[PATCH 2/5] drm/nouveau/kms/nv50-: don't enable a DP output with no trained link
From: David R. Hedges via B4 Relay
Date: Tue Nov 03 2026 - 15:06:05 EST
From: "David R. Hedges" <linuxdev844@xxxxxxxxxxxxxxxx>
A commit that only turns a CRTC back on mustn't fail atomic check, so
it still reaches nv50_sor_atomic_enable() when the sink's link
capabilities have dropped below what the mode needs, or are unknown
because the sink stopped answering AUX. nouveau_dp_train() then has
nothing to train, and the SOR is attached to the head regardless. On
a GA102 with GSP-RM 570.144, mutter turning the screen back on while
the monitor was switched off (HPD still asserted, AUX not answering)
did exactly that, and the display engine hung: "core notifier
timeout", after which GSP stopped answering RPCs.
Have nouveau_dp_train() say why it failed. When no lane count and
link rate can carry the mode, leave the SOR detached, set the
connector's link-status to BAD and send a hotplug event, as the
link-status property's documentation describes. Userspace that
handles link-status can pick a new mode; userspace that doesn't still
gets the hotplug event and reprobes. When training is attempted and
fails, the output is enabled as before; only the case where there was
nothing to train changes.
The head produces no vblanks while the SOR is detached, so until the
sink is back and a modeset restarts the link, each commit to it waits
out the window channel's 2s timeout ("wndw-0: timeout"). On the
GA102 above that was the only side effect, with and without GSP-RM.
Link: https://gitlab.freedesktop.org/drm/nouveau/-/work_items/515
Signed-off-by: David R. Hedges <linuxdev844@xxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/nouveau/dispnv50/disp.c | 10 +++++++++-
drivers/gpu/drm/nouveau/nouveau_connector.c | 18 ++++++++++++++++++
drivers/gpu/drm/nouveau/nouveau_connector.h | 1 +
drivers/gpu/drm/nouveau/nouveau_dp.c | 13 +++++++++----
drivers/gpu/drm/nouveau/nouveau_encoder.h | 2 +-
5 files changed, 38 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 8af01de822d5..7f55c016d846 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -1843,7 +1843,15 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_commit *st
nvif_outp_lvds(&nv_encoder->outp, lvds_dual, lvds_8bpc);
break;
case DCB_OUTPUT_DP:
- nouveau_dp_train(nv_encoder, false, mode->clock, asyh->or.bpc);
+ /* Attaching the SOR to a link that hasn't been trained can hang
+ * the display engine. If the link can't carry the mode at all,
+ * which atomic check only rules out for a modeset, leave the
+ * output detached and tell userspace the link is bad.
+ */
+ if (nouveau_dp_train(nv_encoder, false, mode->clock, asyh->or.bpc) == -EINVAL) {
+ schedule_work(&nv_connector->link_bad_work);
+ return;
+ }
nv50_sor_dp_watermark_sst(nv_encoder, head, asyh);
depth = nv50_dp_bpc_to_depth(asyh->or.bpc);
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index cc3caf8de64b..cae4e35c30aa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -398,6 +398,7 @@ nouveau_connector_destroy(struct drm_connector *connector)
nvif_event_dtor(&nv_connector->irq);
nvif_event_dtor(&nv_connector->hpd);
cancel_work_sync(&nv_connector->irq_work);
+ cancel_work_sync(&nv_connector->link_bad_work);
drm_edid_free(nv_connector->drm_edid);
drm_connector_unregister(connector);
drm_connector_cleanup(connector);
@@ -1261,6 +1262,22 @@ nouveau_connector_funcs_lvds = {
.early_unregister = nouveau_connector_early_unregister,
};
+/* The sink isn't getting a picture with the current mode, and userspace may
+ * need to pick another one to get it back.
+ */
+static void
+nouveau_connector_link_bad(struct work_struct *work)
+{
+ struct nouveau_connector *nv_connector =
+ container_of(work, typeof(*nv_connector), link_bad_work);
+ struct drm_connector *connector = &nv_connector->base;
+
+ drm_dbg_kms(connector->dev, "[CONNECTOR:%d:%s] link-status bad\n",
+ connector->base.id, connector->name);
+ drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+ drm_kms_helper_connector_hotplug_event(connector);
+}
+
void
nouveau_connector_hpd(struct nouveau_connector *nv_connector, u64 bits)
{
@@ -1383,6 +1400,7 @@ nouveau_connector_create(struct drm_device *dev, int index)
connector = &nv_connector->base;
nv_connector->index = index;
INIT_WORK(&nv_connector->irq_work, nouveau_dp_irq);
+ INIT_WORK(&nv_connector->link_bad_work, nouveau_connector_link_bad);
if (disp->disp.conn_mask & BIT(nv_connector->index)) {
ret = nvif_conn_ctor(&disp->disp, nv_connector->base.name, nv_connector->index,
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index eb292d2ba4bc..3109278d36ea 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -134,6 +134,7 @@ struct nouveau_connector {
struct nvif_event hpd;
struct nvif_event irq;
struct work_struct irq_work;
+ struct work_struct link_bad_work;
struct drm_dp_aux aux;
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 019af307c669..9bc24f3914bd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -401,14 +401,17 @@ nouveau_dp_train_link(struct nouveau_encoder *outp, bool retrain)
return ret == 0;
}
-bool
+/* Returns -EINVAL if no lane count and link rate can carry the mode, in which
+ * case nothing has been trained, or -EIO if training failed.
+ */
+int
nouveau_dp_train(struct nouveau_encoder *outp, bool mst, u32 khz, u8 bpc)
{
struct nouveau_drm *drm = nouveau_drm(outp->base.base.dev);
struct drm_dp_aux *aux = &outp->conn->aux;
u32 min_rate;
u8 pwr;
- bool ret = true;
+ int ret = -EINVAL;
if (mst)
min_rate = outp->dp.link_nr * outp->dp.rate[0].rate;
@@ -434,13 +437,15 @@ nouveau_dp_train(struct nouveau_encoder *outp, bool mst, u32 khz, u8 bpc)
outp->dp.lt.nr = nr;
outp->dp.lt.bw = outp->dp.rate[rate].rate;
outp->dp.lt.mst = mst;
- if (nouveau_dp_train_link(outp, false))
+ if (nouveau_dp_train_link(outp, false)) {
+ ret = 0;
goto done;
+ }
+ ret = -EIO;
}
}
}
- ret = false;
done:
mutex_unlock(&outp->dp.hpd_irq_lock);
return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h
index 4422c6185d49..9366678e7d05 100644
--- a/drivers/gpu/drm/nouveau/nouveau_encoder.h
+++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h
@@ -156,7 +156,7 @@ enum nouveau_dp_status {
};
int nouveau_dp_detect(struct nouveau_connector *, struct nouveau_encoder *);
-bool nouveau_dp_train(struct nouveau_encoder *, bool mst, u32 khz, u8 bpc);
+int nouveau_dp_train(struct nouveau_encoder *outp, bool mst, u32 khz, u8 bpc);
void nouveau_dp_power_down(struct nouveau_encoder *);
bool nouveau_dp_link_check(struct nouveau_connector *);
void nouveau_dp_irq(struct work_struct *);
--
2.55.0