Merge tag 'drm-intel-gt-next-2024-04-26' of https://anongit.freedesktop.org/git/drm/drm-intel into drm-next

UAPI Changes:

- drm/i915/guc: Use context hints for GT frequency

    Allow user to provide a low latency context hint. When set, KMD
    sends a hint to GuC which results in special handling for this
    context. SLPC will ramp the GT frequency aggressively every time
    it switches to this context. The down freq threshold will also be
    lower so GuC will ramp down the GT freq for this context more slowly.
    We also disable waitboost for this context as that will interfere with
    the strategy.

    We need to enable the use of SLPC Compute strategy during init, but
    it will apply only to contexts that set this bit during context
    creation.

    Userland can check whether this feature is supported using a new param-
    I915_PARAM_HAS_CONTEXT_FREQ_HINT. This flag is true for all guc submission
    enabled platforms as they use SLPC for frequency management.

    The Mesa usage model for this flag is here -
    https://gitlab.freedesktop.org/sushmave/mesa/-/commits/compute_hint

- drm/i915/gt: Enable only one CCS for compute workload

    Enable only one CCS engine by default with all the compute sices
    allocated to it.

    While generating the list of UABI engines to be exposed to the
    user, exclude any additional CCS engines beyond the first
    instance

    ***

    NOTE: This W/A will make all DG2 SKUs appear like single CCS SKUs by
    default to mitigate a hardware bug. All the EUs will still remain
    usable, and all the userspace drivers have been confirmed to be able
    to dynamically detect the change in number of CCS engines and adjust.

    For the smaller percent of applications that get perf benefit from
    letting the userspace driver dispatch across all 4 CCS engines we will
    be introducing a sysfs control as a later patch to choose 4 CCS each
    with 25% EUs (or 50% if 2 CCS).

    NOTE: A regression has been reported at

    https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10895

    However Andi has been triaging the issue and we're closing in a fix
    to the gap in the W/A implementation:

    https://lists.freedesktop.org/archives/intel-gfx/2024-April/348747.html

Driver Changes:

- Add new and fix to existing workarounds: Wa_14018575942 (MTL),
  Wa_16019325821 (Gen12.70), Wa_14019159160 (MTL), Wa_16015675438,
  Wa_14020495402 (Gen12.70) (Tejas, John, Lucas)
- Fix UAF on destroy against retire race and remove two earlier
  partial fixes (Janusz)
- Limit the reserved VM space to only the platforms that need it (Andi)
- Reset queue_priority_hint on parking for execlist platforms (Chris)
- Fix gt reset with GuC submission is disabled (Nirmoy)
- Correct capture of EIR register on hang (John)

- Remove usage of the deprecated ida_simple_xx() API
- Refactor confusing __intel_gt_reset() (Nirmoy)
- Fix the fix for GuC reset lock confusion (John)
- Simplify/extend platform check for Wa_14018913170 (John)
- Replace dev_priv with i915 (Andi)
- Add and use gt_to_guc() wrapper (Andi)
- Remove bogus null check (Rodrigo, Dan)

. Selftest improvements (Janusz, Nirmoy, Daniele)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZitVBTvZmityDi7D@jlahtine-mobl.ger.corp.intel.com

1 files changed, 43 insertions, 8 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index c8e9aa41fdea..6161f7a3ff70 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -764,7 +764,7 @@ wa_14015076503_end(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 			 HECI_H_GS1_ER_PREP, 0);
 }
 
-int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+static int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 {
 	const int retries = engine_mask == ALL_ENGINES ? RESET_MAX_RETRIES : 1;
 	reset_func reset;
@@ -879,8 +879,17 @@ static intel_engine_mask_t reset_prepare(struct intel_gt *gt)
 	intel_engine_mask_t awake = 0;
 	enum intel_engine_id id;
 
-	/* For GuC mode, ensure submission is disabled before stopping ring */
-	intel_uc_reset_prepare(&gt->uc);
+	/**
+	 * For GuC mode with submission enabled, ensure submission
+	 * is disabled before stopping ring.
+	 *
+	 * For GuC mode with submission disabled, ensure that GuC is not
+	 * sanitized, do that after engine reset. reset_prepare()
+	 * is followed by engine reset which in this mode requires GuC to
+	 * process any CSB FIFO entries generated by the resets.
+	 */
+	if (intel_uc_uses_guc_submission(&gt->uc))
+		intel_uc_reset_prepare(&gt->uc);
 
 	for_each_engine(engine, gt, id) {
 		if (intel_engine_pm_get_if_awake(engine))
@@ -978,7 +987,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 
 	/* Even if the GPU reset fails, it should still stop the engines */
 	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
-		__intel_gt_reset(gt, ALL_ENGINES);
+		intel_gt_reset_all_engines(gt);
 
 	for_each_engine(engine, gt, id)
 		engine->submit_request = nop_submit_request;
@@ -1089,7 +1098,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	/* We must reset pending GPU events before restoring our submission */
 	ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */
 	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
-		ok = __intel_gt_reset(gt, ALL_ENGINES) == 0;
+		ok = intel_gt_reset_all_engines(gt) == 0;
 	if (!ok) {
 		/*
 		 * Warn CI about the unrecoverable wedged condition.
@@ -1133,10 +1142,10 @@ static int do_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 {
 	int err, i;
 
-	err = __intel_gt_reset(gt, ALL_ENGINES);
+	err = intel_gt_reset_all_engines(gt);
 	for (i = 0; err && i < RESET_MAX_RETRIES; i++) {
 		msleep(10 * (i + 1));
-		err = __intel_gt_reset(gt, ALL_ENGINES);
+		err = intel_gt_reset_all_engines(gt);
 	}
 	if (err)
 		return err;
@@ -1227,6 +1236,9 @@ void intel_gt_reset(struct intel_gt *gt,
 
 	intel_overlay_reset(gt->i915);
 
+	/* sanitize uC after engine reset */
+	if (!intel_uc_uses_guc_submission(&gt->uc))
+		intel_uc_reset_prepare(&gt->uc);
 	/*
 	 * Next we need to restore the context, but we don't use those
 	 * yet either...
@@ -1270,7 +1282,30 @@ error:
 	goto finish;
 }
 
-static int intel_gt_reset_engine(struct intel_engine_cs *engine)
+/**
+ * intel_gt_reset_all_engines() - Reset all engines in the given gt.
+ * @gt: the GT to reset all engines for.
+ *
+ * This function resets all engines within the given gt.
+ *
+ * Returns:
+ * Zero on success, negative error code on failure.
+ */
+int intel_gt_reset_all_engines(struct intel_gt *gt)
+{
+	return __intel_gt_reset(gt, ALL_ENGINES);
+}
+
+/**
+ * intel_gt_reset_engine() - Reset a specific engine within a gt.
+ * @engine: engine to be reset.
+ *
+ * This function resets the specified engine within a gt.
+ *
+ * Returns:
+ * Zero on success, negative error code on failure.
+ */
+int intel_gt_reset_engine(struct intel_engine_cs *engine)
 {
 	return __intel_gt_reset(engine->gt, engine->mask);
 }