[PATCH v6 7/8] drm/xe/pm: Introduce xe_device_suspend/resume()

[Raag Jadav <raag.jadav@intel.com>]

PCIe FLR prepare/re-initialization flows pretty much reflect system
suspend/resume flows with a few notable exceptions. Repurpose existing
flows for PCIe FLR with an explicit flag to distinguish between them.

Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v6: Repurpose system suspend/resume flow for FLR (Daniele)
---
 drivers/gpu/drm/xe/xe_device.c | 150 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_device.h |   2 +
 drivers/gpu/drm/xe/xe_pm.c     | 103 ++--------------------
 3 files changed, 160 insertions(+), 95 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 4b45b617a039..65f107ba1410 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -39,6 +39,7 @@
 #include "xe_force_wake.h"
 #include "xe_ggtt.h"
 #include "xe_gt.h"
+#include "xe_gt_idle.h"
 #include "xe_gt_mcr.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_vf.h"
@@ -66,6 +67,7 @@
 #include "xe_soc_remapper.h"
 #include "xe_survivability_mode.h"
 #include "xe_sriov.h"
+#include "xe_sriov_vf_ccs.h"
 #include "xe_svm.h"
 #include "xe_sysctrl.h"
 #include "xe_tile.h"
@@ -1486,3 +1488,151 @@ struct xe_vm *xe_device_asid_to_vm(struct xe_device *xe, u32 asid)
 
 	return vm;
 }
+
+/**
+ * xe_device_suspend() - Common helper for system suspend and FLR prepare
+ * @xe: xe device instance
+ * @flr: indicate FLR prepare
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int xe_device_suspend(struct xe_device *xe, bool flr)
+{
+	struct xe_gt *gt;
+	u8 id;
+	int err;
+
+	err = xe_pxp_pm_suspend(xe->pxp);
+	if (err)
+		return err;
+
+	xe_late_bind_wait_for_worker_completion(&xe->late_bind);
+
+	for_each_gt(gt, xe, id)
+		xe_gt_suspend_prepare(gt);
+
+	if (flr) {
+		for_each_gt(gt, xe, id)
+			xe_gt_flr_prepare(gt);
+	} else {
+		xe_display_pm_suspend(xe);
+
+		/* FIXME: Super racey... */
+		err = xe_bo_evict_all(xe);
+		if (err)
+			goto err_display;
+
+		for_each_gt(gt, xe, id) {
+			err = xe_gt_suspend(gt);
+			if (err)
+				goto err_display;
+		}
+	}
+
+	xe_irq_suspend(xe);
+
+	if (flr) {
+		/* TODO: Drop all user bos */
+		xe_bo_pci_dev_remove_pinned(xe);
+
+		unmap_mapping_range(xe->drm.anon_inode->i_mapping, 0, 0, 1);
+	} else {
+		xe_display_pm_suspend_late(xe);
+
+		xe_i2c_pm_suspend(xe);
+	}
+
+	return 0;
+
+err_display:
+	xe_display_pm_resume(xe);
+	xe_pxp_pm_resume(xe->pxp);
+	return err;
+}
+
+/**
+ * xe_device_resume() - Common helper for System resume and re-initialization post FLR
+ * @xe: xe device instance
+ * @flr: indicate re-initialization post FLR
+ *
+ * Return: 0 on success
+ */
+int xe_device_resume(struct xe_device *xe, bool flr)
+{
+	struct xe_tile *tile;
+	struct xe_gt *gt;
+	u8 id;
+	int err;
+
+	for_each_gt(gt, xe, id)
+		xe_gt_idle_disable_c6(gt);
+
+	for_each_tile(tile, xe, id)
+		xe_wa_apply_tile_workarounds(tile);
+
+	err = xe_pcode_ready(xe, true);
+	if (err)
+		return err;
+
+	assert_lmem_ready(xe);
+
+	if (flr) {
+		err = xe_bo_restore_map(xe);
+		if (err)
+			return err;
+
+		for_each_gt(gt, xe, id) {
+			err = xe_gt_reinit(gt);
+			if (err)
+				return err;
+		}
+	} else {
+		xe_display_pm_resume_early(xe);
+
+		/*
+		 * This only restores pinned memory which is the memory required for the
+		 * GT(s) to resume.
+		 */
+		err = xe_bo_restore_early(xe);
+		if (err)
+			return err;
+	}
+
+	xe_i2c_pm_resume(xe, true);
+
+	xe_sysctrl_pm_resume(xe);
+
+	xe_irq_resume(xe);
+
+	for_each_gt(gt, xe, id) {
+		err = xe_gt_resume(gt);
+		if (err)
+			break;
+	}
+
+	if (flr) {
+		if (err)
+			return err;
+	} else {
+		/*
+		 * Try to bring up display before bailing from GT resume failure,
+		 * so we don't leave the user clueless with a blank screen.
+		 */
+		xe_display_pm_resume(xe);
+		if (err)
+			return err;
+
+		err = xe_bo_restore_late(xe);
+		if (err)
+			return err;
+
+		if (IS_VF_CCS_READY(xe))
+			xe_sriov_vf_ccs_register_context(xe);
+	}
+
+	xe_pxp_pm_resume(xe->pxp);
+
+	xe_late_bind_fw_load(&xe->late_bind);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 555c191f7510..d776e620cdf3 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -48,7 +48,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 int xe_device_probe_early(struct xe_device *xe);
 int xe_device_probe(struct xe_device *xe);
 void xe_device_remove(struct xe_device *xe);
+int xe_device_resume(struct xe_device *xe, bool flr);
 void xe_device_shutdown(struct xe_device *xe);
+int xe_device_suspend(struct xe_device *xe, bool flr);
 
