drm/xe/reg_sr: Add debugfs to verify status of reg_sr programming

When applying save-restore register programming for workarounds, tuning
settings, and general device configuration we assume the programming was
successful.  However there are a number of cases where the desired
reg_sr programming can become lost:

 - workarounds implemented on the wrong RTP table might not get
   saved/restored at the right time leading to, for example, failure to
   re-apply the programming after engine resets
 - some hardware registers become "locked" and can no longer be updated
   after firmware or the driver finishes initializing them
 - sometimes the hardware teams just made a mistake when documenting the
   register and/or bits that needed to be programmed

Add a debugfs entry that will read back the registers referenced on a
GT's save-restore lists and print any cases where the desired
programming is no longer in effect.  Such cases might indicate the
presence of a driver/firmware bug, might indicate that the documentation
we were following has a mistake, or might be benign (occasionally
registers have broken read-back capability preventing verification, but
previous writes were still successful and effective).

For now we only verify the GT and engine reg_sr lists.  Verifying the
LRC list will require checking the expected programming against the
default_lrc contents, not the live registers (which may not reflect the
reg_sr programming if no context is actively running).

Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patch.msgid.link/20260218-sr_verify-v4-2-35d6deeb3421@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 4363bc9c36067f3b22ff9f8fa5d64dece31cbe3b..aa43427a9f4b824b8ad41d02f634c07c76d989b2 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -155,6 +155,30 @@ static int register_save_restore(struct xe_gt *gt, struct drm_printer *p)
        return 0;
 }
 
+/*
+ * Check the registers referenced on a save-restore list and report any
+ * save-restore entries that did not get applied.
+ */
+static int register_save_restore_check(struct xe_gt *gt, struct drm_printer *p)
+{
+       struct xe_hw_engine *hwe;
+       enum xe_hw_engine_id id;
+
+       CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+       if (!xe_force_wake_ref_has_domain(fw_ref.domains, XE_FORCEWAKE_ALL)) {
+               drm_printf(p, "ERROR: Could not acquire forcewake\n");
+               return -ETIMEDOUT;
+       }
+
+       xe_reg_sr_readback_check(&gt->reg_sr, gt, p);
+       for_each_hw_engine(hwe, gt, id)
+               xe_reg_sr_readback_check(&hwe->reg_sr, gt, p);
+
+       /* TODO: Check hwe->reg_lrc against contents of default_lrc. */
+
+       return 0;
+}
+
 static int rcs_default_lrc(struct xe_gt *gt, struct drm_printer *p)
 {
        xe_lrc_dump_default(p, gt, XE_ENGINE_CLASS_RENDER);
@@ -209,6 +233,8 @@ static const struct drm_info_list vf_safe_debugfs_list[] = {
        { "default_lrc_vecs", .show = xe_gt_debugfs_show_with_rpm, .data = vecs_default_lrc },
        { "hwconfig", .show = xe_gt_debugfs_show_with_rpm, .data = hwconfig },
        { "pat_sw_config", .show = xe_gt_debugfs_simple_show, .data = xe_pat_dump_sw_config },
+       { "register-save-restore-check",
+               .show = xe_gt_debugfs_show_with_rpm, .data = register_save_restore_check },
 };
 
 /* everything else should be added here */

diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c
index 1ac911fc6e943ce05b8ac7cef33bc23d872d5ec4..75aa4426b3ec6026bc13095df3c3f9cb0a794b97 100644 (file)
--- a/drivers/gpu/drm/xe/xe_reg_sr.c
+++ b/drivers/gpu/drm/xe/xe_reg_sr.c
@@ -208,3 +208,37 @@ void xe_reg_sr_dump(struct xe_reg_sr *sr, struct drm_printer *p)
                           str_yes_no(entry->reg.masked),
                           str_yes_no(entry->reg.mcr));
 }
+
+static u32 readback_reg(struct xe_gt *gt, struct xe_reg reg)
+{
+       struct xe_reg_mcr mcr_reg = to_xe_reg_mcr(reg);
+
+       if (reg.mcr)
+               return xe_gt_mcr_unicast_read_any(gt, mcr_reg);
+       else
+               return xe_mmio_read32(&gt->mmio, reg);
+}
+
+/**
+ * xe_reg_sr_readback_check() - Readback registers referenced in save/restore
+ *     entries and check whether the programming is in place.
+ * @sr: Save/restore entries
+ * @gt: GT to read register from
+ * @p: DRM printer to report discrepancies on
+ */
+void xe_reg_sr_readback_check(struct xe_reg_sr *sr,
+                             struct xe_gt *gt,
+                             struct drm_printer *p)
+{
+       struct xe_reg_sr_entry *entry;
+       unsigned long offset;
+
+       xa_for_each(&sr->xa, offset, entry) {
+               u32 val = readback_reg(gt, entry->reg);
+               u32 mask = entry->clr_bits | entry->set_bits;
+
+               if ((val & mask) != entry->set_bits)
+                       drm_printf(p, "%#8lx & %#10x :: expected %#10x got %#10x\n",
+                                  offset, mask, entry->set_bits, val & mask);
+       }
+}

diff --git a/drivers/gpu/drm/xe/xe_reg_sr.h b/drivers/gpu/drm/xe/xe_reg_sr.h
index 51fbba423e27f3f3eab737221270e43aba56f54e..cd133a09aa9b3f046dbd913aa9711250e771ee1a 100644 (file)
--- a/drivers/gpu/drm/xe/xe_reg_sr.h
+++ b/drivers/gpu/drm/xe/xe_reg_sr.h
@@ -19,6 +19,9 @@ struct drm_printer;
 
 int xe_reg_sr_init(struct xe_reg_sr *sr, const char *name, struct xe_device *xe);
 void xe_reg_sr_dump(struct xe_reg_sr *sr, struct drm_printer *p);
+void xe_reg_sr_readback_check(struct xe_reg_sr *sr,
+                             struct xe_gt *gt,
+                             struct drm_printer *p);
 
 int xe_reg_sr_add(struct xe_reg_sr *sr, const struct xe_reg_sr_entry *e,
                  struct xe_gt *gt);