[PATCH] drm/amd/display: add module param to disable immediate vblank off

[Michele Palazzi <sysdadmin@m1k.cloud>]

Add amdgpu.no_vblank_immediate parameter to optionally disable the
immediate vblank disable path on DCN35+ non-PSR CRTCs. When set to 1,
a 2-frame offdelay is used instead, matching the behavior used for
older hardware and DGPUs.

This works around flip_done timeouts and GPU hangs that some users
experience with the immediate vblank disable path, particularly with
DisplayPort connections. The default behavior is unchanged.

This is a temporary workaround, to be removed once the underlying
vblank/DM locking issue is properly resolved.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3787
Signed-off-by: Michele Palazzi <sysdadmin@m1k.cloud>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h             |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c         | 16 ++++++++++++++++
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c   | 17 ++++++++++++++---
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b20a06abb65d..5de60af8c5f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -213,6 +213,7 @@ extern uint amdgpu_dc_visual_confirm;
 extern int amdgpu_dm_abm_level;
 extern int amdgpu_backlight;
 extern int amdgpu_damage_clips;
+extern int amdgpu_no_vblank_immediate;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 39387da8586b..94cab76805ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -924,6 +924,22 @@ MODULE_PARM_DESC(damageclips,
 		 "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
 module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
 
+/**
+ * DOC: no_vblank_immediate (int)
+ * Disable immediate vblank disable on DCN35+ non-PSR CRTCs. Use a 2-frame
+ * offdelay instead, matching the behavior used for older hardware and DGPUs.
+ * This works around flip_done timeouts that cause GPU hangs on some hardware
+ * with DisplayPort connections.
+ * (0 = use default immediate disable (default), 1 = use 2-frame offdelay)
+ *
+ * This is a temporary workaround and should be removed once the underlying
+ * vblank/DM locking issue is resolved.
+ */
+int amdgpu_no_vblank_immediate;
+MODULE_PARM_DESC(no_vblank_immediate,
+	"Disable immediate vblank off on DCN35+ (0 = default, 1 = use 2-frame offdelay)");
+module_param_named(no_vblank_immediate, amdgpu_no_vblank_immediate, int, 0444);
+
 /**
  * DOC: tmz (int)
  * Trusted Memory Zone (TMZ) is a method to protect data being written
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a8a59126b2d2..e18ad3949826 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9335,9 +9335,20 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 
 			config.offdelay_ms = offdelay ?: 30;
 		} else {
-			/* offdelay_ms = 0 will never disable vblank */
-			config.offdelay_ms = 1;
-			config.disable_immediate = true;
+			if (amdgpu_no_vblank_immediate) {
+				/*
+				 * Use 2-frame offdelay instead of immediate
+				 * disable to work around flip_done timeouts.
+				 */
+				offdelay = DIV64_U64_ROUND_UP((u64)20 *
+							      timing->v_total *
+							      timing->h_total,
+							      timing->pix_clk_100hz);
+				config.offdelay_ms = offdelay ?: 30;
+			} else {
+				config.offdelay_ms = 1;
+				config.disable_immediate = true;
+			}
 		}
 
 		drm_crtc_vblank_on_config(&acrtc->base,
-- 
2.53.0