Merge tag 'drm-intel-gt-next-2025-01-10' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-next

Driver Changes:

- More robust engine resets on Haswell and older (Nitin)

- Dead code removal (David)
- Selftest, logging and tracing improvements (Sk, Nitin, Sebastian,
  Apoorva)

Signed-off-by: Dave Airlie <[email protected]>
From: Joonas Lahtinen <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

drivers/gpu/drm/i915/gem/i915_gem_lmem.c

@@ -52,29 +52,6 @@ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
 }
 
-/**
- * __i915_gem_object_is_lmem - Whether the object is resident in
- * lmem while in the fence signaling critical path.
- * @obj: The object to check.
- *
- * This function is intended to be called from within the fence signaling
- * path where the fence, or a pin, keeps the object from being migrated. For
- * example during gpu reset or similar.
- *
- * Return: Whether the object is resident in lmem.
- */
-bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
-{
-	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
-
-#ifdef CONFIG_LOCKDEP
-	GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP) &&
-		    i915_gem_object_evictable(obj));
-#endif
-	return mr && (mr->type == INTEL_MEMORY_LOCAL ||
-		      mr->type == INTEL_MEMORY_STOLEN_LOCAL);
-}
-
 /**
  * __i915_gem_object_create_lmem_with_ps - Create lmem object and force the
  * minimum page size for the backing pages.

drivers/gpu/drm/i915/gem/i915_gem_lmem.h

@@ -19,8 +19,6 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
 
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
-bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
-
 struct drm_i915_gem_object *
 i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
 				      const void *data, size_t size);

drivers/gpu/drm/i915/gt/intel_reset.c

@@ -1113,6 +1113,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		 * Warn CI about the unrecoverable wedged condition.
 		 * Time for a reboot.
 		 */
+		gt_err(gt, "Unrecoverable wedged condition\n");
 		add_taint_for_CI(gt->i915, TAINT_WARN);
 		return false;
 	}
@@ -1264,8 +1265,10 @@ void intel_gt_reset(struct intel_gt *gt,
 	}
 
 	ret = resume(gt);
-	if (ret)
+	if (ret) {
+		gt_err(gt, "Failed to resume (%d)\n", ret);
 		goto taint;
+	}
 
 finish:
 	reset_finish(gt, awake);
@@ -1608,6 +1611,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt)
 	set_bit(I915_WEDGED_ON_INIT, &gt->reset.flags);
 
 	/* Wedged on init is non-recoverable */
+	gt_err(gt, "Non-recoverable wedged on init\n");
 	add_taint_for_CI(gt->i915, TAINT_WARN);
 }
 

drivers/gpu/drm/i915/gt/intel_ring.c

@@ -308,30 +308,6 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 	return cs;
 }
 
-/* Align the ring tail to a cacheline boundary */
-int intel_ring_cacheline_align(struct i915_request *rq)
-{
-	int num_dwords;
-	void *cs;
-
-	num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
-	if (num_dwords == 0)
-		return 0;
-
-	num_dwords = CACHELINE_DWORDS - num_dwords;
-	GEM_BUG_ON(num_dwords & 1);
-
-	cs = intel_ring_begin(rq, num_dwords);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2);
-	intel_ring_advance(rq, cs + num_dwords);
-
-	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
-	return 0;
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_ring.c"
 #endif

drivers/gpu/drm/i915/gt/intel_ring.h

@@ -16,7 +16,6 @@ struct intel_ring *
 intel_engine_create_ring(struct intel_engine_cs *engine, int size);
 
 u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords);
-int intel_ring_cacheline_align(struct i915_request *rq);
 
 unsigned int intel_ring_update_space(struct intel_ring *ring);
 

drivers/gpu/drm/i915/gt/intel_ring_submission.c

@@ -26,6 +26,7 @@
 #include "shmem_utils.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
+#include "intel_gt_print.h"
 
