Commit 649a125a authored by Daniele Ceraolo Spurio's avatar Daniele Ceraolo Spurio
Browse files

drm/xe: Always check force_wake_get return code



A force_wake_get failure means that the HW might not be awake for the
access we're doing; this can lead to an immediate error or it can be a
more subtle problem (e.g. a register read might return an incorrect
value that is still valid, leading the driver to make a wrong choice
instead of flagging an error).
We avoid an error from the force_wake function because callers might
handle or tolerate the error, but this only works if all callers
are checking the error code. The majority already do, but a few are not.
These are mainly falling into 3 categories, which are each handled
differently:

1) error capture: in this case we want to continue the capture, but we
   log an info message in dmesg to notify the user that the capture
   might have incorrect data.

2) ioctl: in this case we return a -EIO error to userspace

3) unabortable actions: these are scenarios where we can't simply abort
   and retry and so it's better to just try it anyway because there is a
   chance the HW is awake even with the failure. In this case we throw a
   warning so we know there was a forcewake problem if something fails
   down the line.

v2: use gt_WARN_ON where appropriate

Signed-off-by: default avatarDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: default avatarMatt Roper <matthew.d.roper@intel.com>
Reviewed-by: default avatarTejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240318154924.3453513-1-daniele.ceraolospurio@intel.com
parent 0267ee19
Loading
Loading
Loading
Loading
+7 −2
Original line number Diff line number Diff line
@@ -13,6 +13,7 @@
#include "xe_exec_queue.h"
#include "xe_force_wake.h"
#include "xe_gt.h"
#include "xe_gt_printk.h"
#include "xe_guc_ct.h"
#include "xe_guc_submit.h"
#include "xe_hw_engine.h"
@@ -64,7 +65,9 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
{
	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);

	xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
	/* keep going if fw fails as we still want to save the memory and SW data */
	if (xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL))
		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
	xe_vm_snapshot_capture_delayed(ss->vm);
	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
	xe_force_wake_put(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
@@ -180,7 +183,9 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
		}
	}

	xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
	/* keep going if fw fails as we still want to save the memory and SW data */
	if (xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL))
		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");

	coredump->snapshot.ct = xe_guc_ct_snapshot_capture(&guc->ct, true);
	coredump->snapshot.ge = xe_guc_exec_queue_snapshot_capture(job);
+1 −1
Original line number Diff line number Diff line
@@ -326,7 +326,7 @@ static void gsc_work(struct work_struct *work)
	spin_unlock_irq(&gsc->lock);

	xe_pm_runtime_get(xe);
	xe_force_wake_get(gt_to_fw(gt), XE_FW_GSC);
	xe_gt_WARN_ON(gt, xe_force_wake_get(gt_to_fw(gt), XE_FW_GSC));

	if (actions & GSC_ACTION_ER_COMPLETE) {
		ret = gsc_er_complete(gt);
+1 −1
Original line number Diff line number Diff line
@@ -247,7 +247,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)

		xe_gt_tlb_invalidation_wait(gt, seqno);
	} else if (xe_device_uc_enabled(xe)) {
		xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
		xe_gt_WARN_ON(gt, xe_force_wake_get(gt_to_fw(gt), XE_FW_GT));
		if (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20) {
			xe_mmio_write32(gt, PVC_GUC_TLB_INV_DESC1,
					PVC_GUC_TLB_INV_DESC1_INVALIDATE);
+3 −2
Original line number Diff line number Diff line
@@ -240,10 +240,11 @@ static void guc_write_params(struct xe_guc *guc)
static void guc_fini(struct drm_device *drm, void *arg)
{
	struct xe_guc *guc = arg;
	struct xe_gt *gt = guc_to_gt(guc);

	xe_force_wake_get(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL);
	xe_gt_WARN_ON(gt, xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL));
	xe_uc_fini_hw(&guc_to_gt(guc)->uc);
	xe_force_wake_put(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL);
	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
}

/**
+1 −1
Original line number Diff line number Diff line
@@ -927,7 +927,7 @@ static void xe_guc_pc_fini(struct drm_device *drm, void *arg)
		return;
	}

	xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL);
	XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL));
	XE_WARN_ON(xe_guc_pc_gucrc_disable(pc));
	XE_WARN_ON(xe_guc_pc_stop(pc));
	xe_force_wake_put(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL);
Loading