[PATCH v2 3/4] drm/xe/hw_error: Allow debugging hardware errors

[Raag Jadav <raag.jadav@intel.com>]

Hardware errors are reported through System Controller on the platforms
that support it, and never routed as direct IRQ to SGUnit other than
debug cases. Wedge the device on XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET
so that the hardware errors are available to the user for debugging.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v2: Explain the usecase (Matt Roper)
---
 drivers/gpu/drm/xe/xe_hw_error.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index c7b720ba5a4f..79a85925a02f 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -169,11 +169,14 @@ static void hw_error_work(struct work_struct *work)
 {
 	struct xe_tile *tile = container_of(work, typeof(*tile), hw_error_work);
 	struct xe_device *xe = tile_to_xe(tile);
-	int ret;
+	bool wedge = xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET;
 
-	ret = xe_survivability_mode_runtime_enable(xe);
-	if (ret)
-		drm_err(&xe->drm, "Failed to enable runtime survivability mode\n");
+	if (wedge) {
+		xe_device_declare_wedged(xe);
+		return;
+	}
+
+	xe_survivability_mode_runtime_enable(xe);
 }
 
 static void csc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
@@ -433,6 +436,19 @@ static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_er
 	if (!IS_DGFX(xe))
 		return;
 
+	if (xe->info.has_sysctrl) {
+		/*
+		 * Hardware errors are reported through System Controller on the platforms that
+		 * support it, so we should never be here other than debug cases. Retain the
+		 * hardware state and bail without clearing error registers, so that they are
+		 * available to the user for debugging.
+		 */
+		drm_err_ratelimited(&xe->drm, HW_ERR "Tile%d reported %s error\n",
+				    tile->id, severity_str);
+		schedule_work(&tile->hw_error_work);
+		return;
+	}
+
 	spin_lock_irqsave(&xe->irq.lock, flags);
 	err_src = xe_mmio_read32(&tile->mmio, DEV_ERR_STAT_REG(hw_err));
 	if (!err_src) {
-- 
2.43.0