[PATCH 2/2] RFC drm/xe: re-order lmem init check and wait for initialization to complete

Riana Tauro riana.tauro at intel.com
Fri Mar 8 08:55:17 UTC 2024


Lmem init check should be done only after pcode initialization
status is complete. Move lmem init check after pcode status
check. Also wait for a short while after pcode status check
to allow completion of the task.

Failing to do so, can lead to aborting the module load
leaving the system unusable. Wait until the lmem initialization
is complete within a timeout (60s) or till the user aborts.

Signed-off-by: Riana Tauro <riana.tauro at intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 53 +++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_mmio.c   | 29 -------------------
 2 files changed, 52 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 83dd60f68566..4806e7806be5 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -413,12 +413,59 @@ static int xe_set_dma_info(struct xe_device *xe)
 	return err;
 }
 
+static int verify_lmem_ready(struct xe_gt *gt)
+{
+	return xe_mmio_read32(gt, GU_CNTL) & LMEM_INIT;
+}
+
+static int wait_for_lmem_ready(struct xe_device *xe)
+{
+	struct xe_gt *gt = xe_root_mmio_gt(xe);
+	unsigned long timeout, start;
+
+	if (!IS_DGFX(xe))
+		return 0;
+
+	if (IS_SRIOV_VF(xe))
+		return 0;
+	/*
+	 * The boot firmware initializes local memory and assesses its health.
+	 * If memory training fails, the punit will have been instructed to
+	 * keep the GT powered down; we won't be able to communicate with it
+	 * and we should not continue with driver initialization.
+	 */
+	if (verify_lmem_ready(gt))
+		return 0;
+
+	drm_dbg(&xe->drm, "Waiting for lmem initialisation\n");
+
+	start = jiffies;
+	timeout = start + msecs_to_jiffies(60 * 1000); /* 60 sec! */
+
+	do {
+		if (signal_pending(current))
+			return -EINTR;
+
+		if (time_after(jiffies, timeout))
+			return -EPROBE_DEFER;
+
+		msleep(20);
+
+	} while (!verify_lmem_ready(gt));
+
+	drm_dbg(&xe->drm, "lmem ready after %ums",
+		jiffies_to_msecs(jiffies - start));
+
+	return 0;
+}
+
 /**
  * xe_device_probe_early: Device early probe
  * @xe: xe device instance
  *
  * Initialize MMIO resources that don't require any
- * knowledge about tile count. Also initialize pcode
+ * knowledge about tile count. Also initialize pcode and
+ * check vram initialization on root tile.
  *
  * Return: 0 on success, error code on failure
  */
@@ -438,6 +485,10 @@ int xe_device_probe_early(struct xe_device *xe)
 	if (err)
 		return err;
 
+	err = wait_for_lmem_ready(xe);
+	if (err)
+		return err;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index 7ba2477452d7..7fc0c5453b21 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -360,30 +360,6 @@ static void mmio_fini(struct drm_device *drm, void *arg)
 		iounmap(xe->mem.vram.mapping);
 }
 
-static int xe_verify_lmem_ready(struct xe_device *xe)
-{
-	struct xe_gt *gt = xe_root_mmio_gt(xe);
-
-	if (!IS_DGFX(xe))
-		return 0;
-
-	if (IS_SRIOV_VF(xe))
-		return 0;
-
-	/*
-	 * The boot firmware initializes local memory and assesses its health.
-	 * If memory training fails, the punit will have been instructed to
-	 * keep the GT powered down; we won't be able to communicate with it
-	 * and we should not continue with driver initialization.
-	 */
-	if (!(xe_mmio_read32(gt, GU_CNTL) & LMEM_INIT)) {
-		drm_err(&xe->drm, "VRAM not initialized by firmware\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
 int xe_mmio_init(struct xe_device *xe)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -407,16 +383,11 @@ int xe_mmio_init(struct xe_device *xe)
 int xe_mmio_root_tile_init(struct xe_device *xe)
 {
 	struct xe_tile *root_tile = xe_device_get_root_tile(xe);
-	int err;
 
 	/* Setup first tile; other tiles (if present) will be setup later. */
 	root_tile->mmio.size = SZ_16M;
 	root_tile->mmio.regs = xe->mmio.regs;
 
-	err = xe_verify_lmem_ready(xe);
-	if (err)
-		return err;
-
 	return 0;
 }
 
-- 
2.40.0



More information about the Intel-xe mailing list