Merge tag 'drm-intel-gt-next-2025-02-26' of https://gitlab.freedeskto…

…p.org/drm/i915/kernel into drm-next

UAPI Changes:

- Add sysfs for SLPC power profiles [slpc] (Vinay Belgaumkar)

Driver Changes:

Fixes/improvements/new stuff:

- Fix zero delta busyness issue [pmu] (Umesh Nerlige Ramappa)
- Fix page cleanup on DMA remap failure (Brian Geffon)
- Debug print LRC state entries only if the context is pinned [guc] (Daniele Ceraolo Spurio)
- Drop custom hotplug code [pmu] (Lucas De Marchi)
- Use spin_lock_irqsave() in interruptible context [guc] (Krzysztof Karas)
- Add wait on depth stall done bit handling [gen12] (Juha-Pekka Heikkila)

Miscellaneous:

- Change throttle criteria for rps [selftest] (Raag Jadav)
- Add debug print about hw config table size (John Harrison)
- Include requested frequency in slow firmware load messages [uc] (John Harrison)
- Remove i915_pmu_event_event_idx() [pmu] (Lucas De Marchi)
- Remove unused live_context_for_engine (Dr. David Alan Gilbert)
- Add Wa_22010465259 in its respective WA list (Ranu Maurya)
- Correct frequency handling in RPS power measurement [selftests] (Sk Anirban)
- Add helper function slpc_measure_power [guc/slpc] (Sk Anirban)
- Revert "drm/i915/gt: Log reason for setting TAINT_WARN at reset" [gt] (Sebastian Brzezinka)
- Avoid using uninitialized context [selftests] (Krzysztof Karas)
- Use struct_size() helper in kmalloc() (luoqing)
- Use prandom in selftest [selftests] (Markus Theil)
- Replace kmap with its safer kmap_local_page counterpart [gt] (Andi Shyti)

Merges:

- Merge drm/drm-next into drm-intel-gt-next (Tvrtko Ursulin)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z77NLt2mR7SqxJ4u@linux

drivers/gpu/drm/i915/gem/selftests/mock_context.c

@@ -107,44 +107,6 @@ live_context(struct drm_i915_private *i915, struct file *file)
 	return ERR_PTR(err);
 }
 
-struct i915_gem_context *
-live_context_for_engine(struct intel_engine_cs *engine, struct file *file)
-{
-	struct i915_gem_engines *engines;
-	struct i915_gem_context *ctx;
-	struct intel_sseu null_sseu = {};
-	struct intel_context *ce;
-
-	engines = alloc_engines(1);
-	if (!engines)
-		return ERR_PTR(-ENOMEM);
-
-	ctx = live_context(engine->i915, file);
-	if (IS_ERR(ctx)) {
-		__free_engines(engines, 0);
-		return ctx;
-	}
-
-	ce = intel_context_create(engine);
-	if (IS_ERR(ce)) {
-		__free_engines(engines, 0);
-		return ERR_CAST(ce);
-	}
-
-	intel_context_set_gem(ce, ctx, null_sseu);
-	engines->engines[0] = ce;
-	engines->num_engines = 1;
-
-	mutex_lock(&ctx->engines_mutex);
-	i915_gem_context_set_user_engines(ctx);
-	engines = rcu_replace_pointer(ctx->engines, engines, 1);
-	mutex_unlock(&ctx->engines_mutex);
-
-	engines_idle_release(ctx, engines);
-
-	return ctx;
-}
-
 struct i915_gem_context *
 kernel_context(struct drm_i915_private *i915,
 	       struct i915_address_space *vm)

drivers/gpu/drm/i915/gem/selftests/mock_context.h

@@ -23,9 +23,6 @@ void mock_context_close(struct i915_gem_context *ctx);
 struct i915_gem_context *
 live_context(struct drm_i915_private *i915, struct file *file);
 
-struct i915_gem_context *
-live_context_for_engine(struct intel_engine_cs *engine, struct file *file);
-
 struct i915_gem_context *kernel_context(struct drm_i915_private *i915,
 					struct i915_address_space *vm);
 void kernel_context_close(struct i915_gem_context *ctx);

drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c

@@ -103,8 +103,7 @@ static struct dma_buf *mock_dmabuf(int npages)
 	struct dma_buf *dmabuf;
 	int i;
 