 /* Rough estimate of the typical request size, performing a flush,
  * set-context and then emitting the batch.
@@ -230,8 +231,13 @@ static int xcs_resume(struct intel_engine_cs *engine)
 
 	set_pp_dir(engine);
 
-	/* First wake the ring up to an empty/idle ring */
-	for ((kt) = ktime_get() + (2 * NSEC_PER_MSEC);
+	/*
+	 * First wake the ring up to an empty/idle ring.
+	 * Use 50ms of delay to let the engine write successfully
+	 * for all platforms. Experimented with different values and
+	 * determined that 50ms works best based on testing.
+	 */
+	for ((kt) = ktime_get() + (50 * NSEC_PER_MSEC);
 			ktime_before(ktime_get(), (kt)); cpu_relax()) {
 		/*
 		 * In case of resets fails because engine resumes from
@@ -282,16 +288,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	return 0;
 
 err:
-	drm_err(&engine->i915->drm,
-		"%s initialization failed; "
-		"ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
-		engine->name,
-		ENGINE_READ(engine, RING_CTL),
-		ENGINE_READ(engine, RING_CTL) & RING_VALID,
-		ENGINE_READ(engine, RING_HEAD), ring->head,
-		ENGINE_READ(engine, RING_TAIL), ring->tail,
-		ENGINE_READ(engine, RING_START),
-		i915_ggtt_offset(ring->vma));
+	gt_err(engine->gt, "%s initialization failed\n", engine->name);
+	ENGINE_TRACE(engine,
+		     "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
+		     ENGINE_READ(engine, RING_CTL),
+		     ENGINE_READ(engine, RING_CTL) & RING_VALID,
+		     ENGINE_READ(engine, RING_HEAD), ring->head,
+		     ENGINE_READ(engine, RING_TAIL), ring->tail,
+		     ENGINE_READ(engine, RING_START),
+		     i915_ggtt_offset(ring->vma));
+	GEM_TRACE_DUMP();
 	return -EIO;
 }
 

drivers/gpu/drm/i915/gt/selftest_migrate.c

@@ -262,7 +262,7 @@ static int clear(struct intel_migrate *migrate,
 {
 	struct drm_i915_private *i915 = migrate->context->engine->i915;
 	struct drm_i915_gem_object *obj;
-	struct i915_request *rq;
+	struct i915_request *rq = NULL;
 	struct i915_gem_ww_ctx ww;
 	u32 *vaddr, val = 0;
 	bool ccs_cap = false;

drivers/gpu/drm/i915/gt/selftest_rc6.c

@@ -8,6 +8,7 @@
 #include "intel_gpu_commands.h"
 #include "intel_gt_requests.h"
 #include "intel_ring.h"
+#include "intel_rps.h"
 #include "selftest_rc6.h"
 
 #include "selftests/i915_random.h"
@@ -38,6 +39,9 @@ int live_rc6_manual(void *arg)
 	ktime_t dt;
 	u64 res[2];
 	int err = 0;
+	u32 rc0_freq = 0;
+	u32 rc6_freq = 0;
+	struct intel_rps *rps = &gt->rps;
 
