drm/i915: Prepare for multiple GTs

On a multi-tile platform, each tile has its own registers + GGTT
space, and BAR 0 is extended to cover all of them.

Up to four GTs are supported in i915->gt[], with slot zero
shadowing the existing i915->gt0 to enable source compatibility
with legacy driver paths. A for_each_gt macro is added to iterate
over the GTs and will be used by upcoming patches that convert
various parts of the driver to be multi-gt aware.

Only the primary/root tile is initialized for now; the other
tiles will be detected and plugged in by future patches once the
necessary infrastructure is in place to handle them.

Signed-off-by: Abdiel Janulgue <abdiel.janulgue@gmail.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220318233938.149744-4-andi.shyti@linux.intel.com

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

@@ -29,7 +29,7 @@
 #include "intel_uncore.h"
 #include "shmem_utils.h"
 
-void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+static void __intel_gt_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(&gt->irq_lock);
 
@@ -51,17 +51,23 @@ void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 	intel_rps_init_early(&gt->rps);
 }
 
-void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+/* Preliminary initialization of Tile 0 */
+void intel_root_gt_init_early(struct drm_i915_private *i915)
 {
+	struct intel_gt *gt = to_gt(i915);
+
 	gt->i915 = i915;
 	gt->uncore = &i915->uncore;
+
+	__intel_gt_init_early(gt);
 }
 
-int intel_gt_probe_lmem(struct intel_gt *gt)
+static int intel_gt_probe_lmem(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
+	unsigned int instance = gt->info.id;
+	int id = INTEL_REGION_LMEM_0 + instance;
 	struct intel_memory_region *mem;
-	int id;
 	int err;
 
 	mem = intel_gt_setup_lmem(gt);
@@ -76,9 +82,8 @@ int intel_gt_probe_lmem(struct intel_gt *gt)
 		return err;
 	}
 
-	id = INTEL_REGION_LMEM_0;
-
 	mem->id = id;
+	mem->instance = instance;
 
 	intel_memory_region_set_name(mem, "local%u", mem->instance);
 
@@ -807,16 +812,21 @@ void intel_gt_driver_release(struct intel_gt *gt)
 	intel_gt_fini_hwconfig(gt);
 }
 
-void intel_gt_driver_late_release(struct intel_gt *gt)
+void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 {
+	struct intel_gt *gt;
+	unsigned int id;
+
 	/* We need to wait for inflight RCU frees to release their grip */
 	rcu_barrier();
 
-	intel_uc_driver_late_release(&gt->uc);
-	intel_gt_fini_requests(gt);
-	intel_gt_fini_reset(gt);
-	intel_gt_fini_timelines(gt);
-	intel_engines_free(gt);
+	for_each_gt(gt, i915, id) {
+		intel_uc_driver_late_release(&gt->uc);
+		intel_gt_fini_requests(gt);
+		intel_gt_fini_reset(gt);
+		intel_gt_fini_timelines(gt);
+		intel_engines_free(gt);
+	}
 }
 
 /**
@@ -1013,6 +1023,105 @@ void intel_gt_report_steering(struct drm_printer *p, struct intel_gt *gt,
 	}
 }
 
+static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr)
+{
+	int ret;
+
+	if (!gt_is_root(gt)) {
+		struct intel_uncore_mmio_debug *mmio_debug;
+		struct intel_uncore *uncore;
+
+		uncore = kzalloc(sizeof(*uncore), GFP_KERNEL);
+		if (!uncore)
+			return -ENOMEM;
+
+		mmio_debug = kzalloc(sizeof(*mmio_debug), GFP_KERNEL);
+		if (!mmio_debug) {
+			kfree(uncore);
+			return -ENOMEM;
+		}
+
+		gt->uncore = uncore;
+		gt->uncore->debug = mmio_debug;
+
+		__intel_gt_init_early(gt);
+	}
+
+	intel_uncore_init_early(gt->uncore, gt);
+
+	ret = intel_uncore_setup_mmio(gt->uncore, phys_addr);
+	if (ret)
+		return ret;
+
+	gt->phys_addr = phys_addr;
+
+	return 0;
+}
+
+static void
+intel_gt_tile_cleanup(struct intel_gt *gt)
+{
+	intel_uncore_cleanup_mmio(gt->uncore);
+
+	if (!gt_is_root(gt)) {
+		kfree(gt->uncore->debug);
+		kfree(gt->uncore);
+		kfree(gt);
+	}
+}
+
+int intel_gt_probe_all(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+	struct intel_gt *gt = &i915->gt0;
+	phys_addr_t phys_addr;
+	unsigned int mmio_bar;
+	int ret;
+
+	mmio_bar = GRAPHICS_VER(i915) == 2 ? 1 : 0;
+	phys_addr = pci_resource_start(pdev, mmio_bar);
+
+	/*
+	 * We always have at least one primary GT on any device
+	 * and it has been already initialized early during probe
+	 * in i915_driver_probe()
+	 */
+	ret = intel_gt_tile_setup(gt, phys_addr);
+	if (ret)
+		return ret;
+
+	i915->gt[0] = gt;
+
+	/* TODO: add more tiles */
+	return 0;
+}
+
+int intel_gt_tiles_init(struct drm_i915_private *i915)
+{
+	struct intel_gt *gt;
+	unsigned int id;
+	int ret;
+
+	for_each_gt(gt, i915, id) {
+		ret = intel_gt_probe_lmem(gt);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void intel_gt_release_all(struct drm_i915_private *i915)
+{
+	struct intel_gt *gt;
+	unsigned int id;
+
+	for_each_gt(gt, i915, id) {
+		intel_gt_tile_cleanup(gt);
+		i915->gt[id] = NULL;
+	}
+}
+
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p)
 {

