drm/xe/pm: Toggle d3cold_allowed using vram_usages

Adding support to control d3cold by using vram_usages metric from
ttm resource manager.
When root port  is capable of d3cold but xe has disallowed d3cold
due to vram_usages above vram_d3ccold_threshol. It is required to
disable d3cold to avoid any resume failure because root port can
still transition to d3cold when all of pcie endpoints and
{upstream, virtual} switch ports will transition to d3hot.
Also cleaning up the TODO code comment.

v2:
- Modify d3cold.allowed in xe_pm_d3cold_allowed_toggle. [Riana]
- Cond changed (total_vram_used_mb < xe->d3cold.vram_threshold)
  according to doc comment.
v3:
- Added enum instead of true/false argument in
  d3cold_toggle(). [Rodrigo]
- Removed TODO comment. [Rodrigo]

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Reviewed-by: Badal Nilawar <badal.nilawar@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230718080703.239343-5-anshuman.gupta@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_pci.c

@@ -25,6 +25,11 @@
 #include "xe_pm.h"
 #include "xe_step.h"
 
+enum toggle_d3cold {
+	D3COLD_DISABLE,
+	D3COLD_ENABLE,
+};
+
 struct xe_subplatform_desc {
 	enum xe_subplatform subplatform;
 	const char *name;
@@ -726,6 +731,28 @@ static int xe_pci_resume(struct device *dev)
 	return 0;
 }
 
+static void d3cold_toggle(struct pci_dev *pdev, enum toggle_d3cold toggle)
+{
+	struct xe_device *xe = pdev_to_xe_device(pdev);
+	struct pci_dev *root_pdev;
+
+	if (!xe->d3cold.capable)
+		return;
+
+	root_pdev = pcie_find_root_port(pdev);
+	if (!root_pdev)
+		return;
+
+	switch (toggle) {
+	case D3COLD_DISABLE:
+		pci_d3cold_disable(root_pdev);
+		break;
+	case D3COLD_ENABLE:
+		pci_d3cold_enable(root_pdev);
+		break;
+	}
+}
+
 static int xe_pci_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -743,6 +770,7 @@ static int xe_pci_runtime_suspend(struct device *dev)
 		pci_ignore_hotplug(pdev);
 		pci_set_power_state(pdev, PCI_D3cold);
 	} else {
+		d3cold_toggle(pdev, D3COLD_DISABLE);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
 
@@ -767,6 +795,8 @@ static int xe_pci_runtime_resume(struct device *dev)
 			return err;
 
 		pci_set_master(pdev);
+	} else {
+		d3cold_toggle(pdev, D3COLD_ENABLE);
 	}
 
 	return xe_pm_runtime_resume(xe);
@@ -780,15 +810,15 @@ static int xe_pci_runtime_idle(struct device *dev)
 	if (!xe->d3cold.capable) {
 		xe->d3cold.allowed = false;
 	} else {
+		xe_pm_d3cold_allowed_toggle(xe);
+
 		/*
 		 * TODO: d3cold should be allowed (true) if
 		 * (IS_DGFX(xe) && !xe_device_mem_access_ongoing(xe))
 		 * but maybe include some other conditions. So, before
 		 * we can re-enable the D3cold, we need to:
 		 * 1. rewrite the VRAM save / restore to avoid buffer object locks
-		 * 2. block D3cold if we have a big amount of device memory in use
-		 *    in order to reduce the latency.
-		 * 3. at resume, detect if we really lost power and avoid memory
+		 * 2. at resume, detect if we really lost power and avoid memory
 		 *    restoration if we were only up to d3cold
 		 */
 		xe->d3cold.allowed = false;

drivers/gpu/drm/xe/xe_pm.c

@@ -280,3 +280,28 @@ int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold)
 
 	return 0;
 }
+
+void xe_pm_d3cold_allowed_toggle(struct xe_device *xe)
+{
+	struct ttm_resource_manager *man;
+	u32 total_vram_used_mb = 0;
+	u64 vram_used;
+	int i;
+
+	for (i = XE_PL_VRAM0; i <= XE_PL_VRAM1; ++i) {
+		man = ttm_manager_type(&xe->ttm, i);
+		if (man) {
+			vram_used = ttm_resource_manager_usage(man);
+			total_vram_used_mb += DIV_ROUND_UP_ULL(vram_used, 1024 * 1024);
+		}
+	}
+
+	mutex_lock(&xe->d3cold.lock);
+
+	if (total_vram_used_mb < xe->d3cold.vram_threshold)
+		xe->d3cold.allowed = true;
+	else
+		xe->d3cold.allowed = false;
+
+	mutex_unlock(&xe->d3cold.lock);
+}

drivers/gpu/drm/xe/xe_pm.h

@@ -25,5 +25,6 @@ bool xe_pm_runtime_resume_if_suspended(struct xe_device *xe);
 int xe_pm_runtime_get_if_active(struct xe_device *xe);
 void xe_pm_assert_unbounded_bridge(struct xe_device *xe);
 int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold);
+void xe_pm_d3cold_allowed_toggle(struct xe_device *xe);
 
 #endif