 	/*
 	 * Our claim is that we can "encourage" the GPU to enter rc6 at will.
@@ -66,6 +70,7 @@ int live_rc6_manual(void *arg)
 	rc0_power = librapl_energy_uJ() - rc0_power;
 	dt = ktime_sub(ktime_get(), dt);
 	res[1] = rc6_residency(rc6);
+	rc0_freq = intel_rps_read_actual_frequency_fw(rps);
 	if ((res[1] - res[0]) >> 10) {
 		pr_err("RC6 residency increased by %lldus while disabled for 1000ms!\n",
 		       (res[1] - res[0]) >> 10);
@@ -77,7 +82,11 @@ int live_rc6_manual(void *arg)
 		rc0_power = div64_u64(NSEC_PER_SEC * rc0_power,
 				      ktime_to_ns(dt));
 		if (!rc0_power) {
-			pr_err("No power measured while in RC0\n");
+			if (rc0_freq)
+				pr_debug("No power measured while in RC0! GPU Freq: %u in RC0\n",
+					 rc0_freq);
+			else
+				pr_err("No power and freq measured while in RC0\n");
 			err = -EINVAL;
 			goto out_unlock;
 		}
@@ -90,7 +99,8 @@ int live_rc6_manual(void *arg)
 	intel_uncore_forcewake_flush(rc6_to_uncore(rc6), FORCEWAKE_ALL);
 	dt = ktime_get();
 	rc6_power = librapl_energy_uJ();
-	msleep(100);
+	msleep(1000);
+	rc6_freq = intel_rps_read_actual_frequency_fw(rps);
 	rc6_power = librapl_energy_uJ() - rc6_power;
 	dt = ktime_sub(ktime_get(), dt);
 	res[1] = rc6_residency(rc6);
@@ -108,7 +118,8 @@ int live_rc6_manual(void *arg)
 		pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n",
 			rc0_power, rc6_power);
 		if (2 * rc6_power > rc0_power) {
-			pr_err("GPU leaked energy while in RC6!\n");
+			pr_err("GPU leaked energy while in RC6! GPU Freq: %u in RC6 and %u in RC0\n",
+			       rc6_freq, rc0_freq);
 			err = -EINVAL;
 			goto out_unlock;
 		}

drivers/gpu/drm/i915/gt/uc/intel_guc_log.c

@@ -18,7 +18,7 @@
 #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE	SZ_2M
 #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE	SZ_16M
 #define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_1M
-#elif defined(CONFIG_DRM_I915_DEBUG_GEM)
+#elif IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 #define GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE	SZ_1M
 #define GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE	SZ_2M
 #define GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE	SZ_1M

drivers/gpu/drm/i915/gt/uc/intel_huc.c

@@ -427,19 +427,6 @@ void intel_huc_fini(struct intel_huc *huc)
 		intel_uc_fw_fini(&huc->fw);
 }
 
-void intel_huc_suspend(struct intel_huc *huc)
-{
-	if (!intel_uc_fw_is_loadable(&huc->fw))
-		return;
-
-	/*
-	 * in the unlikely case that we're suspending before the GSC has
-	 * completed its loading sequence, just stop waiting. We'll restart
-	 * on resume.
-	 */
-	delayed_huc_load_complete(huc);
-}
-
 static const char *auth_mode_string(struct intel_huc *huc,
 				    enum intel_huc_authentication_type type)
 {

drivers/gpu/drm/i915/gt/uc/intel_huc.h

@@ -57,7 +57,6 @@ int intel_huc_sanitize(struct intel_huc *huc);
 void intel_huc_init_early(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
-void intel_huc_suspend(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc, enum intel_huc_authentication_type type);
 int intel_huc_wait_for_auth_complete(struct intel_huc *huc,
 				     enum intel_huc_authentication_type type);

drivers/gpu/drm/i915/i915_active.c

@@ -527,24 +527,6 @@ int i915_active_acquire(struct i915_active *ref)
 	return err;
 }
 
-int i915_active_acquire_for_context(struct i915_active *ref, u64 idx)
-{
-	struct i915_active_fence *active;
-	int err;
-
-	err = i915_active_acquire(ref);
-	if (err)
-		return err;
-
-	active = active_instance(ref, idx);
-	if (!active) {
-		i915_active_release(ref);
-		return -ENOMEM;
-	}
-
-	return 0; /* return with active ref */
-}
-
 void i915_active_release(struct i915_active *ref)
 {
 	debug_active_assert(ref);

drivers/gpu/drm/i915/i915_active.h

@@ -186,7 +186,6 @@ int i915_request_await_active(struct i915_request *rq,
 #define I915_ACTIVE_AWAIT_BARRIER BIT(2)
 
 int i915_active_acquire(struct i915_active *ref);
-int i915_active_acquire_for_context(struct i915_active *ref, u64 idx);
 bool i915_active_acquire_if_busy(struct i915_active *ref);
 
 void i915_active_release(struct i915_active *ref);