Merge tag 'drm-intel-gt-next-2024-09-06' of https://gitlab.freedesktop.org/drm/i915/kernel into drm-next

Driver Changes:

- Expose fan speed via hwmon (Raag)
- Correction to Wa_14019159160 on ARL (John H)
- Whitelist COMMON_SLICE_CHICKEN1 for UMD access on DG2/MTL/ARL (Dnyaneshwar)
- Do not attempt to load the GSC multiple times to avoid hanging GSC HW (Daniele)

- Populate /sys/class/drm/cardX/engines/ even if one engine fails (Andi)
- Use kmemdup_array instead of kmemdup for multiple allocation (Yu)
- Remove extra unlikely() (Hongbo)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Ztrfr_Wuurfa-3Rv@jlahtine-mobl.ger.corp.intel.com

Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon

@@ -75,3 +75,11 @@ Description:	RO. Energy input of device or gt in microjoules.
 		for the gt.
 
 		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/fan1_input
+Date:		November 2024
+KernelVersion:	6.12
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RO. Fan speed of device in RPM.
+
+		Only supported for particular Intel i915 graphics platforms.

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -825,7 +825,7 @@ static int eb_select_context(struct i915_execbuffer *eb)
 	struct i915_gem_context *ctx;
 
 	ctx = i915_gem_context_lookup(eb->file->driver_priv, eb->args->rsvd1);
-	if (unlikely(IS_ERR(ctx)))
+	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
 	eb->gem_context = ctx;

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

@@ -1553,6 +1553,8 @@
 #define VLV_RENDER_C0_COUNT			_MMIO(0x138118)
 #define VLV_MEDIA_C0_COUNT			_MMIO(0x13811c)
 
+#define PCU_PWM_FAN_SPEED			_MMIO(0x138140)
+
 #define GEN12_RPSTAT1				_MMIO(0x1381b4)
 #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
 #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)

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

@@ -111,9 +111,8 @@ static void wa_init_finish(struct i915_wa_list *wal)
 {
 	/* Trim unused entries. */
 	if (!IS_ALIGNED(wal->count, WA_LIST_CHUNK)) {
-		struct i915_wa *list = kmemdup(wal->list,
-					       wal->count * sizeof(*list),
-					       GFP_KERNEL);
+		struct i915_wa *list = kmemdup_array(wal->list, wal->count,
+						     sizeof(*list), GFP_KERNEL);
 
 		if (list) {
 			kfree(wal->list);
@@ -2072,7 +2071,7 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine)
 	case RENDER_CLASS:
 		/* Required by recommended tuning setting (not a workaround) */
 		whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3);
-
+		whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1);
 		break;
 	default:
 		break;
@@ -2087,7 +2086,7 @@ static void xelpg_whitelist_build(struct intel_engine_cs *engine)
 	case RENDER_CLASS:
 		/* Required by recommended tuning setting (not a workaround) */
 		whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3);
-
+		whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1);
 		break;
 	default:
 		break;

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

@@ -530,9 +530,8 @@ void intel_engines_add_sysfs(struct drm_i915_private *i915)
 err_object:
 			kobject_put(kobj);
 err_engine:
-			dev_err(kdev, "Failed to add sysfs engine '%s'\n",
-				engine->name);
-			break;
+			dev_warn(kdev, "Failed to add sysfs engine '%s'\n",
+				 engine->name);
 		}
 	}
 }

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

@@ -302,7 +302,7 @@ void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc)
 {
 	struct intel_gt *gt = gsc_uc_to_gt(gsc);
 
-	if (!intel_uc_fw_is_loadable(&gsc->fw))
+	if (!intel_uc_fw_is_loadable(&gsc->fw) || intel_uc_fw_is_in_error(&gsc->fw))
 		return;
 
 	if (intel_gsc_uc_fw_init_done(gsc))

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

@@ -4507,7 +4507,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 	/* Wa_16019325821 */
 	/* Wa_14019159160 */
 	if ((engine->class == COMPUTE_CLASS || engine->class == RENDER_CLASS) &&
-	    IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71)))
+	    IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74)))
 		engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT;
 
 	/*

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

@@ -258,6 +258,11 @@ static inline bool intel_uc_fw_is_running(struct intel_uc_fw *uc_fw)
 	return __intel_uc_fw_status(uc_fw) == INTEL_UC_FIRMWARE_RUNNING;
 }
 
+static inline bool intel_uc_fw_is_in_error(struct intel_uc_fw *uc_fw)
+{
+	return intel_uc_fw_status_to_error(__intel_uc_fw_status(uc_fw)) != 0;
+}
+
 static inline bool intel_uc_fw_is_overridden(const struct intel_uc_fw *uc_fw)
 {
 	return uc_fw->user_overridden;

drivers/gpu/drm/i915/i915_hwmon.c

@@ -5,6 +5,7 @@
 
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
 #include <linux/types.h>
 
 #include "i915_drv.h"
@@ -36,6 +37,7 @@ struct hwm_reg {
 	i915_reg_t pkg_rapl_limit;
 	i915_reg_t energy_status_all;
 	i915_reg_t energy_status_tile;
+	i915_reg_t fan_speed;
 };
 
 struct hwm_energy_info {
@@ -43,11 +45,17 @@ struct hwm_energy_info {
 	long accum_energy;			/* Accumulated energy for energy1_input */
 };
 
