drm/xe/nvlp: Implement Wa_14026539277

Implement the KMD part of Wa_14026539277, which applies to NVL-P A0.
The KMD implementation is just one component of the workaround, which
also depends on Pcode to implement its part in order to be complete.

v2:
  - Add FUNC(xe_rtp_match_not_sriov_vf) to skip applying the workaround
    to SRIOV VFs. (Matt)
v3:
  - Make Wa_14026539277 a device workaround instead of a GT workaround.
    (Matt)
v4:
  - Drop FUNC(xe_rtp_match_not_sriov_vf) and use a direct check with
    IS_SRIOV_VF() in the workaround implementation. (Matt)

Reviewed-by: Matt Roper <matthew.d.roper@intel.com> # v3
Link: https://patch.msgid.link/20260309-extra-nvl-p-enabling-patches-v5-5-be9c902ee34e@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>

3 files changed, 44 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 4ee88f629c02..daef5f66955a 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -456,6 +456,10 @@
 
 #define XEHPC_L3CLOS_MASK(i)			XE_REG_MCR(0xb194 + (i) * 8)
 
+#define L2COMPUTESIDECTRL			XE_REG_MCR(0xb1c0)
+#define   CECTRL				REG_GENMASK(2, 1)
+#define   CECTRL_CENODATA_ALWAYS		REG_FIELD_PREP(CECTRL, 0x0)
+
 #define XE2_GLOBAL_INVAL			XE_REG(0xb404)
 
 #define XE2LPM_L3SQCREG2			XE_REG_MCR(0xb604)
diff --git a/drivers/gpu/drm/xe/xe_device_wa_oob.rules b/drivers/gpu/drm/xe/xe_device_wa_oob.rules
index 55ba01bc8f38..d129cddb6ead 100644
--- a/drivers/gpu/drm/xe/xe_device_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_device_wa_oob.rules
@@ -3,3 +3,4 @@
 		PLATFORM(PANTHERLAKE)
 22019338487_display	PLATFORM(LUNARLAKE)
 14022085890	SUBPLATFORM(BATTLEMAGE, G21)
+14026539277	PLATFORM(NOVALAKE_P), PLATFORM_STEP(A0, B0)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index f3bb856aad2a..bae895fa066a 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -10,6 +10,7 @@
 #include <drm/drm_managed.h>
 #include <uapi/drm/xe_drm.h>
 
+#include <generated/xe_device_wa_oob.h>
 #include <generated/xe_wa_oob.h>
 
 #include "instructions/xe_alu_commands.h"
@@ -451,6 +452,35 @@ put_exec_queue:
 	return err;
 }
 
+static void wa_14026539277(struct xe_gt *gt)
+{
+	struct xe_device *xe = gt_to_xe(gt);
+	u32 val;
+
+	/*
+	 * FIXME: We currently can't use FUNC(xe_rtp_match_not_sriov_vf) in the
+	 * rules for Wa_14026539277 due to xe_wa_process_device_oob() being
+	 * called before xe_sriov_probe_early(); and we can't move the call to
+	 * the former to happen after the latter because MMIO read functions
+	 * already depend on a device OOB workaround.  This needs to be fixed by
+	 * allowing workaround checks to happen at different stages of driver
+	 * initialization.
+	 */
+	if (IS_SRIOV_VF(xe))
+		return;
+
+	if (!XE_DEVICE_WA(xe, 14026539277))
+		return;
+
+	if (!xe_gt_is_main_type(gt))
+		return;
+
+	val = xe_gt_mcr_unicast_read_any(gt, L2COMPUTESIDECTRL);
+	val &= ~CECTRL;
+	val |= CECTRL_CENODATA_ALWAYS;
+	xe_gt_mcr_multicast_write(gt, L2COMPUTESIDECTRL, val);
+}
+
 int xe_gt_init_early(struct xe_gt *gt)
 {
 	int err;
@@ -576,6 +606,15 @@ static int gt_init_with_gt_forcewake(struct xe_gt *gt)
 	 */
 	gt->info.gmdid = xe_mmio_read32(&gt->mmio, GMD_ID);
 
+	/*
+	 * Wa_14026539277 can't be implemented as a regular GT workaround (i.e.
+	 * as an entry in gt_was[]) for two reasons: it is actually a device
+	 * workaround that happens to involve programming a GT register; and it
+	 * needs to be applied early to avoid getting the hardware in a bad
+	 * state before we have a chance to do the necessary programming.
+	 */
+	wa_14026539277(gt);
+
 	return 0;
 }