drm/xe: Apply whitelist to engine save-restore

Instead of handling the whitelist directly in the GuC ADS
initialization, make it follow the same logic as other engine registers
that are save-restored. Main benefit is that then the SW tracking then
shows it in debugfs and there's no risk of an engine workaround to write
to the same nopriv register that is being passed directly to GuC.

This means that xe_reg_whitelist_process_engine() only has to process
the RTP and convert them to entries for the hwe. With that all the
registers should be covered by xe_reg_sr_apply_mmio() to write to the HW
and there's no special handling in GuC ADS to also add these registers
to the list of registers that is passed to GuC.

Example for DG2:

# cat /sys/kernel/debug/dri/0000\:03\:00.0/gt0/register-save-restore
...
Engine
rcs0
...
REG[0x24d0] clr=0xffffffff set=0x1000dafc masked=no mcr=no
REG[0x24d4] clr=0xffffffff set=0x1000db01 masked=no mcr=no
REG[0x24d8] clr=0xffffffff set=0x0000db1c masked=no mcr=no
...
Whitelist
rcs0
REG[0xdafc-0xdaff]: allow read access
REG[0xdb00-0xdb1f]: allow read access
REG[0xdb1c-0xdb1f]: allow rw access

v2:
- Use ~0u for clr bits so it's just a write (Matt Roper)
- Simplify helpers now that unused slots are not written

Reviewed-by: Matt Roper <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]
Signed-off-by: Lucas De Marchi <[e-mail]>

drivers/gpu/drm/xe/xe_gt.c

···
 	if (err)
 		return err;
 
-	for_each_hw_engine(hwe, gt, id) {
+	for_each_hw_engine(hwe, gt, id)
 		xe_reg_sr_apply_mmio(&hwe->reg_sr, gt);
-		xe_reg_sr_apply_whitelist(hwe);
-	}
 
 	/* Get CCS mode in sync between sw/hw */
 	xe_gt_apply_ccs_mode(gt);

drivers/gpu/drm/xe/xe_guc_ads.c

···
 		xa_for_each(&hwe->reg_sr.xa, sr_idx, sr_entry)
 			count++;
 
-	count += RING_MAX_NONPRIV_SLOTS * XE_NUM_HW_ENGINES;
-
 	count += ADS_REGSET_EXTRA_MAX * XE_NUM_HW_ENGINES;
 
 	if (XE_WA(gt, 1607983814))
···
 
 	xa_for_each(&hwe->reg_sr.xa, idx, entry)
 		guc_mmio_regset_write_one(ads, regset_map, entry->reg, count++);
-
-	for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++)
-		guc_mmio_regset_write_one(ads, regset_map,
-					  RING_FORCE_TO_NONPRIV(hwe->mmio_base, i),
-					  count++);
 
 	for (e = extra_regs; e < extra_regs + ARRAY_SIZE(extra_regs); e++) {
 		if (e->skip)

drivers/gpu/drm/xe/xe_hw_engine.c

···
 	xe_gt_assert(gt, gt->info.engine_mask & BIT(id));
 
 	xe_reg_sr_apply_mmio(&hwe->reg_sr, gt);
-	xe_reg_sr_apply_whitelist(hwe);
 
 	hwe->hwsp = xe_managed_bo_create_pin_map(xe, tile, SZ_4K,
 						 XE_BO_FLAG_VRAM_IF_DGFX(tile) |

drivers/gpu/drm/xe/xe_reg_sr.c

···
 #include "xe_hw_engine_types.h"
 #include "xe_macros.h"
 #include "xe_mmio.h"
-#include "xe_reg_whitelist.h"
 #include "xe_rtp_types.h"
 
 static void reg_sr_fini(struct drm_device *drm, void *arg)
···
 
 	xa_for_each(&sr->xa, reg, entry)
 		apply_one_mmio(gt, entry);
-
-	xe_force_wake_put(gt_to_fw(gt), fw_ref);
-
-	return;
-
-err_force_wake:
-	xe_force_wake_put(gt_to_fw(gt), fw_ref);
-	xe_gt_err(gt, "Failed to apply, err=-ETIMEDOUT\n");
-}
-
-void xe_reg_sr_apply_whitelist(struct xe_hw_engine *hwe)
-{
-	struct xe_reg_sr *sr = &hwe->reg_whitelist;
-	struct xe_gt *gt = hwe->gt;
-	struct xe_reg_sr_entry *entry;
-	struct drm_printer p;
-	u32 mmio_base = hwe->mmio_base;
-	unsigned long reg;
-	unsigned int slot = 0;
-	unsigned int fw_ref;
-
-	if (xa_empty(&sr->xa))
-		return;
-
-	xe_gt_dbg(gt, "Whitelisting %s registers\n", sr->name);
-
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
-		goto err_force_wake;
-
-	p = xe_gt_dbg_printer(gt);
-	xa_for_each(&sr->xa, reg, entry) {
-		if (slot == RING_MAX_NONPRIV_SLOTS) {
-			xe_gt_err(gt,
-				  "hwe %s: maximum register whitelist slots (%d) reached, refusing to add more\n",
-				  hwe->name, RING_MAX_NONPRIV_SLOTS);
-			break;
-		}
-
-		xe_reg_whitelist_print_entry(&p, 0, reg, entry);
-		xe_mmio_write32(&gt->mmio, RING_FORCE_TO_NONPRIV(mmio_base, slot),
-				reg | entry->set_bits);
-		slot++;
-	}
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 

drivers/gpu/drm/xe/xe_reg_whitelist.c

···
 #include "regs/xe_oa_regs.h"
 #include "regs/xe_regs.h"
 #include "xe_gt_types.h"
+#include "xe_gt_printk.h"
 #include "xe_platform_types.h"
+#include "xe_reg_sr.h"
 #include "xe_rtp.h"
 #include "xe_step.h"
 
···
 	{}
 };
 
+static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe)
+{
+	struct xe_reg_sr *sr = &hwe->reg_whitelist;
+	struct xe_reg_sr_entry *entry;
+	struct drm_printer p;
+	unsigned long reg;
+	unsigned int slot;
+
+	xe_gt_dbg(hwe->gt, "Add %s whitelist to engine\n", sr->name);
+	p = xe_gt_dbg_printer(hwe->gt);
+
+	slot = 0;
+	xa_for_each(&sr->xa, reg, entry) {
+		struct xe_reg_sr_entry hwe_entry = {
+			.reg = RING_FORCE_TO_NONPRIV(hwe->mmio_base, slot),
+			.set_bits = entry->reg.addr | entry->set_bits,
+			.clr_bits = ~0u,
+			.read_mask = entry->read_mask,
+		};
+
+		if (slot == RING_MAX_NONPRIV_SLOTS) {
+			xe_gt_err(hwe->gt,
+				  "hwe %s: maximum register whitelist slots (%d) reached, refusing to add more\n",
+				  hwe->name, RING_MAX_NONPRIV_SLOTS);
+			break;
+		}
+
+		xe_reg_whitelist_print_entry(&p, 0, reg, entry);
+		xe_reg_sr_add(&hwe->reg_sr, &hwe_entry, hwe->gt);
+
+		slot++;
+	}
+}
+
 /**
  * xe_reg_whitelist_process_engine - process table of registers to whitelist
  * @hwe: engine instance to process whitelist for
···
 	struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(hwe);
 
 	xe_rtp_process_to_sr(&ctx, register_whitelist, &hwe->reg_whitelist);
+	whitelist_apply_to_hwe(hwe);
 }
 
 /**