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

@@ -39,10 +39,8 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc)
 	return container_of(huc, struct intel_gt, uc.huc);
 }
 
-void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
-void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
+void intel_root_gt_init_early(struct drm_i915_private *i915);
 int intel_gt_assign_ggtt(struct intel_gt *gt);
-int intel_gt_probe_lmem(struct intel_gt *gt);
 int intel_gt_init_mmio(struct intel_gt *gt);
 int __must_check intel_gt_init_hw(struct intel_gt *gt);
 int intel_gt_init(struct intel_gt *gt);
@@ -52,7 +50,7 @@ void intel_gt_driver_unregister(struct intel_gt *gt);
 void intel_gt_driver_remove(struct intel_gt *gt);
 void intel_gt_driver_release(struct intel_gt *gt);
 
-void intel_gt_driver_late_release(struct intel_gt *gt);
+void intel_gt_driver_late_release_all(struct drm_i915_private *i915);
 
 int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 
@@ -97,6 +95,17 @@ u32 intel_gt_read_register(struct intel_gt *gt, i915_reg_t reg);
 
 void intel_gt_report_steering(struct drm_printer *p, struct intel_gt *gt,
 			      bool dump_table);
+
+int intel_gt_probe_all(struct drm_i915_private *i915);
+int intel_gt_tiles_init(struct drm_i915_private *i915);
+void intel_gt_release_all(struct drm_i915_private *i915);
+
+#define for_each_gt(gt__, i915__, id__) \
+	for ((id__) = 0; \
+	     (id__) < I915_MAX_GT; \
+	     (id__)++) \
+		for_each_if(((gt__) = (i915__)->gt[(id__)]))
+
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p);
 

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

@@ -128,7 +128,14 @@ static const struct intel_wakeref_ops wf_ops = {
 
 void intel_gt_pm_init_early(struct intel_gt *gt)
 {
-	intel_wakeref_init(&gt->wakeref, gt->uncore->rpm, &wf_ops);
+	/*
+	 * We access the runtime_pm structure via gt->i915 here rather than
+	 * gt->uncore as we do elsewhere in the file because gt->uncore is not
+	 * yet initialized for all tiles at this point in the driver startup.
+	 * runtime_pm is per-device rather than per-tile, so this is still the
+	 * correct structure.
+	 */
+	intel_wakeref_init(&gt->wakeref, &gt->i915->runtime_pm, &wf_ops);
 	seqcount_mutex_init(&gt->stats.lock, &gt->wakeref.mutex);
 }
 

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

@@ -188,7 +188,14 @@ struct intel_gt {
 		u8 instanceid;
 	} default_steering;
 
+	/*
+	 * Base of per-tile GTTMMADR where we can derive the MMIO and the GGTT.
+	 */
+	phys_addr_t phys_addr;
+
 	struct intel_gt_info {
+		unsigned int id;
+
 		intel_engine_mask_t engine_mask;
 
 		u32 l3bank_mask;

drivers/gpu/drm/i915/i915_driver.c

@@ -320,9 +320,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 	intel_device_info_subplatform_init(dev_priv);
 	intel_step_init(dev_priv);
 
-	intel_gt_init_early(to_gt(dev_priv), dev_priv);
 	intel_uncore_mmio_debug_init_early(&dev_priv->mmio_debug);
-	intel_uncore_init_early(&dev_priv->uncore, to_gt(dev_priv));
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
@@ -353,7 +351,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 
 	intel_wopcm_init_early(&dev_priv->wopcm);
 