-	mock = kmalloc(sizeof(*mock) + npages * sizeof(struct page *),
-		       GFP_KERNEL);
+	mock = kmalloc(struct_size(mock, pages, npages), GFP_KERNEL);
 	if (!mock)
 		return ERR_PTR(-ENOMEM);
 

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

@@ -750,15 +750,15 @@ static void swizzle_page(struct page *page)
 	char *vaddr;
 	int i;
 
-	vaddr = kmap(page);
+	vaddr = kmap_local_page(page);
 
 	for (i = 0; i < PAGE_SIZE; i += 128) {
 		memcpy(temp, &vaddr[i], 64);
 		memcpy(&vaddr[i], &vaddr[i + 64], 64);
 		memcpy(&vaddr[i + 64], temp, 64);
 	}
 
-	kunmap(page);
+	kunmap_local(vaddr);
 }
 
 /**

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

@@ -409,6 +409,9 @@
 #define GEN7_SO_PRIM_STORAGE_NEEDED(n)		_MMIO(0x5240 + (n) * 8)
 #define GEN7_SO_PRIM_STORAGE_NEEDED_UDW(n)	_MMIO(0x5240 + (n) * 8 + 4)
 
+#define GEN8_WM_CHICKEN2			MCR_REG(0x5584)
+#define   WAIT_ON_DEPTH_STALL_DONE_DISABLE	REG_BIT(5)
+
 #define GEN9_WM_CHICKEN3			_MMIO(0x5588)
 #define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
 

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

@@ -464,6 +464,45 @@ static ssize_t slpc_ignore_eff_freq_store(struct kobject *kobj,
 	return err ?: count;
 }
 
+static ssize_t slpc_power_profile_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *buff)
+{
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+
+	switch (slpc->power_profile) {
+	case SLPC_POWER_PROFILES_BASE:
+		return sysfs_emit(buff, "[%s]    %s\n", "base", "power_saving");
+	case SLPC_POWER_PROFILES_POWER_SAVING:
+		return sysfs_emit(buff, "%s    [%s]\n", "base", "power_saving");
+	}
+
+	return sysfs_emit(buff, "%u\n", slpc->power_profile);
+}
+
+static ssize_t slpc_power_profile_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buff, size_t count)
+{
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+	char power_saving[] = "power_saving";
+	char base[] = "base";
+	int err;
+	u32 val;
+
+	if (!strncmp(buff, power_saving, sizeof(power_saving) - 1))
+		val = SLPC_POWER_PROFILES_POWER_SAVING;
+	else if (!strncmp(buff, base, sizeof(base) - 1))
+		val = SLPC_POWER_PROFILES_BASE;
+	else
+		return -EINVAL;
+
+	err = intel_guc_slpc_set_power_profile(slpc, val);
+	return err ?: count;
+}
+
 struct intel_gt_bool_throttle_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr,
@@ -668,6 +707,7 @@ INTEL_GT_ATTR_RO(media_RP0_freq_mhz);
 INTEL_GT_ATTR_RO(media_RPn_freq_mhz);
 
 INTEL_GT_ATTR_RW(slpc_ignore_eff_freq);
+INTEL_GT_ATTR_RW(slpc_power_profile);
 
 static const struct attribute *media_perf_power_attrs[] = {
 	&attr_media_freq_factor.attr,
@@ -864,6 +904,13 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 			gt_warn(gt, "failed to create ignore_eff_freq sysfs (%pe)", ERR_PTR(ret));
 	}
 
+	if (intel_uc_uses_guc_slpc(&gt->uc)) {
+		ret = sysfs_create_file(kobj, &attr_slpc_power_profile.attr);
+		if (ret)
+			gt_warn(gt, "failed to create slpc_power_profile sysfs (%pe)",
+				ERR_PTR(ret));
+	}
+
 	if (i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt))) {
 		ret = sysfs_create_files(kobj, throttle_reason_attrs);
 		if (ret)

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

@@ -1113,7 +1113,6 @@ 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;
 	}
@@ -1272,10 +1271,8 @@ void intel_gt_reset(struct intel_gt *gt,
 	}
 
 	ret = resume(gt);
-	if (ret) {
-		gt_err(gt, "Failed to resume (%d)\n", ret);
+	if (ret)
 		goto taint;
-	}
 
 finish:
 	reset_finish(gt, awake);
@@ -1641,7 +1638,6 @@ 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_rps.c