 void xe_device_wmb(struct xe_device *xe);
 
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index d4672eb07476..e2097e4524af 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -171,52 +171,18 @@ static void xe_rpm_lockmap_release(const struct xe_device *xe)
  */
 int xe_pm_suspend(struct xe_device *xe)
 {
-	struct xe_gt *gt;
-	u8 id;
 	int err;
 
 	drm_dbg(&xe->drm, "Suspending device\n");
 	xe_pm_block_begin_signalling();
 	trace_xe_pm_suspend(xe, __builtin_return_address(0));
 
-	err = xe_pxp_pm_suspend(xe->pxp);
+	err = xe_device_suspend(xe, false);
 	if (err)
-		goto err;
+		drm_dbg(&xe->drm, "Device suspend failed %d\n", err);
+	else
+		drm_dbg(&xe->drm, "Device suspended\n");
 
-	xe_late_bind_wait_for_worker_completion(&xe->late_bind);
-
-	for_each_gt(gt, xe, id)
-		xe_gt_suspend_prepare(gt);
-
-	xe_display_pm_suspend(xe);
-
-	/* FIXME: Super racey... */
-	err = xe_bo_evict_all(xe);
-	if (err)
-		goto err_display;
-
-	for_each_gt(gt, xe, id) {
-		err = xe_gt_suspend(gt);
-		if (err)
-			goto err_display;
-	}
-
-	xe_irq_suspend(xe);
-
-	xe_display_pm_suspend_late(xe);
-
-	xe_i2c_pm_suspend(xe);
-
-	drm_dbg(&xe->drm, "Device suspended\n");
-	xe_pm_block_end_signalling();
-
-	return 0;
-
-err_display:
-	xe_display_pm_resume(xe);
-	xe_pxp_pm_resume(xe->pxp);
-err:
-	drm_dbg(&xe->drm, "Device suspend failed %d\n", err);
 	xe_pm_block_end_signalling();
 	return err;
 }
@@ -229,71 +195,18 @@ int xe_pm_suspend(struct xe_device *xe)
  */
 int xe_pm_resume(struct xe_device *xe)
 {
-	struct xe_tile *tile;
-	struct xe_gt *gt;
-	u8 id;
 	int err;
 
 	xe_pm_block_begin_signalling();
 	drm_dbg(&xe->drm, "Resuming device\n");
 	trace_xe_pm_resume(xe, __builtin_return_address(0));
 
-	for_each_gt(gt, xe, id)
-		xe_gt_idle_disable_c6(gt);
-
-	for_each_tile(tile, xe, id)
-		xe_wa_apply_tile_workarounds(tile);
-
-	err = xe_pcode_ready(xe, true);
-	if (err)
-		return err;
-
-	xe_display_pm_resume_early(xe);
-
-	/*
-	 * This only restores pinned memory which is the memory required for the
-	 * GT(s) to resume.
-	 */
-	err = xe_bo_restore_early(xe);
-	if (err)
-		goto err;
-
-	xe_i2c_pm_resume(xe, true);
-
-	xe_sysctrl_pm_resume(xe);
-
-	xe_irq_resume(xe);
-
-	for_each_gt(gt, xe, id) {
-		err = xe_gt_resume(gt);
-		if (err)
-			break;
-	}
-
-	/*
-	 * Try to bring up display before bailing from GT resume failure,
-	 * so we don't leave the user clueless with a blank screen.
-	 */
-	xe_display_pm_resume(xe);
-	if (err)
-		goto err;
-
-	err = xe_bo_restore_late(xe);
+	err = xe_device_resume(xe, false);
 	if (err)
-		goto err;
-
-	xe_pxp_pm_resume(xe->pxp);
-
-	if (IS_VF_CCS_READY(xe))
-		xe_sriov_vf_ccs_register_context(xe);
-
-	xe_late_bind_fw_load(&xe->late_bind);
+		drm_dbg(&xe->drm, "Device resume failed %d\n", err);
+	else
+		drm_dbg(&xe->drm, "Device resumed\n");
 
-	drm_dbg(&xe->drm, "Device resumed\n");
-	xe_pm_block_end_signalling();
-	return 0;
-err:
-	drm_dbg(&xe->drm, "Device resume failed %d\n", err);
 	xe_pm_block_end_signalling();
 	return err;
 }
-- 
2.43.0