-	__intel_gt_init_early(to_gt(dev_priv), dev_priv);
+	intel_root_gt_init_early(dev_priv);
 
 	i915_gem_init_early(dev_priv);
 
@@ -374,7 +372,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 
 err_gem:
 	i915_gem_cleanup_early(dev_priv);
-	intel_gt_driver_late_release(to_gt(dev_priv));
+	intel_gt_driver_late_release_all(dev_priv);
 	intel_region_ttm_device_fini(dev_priv);
 err_ttm:
 	vlv_suspend_cleanup(dev_priv);
@@ -393,7 +391,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv)
 	intel_irq_fini(dev_priv);
 	intel_power_domains_cleanup(dev_priv);
 	i915_gem_cleanup_early(dev_priv);
-	intel_gt_driver_late_release(to_gt(dev_priv));
+	intel_gt_driver_late_release_all(dev_priv);
 	intel_region_ttm_device_fini(dev_priv);
 	vlv_suspend_cleanup(dev_priv);
 	i915_workqueues_cleanup(dev_priv);
@@ -424,13 +422,9 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv)
 	if (ret < 0)
 		return ret;
 
-	ret = intel_uncore_setup_mmio(&dev_priv->uncore);
-	if (ret < 0)
-		goto err_bridge;
-
 	ret = intel_uncore_init_mmio(&dev_priv->uncore);
 	if (ret)
-		goto err_mmio;
+		return ret;
 
 	/* Try to make sure MCHBAR is enabled before poking at it */
 	intel_setup_mchbar(dev_priv);
@@ -448,9 +442,6 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv)
 err_uncore:
 	intel_teardown_mchbar(dev_priv);
 	intel_uncore_fini_mmio(&dev_priv->uncore);
-err_mmio:
-	intel_uncore_cleanup_mmio(&dev_priv->uncore);
-err_bridge:
 	pci_dev_put(dev_priv->bridge_dev);
 
 	return ret;
@@ -464,7 +455,6 @@ static void i915_driver_mmio_release(struct drm_i915_private *dev_priv)
 {
 	intel_teardown_mchbar(dev_priv);
 	intel_uncore_fini_mmio(&dev_priv->uncore);
-	intel_uncore_cleanup_mmio(&dev_priv->uncore);
 	pci_dev_put(dev_priv->bridge_dev);
 }
 
@@ -597,7 +587,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_ggtt;
 
-	ret = intel_gt_probe_lmem(to_gt(dev_priv));
+	ret = intel_gt_tiles_init(dev_priv);
 	if (ret)
 		goto err_mem_regions;
 
@@ -847,10 +837,14 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	intel_vgpu_detect(i915);
 
-	ret = i915_driver_mmio_probe(i915);
+	ret = intel_gt_probe_all(i915);
 	if (ret < 0)
 		goto out_runtime_pm_put;
 
+	ret = i915_driver_mmio_probe(i915);
+	if (ret < 0)
+		goto out_tiles_cleanup;
+
 	ret = i915_driver_hw_probe(i915);
 	if (ret < 0)
 		goto out_cleanup_mmio;
@@ -907,6 +901,8 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i915_ggtt_driver_late_release(i915);
 out_cleanup_mmio:
 	i915_driver_mmio_release(i915);
+out_tiles_cleanup:
+	intel_gt_release_all(i915);
 out_runtime_pm_put:
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 	i915_driver_late_release(i915);

drivers/gpu/drm/i915/i915_drv.h

@@ -808,6 +808,12 @@ struct drm_i915_private {
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct intel_gt gt0;
 
+	/*
+	 * i915->gt[0] == &i915->gt0
+	 */
+#define I915_MAX_GT 4
+	struct intel_gt *gt[I915_MAX_GT];
+
 	struct {
 		struct i915_gem_contexts {
 			spinlock_t lock; /* locks list */

drivers/gpu/drm/i915/intel_memory_region.h

@@ -30,6 +30,9 @@ enum intel_memory_type {
 enum intel_region_id {
 	INTEL_REGION_SMEM = 0,
 	INTEL_REGION_LMEM_0,
+	INTEL_REGION_LMEM_1,
+	INTEL_REGION_LMEM_2,
+	INTEL_REGION_LMEM_3,
 	INTEL_REGION_STOLEN_SMEM,
 	INTEL_REGION_STOLEN_LMEM,
 	INTEL_REGION_UNKNOWN, /* Should be last */