@@ -1025,6 +1025,10 @@ void intel_rps_boost(struct i915_request *rq)
 		if (rps_uses_slpc(rps)) {
 			slpc = rps_to_slpc(rps);
 
+			/* Waitboost should not be done with power saving profile */
+			if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING)
+				return;
+
 			if (slpc->min_freq_softlimit >= slpc->boost_freq)
 				return;
 

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

@@ -691,16 +691,17 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	struct drm_i915_private *i915 = engine->i915;
 
 	/*
-	 * Wa_1409142259:tgl,dg1,adl-p
+	 * Wa_1409142259:tgl,dg1,adl-p,adl-n
 	 * Wa_1409347922:tgl,dg1,adl-p
 	 * Wa_1409252684:tgl,dg1,adl-p
 	 * Wa_1409217633:tgl,dg1,adl-p
 	 * Wa_1409207793:tgl,dg1,adl-p
-	 * Wa_1409178076:tgl,dg1,adl-p
-	 * Wa_1408979724:tgl,dg1,adl-p
-	 * Wa_14010443199:tgl,rkl,dg1,adl-p
-	 * Wa_14010698770:tgl,rkl,dg1,adl-s,adl-p
-	 * Wa_1409342910:tgl,rkl,dg1,adl-s,adl-p
+	 * Wa_1409178076:tgl,dg1,adl-p,adl-n
+	 * Wa_1408979724:tgl,dg1,adl-p,adl-n
+	 * Wa_14010443199:tgl,rkl,dg1,adl-p,adl-n
+	 * Wa_14010698770:tgl,rkl,dg1,adl-s,adl-p,adl-n
+	 * Wa_1409342910:tgl,rkl,dg1,adl-s,adl-p,adl-n
+	 * Wa_22010465259:tgl,rkl,dg1,adl-s,adl-p,adl-n
 	 */
 	wa_masked_en(wal, GEN11_COMMON_SLICE_CHICKEN3,
 		     GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
@@ -741,6 +742,12 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 		/* Wa_1606376872 */
 		wa_masked_en(wal, COMMON_SLICE_CHICKEN4, DISABLE_TDC_LOAD_BALANCING_CALC);
 	}
+
+	/*
+	 * This bit must be set to enable performance optimization for fast
+	 * clears.
+	 */
+	wa_mcr_write_or(wal, GEN8_WM_CHICKEN2, WAIT_ON_DEPTH_STALL_DONE_DISABLE);
 }
 
 static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,

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

@@ -477,12 +477,13 @@ int live_rps_control(void *arg)
 			limit, intel_gpu_freq(rps, limit),
 			min, max, ktime_to_ns(min_dt), ktime_to_ns(max_dt));
 
-		if (limit == rps->min_freq) {
-			pr_err("%s: GPU throttled to minimum!\n",
-			       engine->name);
+		if (limit != rps->max_freq) {
+			u32 throttle = intel_uncore_read(gt->uncore,
+							 intel_gt_perf_limit_reasons_reg(gt));
+
+			pr_warn("%s: GPU throttled with reasons 0x%08x\n",
+				engine->name, throttle & GT0_PERF_LIMIT_REASONS_MASK);
 			show_pstate_limits(rps);
-			err = -ENODEV;
-			break;
 		}
 
 		if (igt_flush_test(gt->i915)) {
@@ -1115,7 +1116,7 @@ static u64 measure_power(struct intel_rps *rps, int *freq)
 	for (i = 0; i < 5; i++)
 		x[i] = __measure_power(5);
 
-	*freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2;
+	*freq = (*freq + read_cagf(rps)) / 2;
 
 	/* A simple triangle filter for better result stability */
 	sort(x, 5, sizeof(*x), cmp_u64, NULL);

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

@@ -95,6 +95,21 @@ static int slpc_restore_freq(struct intel_guc_slpc *slpc, u32 min, u32 max)
 	return 0;
 }
 