+struct hwm_fan_info {
+	u32 reg_val_prev;
+	u64 time_prev;
+};
+
 struct hwm_drvdata {
 	struct i915_hwmon *hwmon;
 	struct intel_uncore *uncore;
 	struct device *hwmon_dev;
 	struct hwm_energy_info ei;		/*  Energy info for energy1_input */
+	struct hwm_fan_info fi;			/*  Fan info for fan1_input */
 	char name[12];
 	int gt_n;
 	bool reset_in_progress;
@@ -276,6 +284,7 @@ static const struct hwmon_channel_info * const hwm_info[] = {
 	HWMON_CHANNEL_INFO(power, HWMON_P_MAX | HWMON_P_RATED_MAX | HWMON_P_CRIT),
 	HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT),
 	HWMON_CHANNEL_INFO(curr, HWMON_C_CRIT),
+	HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT),
 	NULL
 };
 
@@ -613,6 +622,69 @@ hwm_curr_write(struct hwm_drvdata *ddat, u32 attr, long val)
 	}
 }
 
+static umode_t
+hwm_fan_is_visible(const struct hwm_drvdata *ddat, u32 attr)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+
+	if (attr == hwmon_fan_input && i915_mmio_reg_valid(hwmon->rg.fan_speed))
+		return 0444;
+
+	return 0;
+}
+
+static int
+hwm_fan_input_read(struct hwm_drvdata *ddat, long *val)
+{
+	struct i915_hwmon *hwmon = ddat->hwmon;
+	struct hwm_fan_info *fi = &ddat->fi;
+	u64 rotations, time_now, time;
+	intel_wakeref_t wakeref;
+	u32 reg_val;
+	int ret = 0;
+
+	wakeref = intel_runtime_pm_get(ddat->uncore->rpm);
+	mutex_lock(&hwmon->hwmon_lock);
+
+	reg_val = intel_uncore_read(ddat->uncore, hwmon->rg.fan_speed);
+	time_now = get_jiffies_64();
+
+	/*
+	 * HW register value is accumulated count of pulses from
+	 * PWM fan with the scale of 2 pulses per rotation.
+	 */
+	rotations = (reg_val - fi->reg_val_prev) / 2;
+
+	time = jiffies_delta_to_msecs(time_now - fi->time_prev);
+	if (unlikely(!time)) {
+		ret = -EAGAIN;
+		goto exit;
+	}
+
+	/*
+	 * Calculate fan speed in RPM by time averaging two subsequent
+	 * readings in minutes.
+	 * RPM = number of rotations * msecs per minute / time in msecs
+	 */
+	*val = DIV_ROUND_UP_ULL(rotations * (MSEC_PER_SEC * 60), time);
+
+	fi->reg_val_prev = reg_val;
+	fi->time_prev = time_now;
+exit:
+	mutex_unlock(&hwmon->hwmon_lock);
+	intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
+	return ret;
+}
+
+static int
+hwm_fan_read(struct hwm_drvdata *ddat, u32 attr, long *val)
+{
+	if (attr == hwmon_fan_input)
+		return hwm_fan_input_read(ddat, val);
+
+	return -EOPNOTSUPP;
+}
+
 static umode_t
 hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type,
 	       u32 attr, int channel)
@@ -628,6 +700,8 @@ hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type,
 		return hwm_energy_is_visible(ddat, attr);
 	case hwmon_curr:
 		return hwm_curr_is_visible(ddat, attr);
+	case hwmon_fan:
+		return hwm_fan_is_visible(ddat, attr);
 	default:
 		return 0;
 	}
@@ -648,6 +722,8 @@ hwm_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		return hwm_energy_read(ddat, attr, val);
 	case hwmon_curr:
 		return hwm_curr_read(ddat, attr, val);
+	case hwmon_fan:
+		return hwm_fan_read(ddat, attr, val);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -739,12 +815,14 @@ hwm_get_preregistration_info(struct drm_i915_private *i915)
 		hwmon->rg.pkg_rapl_limit = PCU_PACKAGE_RAPL_LIMIT;
 		hwmon->rg.energy_status_all = PCU_PACKAGE_ENERGY_STATUS;
 		hwmon->rg.energy_status_tile = INVALID_MMIO_REG;
+		hwmon->rg.fan_speed = PCU_PWM_FAN_SPEED;
 	} else {
 		hwmon->rg.pkg_power_sku_unit = INVALID_MMIO_REG;
 		hwmon->rg.pkg_power_sku = INVALID_MMIO_REG;
 		hwmon->rg.pkg_rapl_limit = INVALID_MMIO_REG;
 		hwmon->rg.energy_status_all = INVALID_MMIO_REG;
 		hwmon->rg.energy_status_tile = INVALID_MMIO_REG;
+		hwmon->rg.fan_speed = INVALID_MMIO_REG;
 	}
 
 	with_intel_runtime_pm(uncore->rpm, wakeref) {
@@ -755,6 +833,16 @@ hwm_get_preregistration_info(struct drm_i915_private *i915)
 		if (i915_mmio_reg_valid(hwmon->rg.pkg_power_sku_unit))
 			val_sku_unit = intel_uncore_read(uncore,
 							 hwmon->rg.pkg_power_sku_unit);
+
+		/*
+		 * Store the initial fan register value, so that we can use it for
+		 * initial fan speed calculation.
+		 */
+		if (i915_mmio_reg_valid(hwmon->rg.fan_speed)) {
+			ddat->fi.reg_val_prev = intel_uncore_read(uncore,
+								  hwmon->rg.fan_speed);
+			ddat->fi.time_prev = get_jiffies_64();
+		}
 	}
 
 	hwmon->scl_shift_power = REG_FIELD_GET(PKG_PWR_UNIT, val_sku_unit);