[PATCH 09/10] drm/xe: Clear SOC CORRECTABLE error registers.

[Aravind Iddamsetty]

From: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>

PVC doesn't support correctable SOC error reporting, classify them as
Undefined and clear the registers.

v2
- Fix commit message.
- Although the errors are correctable but they are spurious interrupt.
Hence use drm_err instead of drm_warn.(Aravind)

Cc: Aravind Iddamsetty <aravind.iddamsetty at linux.intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty at linux.intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
---
 drivers/gpu/drm/xe/xe_hw_error.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 690b7df7ccba..a77779eb6ce8 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -624,13 +624,31 @@ xe_soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
 	if (tile_to_xe(tile)->info.platform != XE_PVC)
 		return;
 
-	if (hw_err == HARDWARE_ERROR_CORRECTABLE)
-		return;
-
 	base = SOC_PVC_BASE;
 	slave_base = SOC_PVC_SLAVE_BASE;
 	err_regs = &tile_to_xe(tile)->hw_err_regs;
 
+	if (hw_err == HARDWARE_ERROR_CORRECTABLE) {
+		for (i = 0; i < XE_SOC_NUM_IEH; i++)
+			xe_mmio_write32(&gt->tile->mmio, SOC_GSYSEVTCTL_REG(base, slave_base, i),
+					~REG_BIT(hw_err));
+
+		xe_mmio_write32(&gt->tile->mmio, SOC_GLOBAL_ERR_STAT_MASTER_REG(base, hw_err),
+				REG_GENMASK(31, 0));
+		xe_mmio_write32(&gt->tile->mmio, SOC_LOCAL_ERR_STAT_MASTER_REG(base, hw_err),
+				REG_GENMASK(31, 0));
+		xe_mmio_write32(&gt->tile->mmio, SOC_GLOBAL_ERR_STAT_SLAVE_REG(slave_base, hw_err),
+				REG_GENMASK(31, 0));
+		xe_mmio_write32(&gt->tile->mmio, SOC_LOCAL_ERR_STAT_SLAVE_REG(slave_base, hw_err),
+				REG_GENMASK(31, 0));
+
+		drm_err(&tile_to_xe(tile)->drm, HW_ERR
+			"Tile%d reported Undefine SOC CORRECTABLE error.",
+			tile->id);
+
+		goto unmask_gsysevtctl;
+	}
+
 	/*
 	 * Mask error type in GSYSEVTCTL so that no new errors of the type
 	 * will be reported. Read the master global IEH error register if
@@ -707,6 +725,7 @@ xe_soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
 	xe_mmio_write32(&gt->tile->mmio, SOC_GLOBAL_ERR_STAT_MASTER_REG(base, hw_err),
 			mst_glb_errstat);
 
+unmask_gsysevtctl:
 	for (i = 0; i < XE_SOC_NUM_IEH; i++)
 		xe_mmio_write32(&gt->tile->mmio, SOC_GSYSEVTCTL_REG(base, slave_base, i),
 				(HARDWARE_ERROR_MAX << 1) + 1);
-- 
2.25.1