+static u64 slpc_measure_power(struct intel_rps *rps, int *freq)
+{
+	u64 x[5];
+	int i;
+
+	for (i = 0; i < 5; i++)
+		x[i] = __measure_power(5);
+
+	*freq = (*freq + intel_rps_read_actual_frequency(rps)) / 2;
+
+	/* A simple triangle filter for better result stability */
+	sort(x, 5, sizeof(*x), cmp_u64, NULL);
+	return div_u64(x[1] + 2 * x[2] + x[3], 4);
+}
+
 static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power)
 {
 	int err = 0;
@@ -103,7 +118,7 @@ static u64 measure_power_at_freq(struct intel_gt *gt, int *freq, u64 *power)
 	if (err)
 		return err;
 	*freq = intel_rps_read_actual_frequency(&gt->rps);
-	*power = measure_power(&gt->rps, freq);
+	*power = slpc_measure_power(&gt->rps, freq);
 
 	return err;
 }

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

@@ -108,15 +108,15 @@ static int __shmem_rw(struct file *file, loff_t off,
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
-		vaddr = kmap(page);
+		vaddr = kmap_local_page(page);
 		if (write) {
 			memcpy(vaddr + offset_in_page(off), ptr, this);
 			set_page_dirty(page);
 		} else {
 			memcpy(ptr, vaddr + offset_in_page(off), this);
 		}
 		mark_page_accessed(page);
-		kunmap(page);
+		kunmap_local(vaddr);
 		put_page(page);
 
 		len -= this;
@@ -143,11 +143,11 @@ int shmem_read_to_iosys_map(struct file *file, loff_t off,
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
-		vaddr = kmap(page);
+		vaddr = kmap_local_page(page);
 		iosys_map_memcpy_to(map, map_off, vaddr + offset_in_page(off),
 				    this);
 		mark_page_accessed(page);
-		kunmap(page);
+		kunmap_local(vaddr);
 		put_page(page);
 
 		len -= this;

drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h

@@ -228,6 +228,11 @@ struct slpc_optimized_strategies {
 
 #define SLPC_OPTIMIZED_STRATEGY_COMPUTE		REG_BIT(0)
 
+enum slpc_power_profiles {
+	SLPC_POWER_PROFILES_BASE = 0x0,
+	SLPC_POWER_PROFILES_POWER_SAVING = 0x1
+};
+
 /**
  * DOC: SLPC H2G MESSAGE FORMAT
  *

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

@@ -259,13 +259,14 @@ static int guc_wait_ucode(struct intel_guc *guc)
 	} else if (delta_ms > 200) {
 		guc_warn(guc, "excessive init time: %lldms! [status = 0x%08X, count = %d, ret = %d]\n",
 			 delta_ms, status, count, ret);
-		guc_warn(guc, "excessive init time: [freq = %dMHz, before = %dMHz, perf_limit_reasons = 0x%08X]\n",
-			 intel_rps_read_actual_frequency(&gt->rps), before_freq,
+		guc_warn(guc, "excessive init time: [freq = %dMHz -> %dMHz vs %dMHz, perf_limit_reasons = 0x%08X]\n",
+			 before_freq, intel_rps_read_actual_frequency(&gt->rps),
+			 intel_rps_get_requested_frequency(&gt->rps),
 			 intel_uncore_read(uncore, intel_gt_perf_limit_reasons_reg(gt)));
 	} else {
-		guc_dbg(guc, "init took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n",
-			delta_ms, intel_rps_read_actual_frequency(&gt->rps),
-			before_freq, status, count, ret);
+		guc_dbg(guc, "init took %lldms, freq = %dMHz -> %dMHz vs %dMHz, status = 0x%08X, count = %d, ret = %d\n",
+			delta_ms, before_freq, intel_rps_read_actual_frequency(&gt->rps),
+			intel_rps_get_requested_frequency(&gt->rps), status, count, ret);
 	}
 
 	return ret;

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

@@ -7,6 +7,7 @@
 #include "gt/intel_hwconfig.h"
 #include "i915_drv.h"
 #include "i915_memcpy.h"
+#include "intel_guc_print.h"
 
 /*
  * GuC has a blob containing hardware configuration information (HWConfig).
@@ -42,6 +43,8 @@ static int __guc_action_get_hwconfig(struct intel_guc *guc,
 	};
 	int ret;
 
+	guc_dbg(guc, "Querying HW config table: size = %d, offset = 0x%08X\n",
+		ggtt_size, ggtt_offset);
 	ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
 	if (ret == -ENXIO)
 		return -ENOENT;