cgroup_subsys_state *css, struct cftype *cftype,
 	return 0;
 }
 
+static u64
+drmcs_read_total_us(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct drm_cgroup_state *drmcs = css_to_drmcs(css);
+	u64 val;
+
+	/* Mutex being overkill unless arch cannot atomically read u64.. */
+	mutex_lock(&drmcg_mutex);
+	val = drmcs->total_us;
+	mutex_unlock(&drmcg_mutex);
+
+	return val;
+}
+
 static bool __start_scanning(unsigned int period_us)
 {
 	struct drm_cgroup_state *root = &root_drmcs.drmcs;
@@ -169,11 +185,14 @@ static bool __start_scanning(unsigned int period_us)
 		parent = css_to_drmcs(node->parent);
 
 		active = drmcs_get_active_time_us(drmcs);
-		if (period_us && active > drmcs->prev_active_us)
+		if (period_us && active > drmcs->prev_active_us) {
 			drmcs->active_us += active - drmcs->prev_active_us;
+			drmcs->total_us += drmcs->active_us;
+		}
 		drmcs->prev_active_us = active;
 
 		parent->active_us += drmcs->active_us;
+		parent->total_us += drmcs->active_us;
 		parent->sum_children_weights += drmcs->weight;
 
 		css_put(node);
@@ -551,6 +570,11 @@ struct cftype files[] = {
 		.read_u64 = drmcs_read_weight,
 		.write_u64 = drmcs_write_weight,
 	},
+	{
+		.name = "active_us",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = drmcs_read_total_us,
+	},
 	{ } /* Zero entry terminates. */
 };
 
-- 
2.39.2