Revert "drm/xe: make gt_remove use devm"

This reverts commit cd506a33b0d9759e0a58556799b1b38650fa3698.

The gt_remove function was explicitly added as part of the remove flow
instead of using drmm/devm automatic cleanup due to it being illegal
to remove a component after the driver has been detached from the pci
device; the GSC proxy component is removed as part of gt_remove, so we
need to do it in the pci cleanup flow. The function already has a
comment above it to explain this.

Note that the change to use the devm also caused an invalid pointer
deref in the gsc_proxy unbind function, but I didn't bother to debug
which pointer was bad since we shouldn't be calling the unbind that
late anyway and this revert fixes it.

Both issue were not seen in CI because the GSC loading is temporarily
disabled due to a critical bug, which means we're not binding the
component.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240528182354.1200424-1-daniele.ceraolospurio@intel.com

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d1560f5d4b8480b17f3af6eda85eef7cf9b124f8..f0a2604bf62ad60799bf8fd1797832c7a1c32a4a 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -544,6 +544,7 @@ int xe_device_probe(struct xe_device *xe)
        struct xe_tile *tile;
        struct xe_gt *gt;
        int err;
+       u8 last_gt;
        u8 id;
 
        xe_pat_init_early(xe);
@@ -642,16 +643,18 @@ int xe_device_probe(struct xe_device *xe)
                goto err_irq_shutdown;
 
        for_each_gt(gt, xe, id) {
+               last_gt = id;
+
                err = xe_gt_init(gt);
                if (err)
-                       goto err_irq_shutdown;
+                       goto err_fini_gt;
        }
 
        xe_heci_gsc_init(xe);
 
        err = xe_display_init(xe);
        if (err)
-               goto err_irq_shutdown;
+               goto err_fini_gt;
 
        err = drm_dev_register(&xe->drm, 0);
        if (err)
@@ -667,6 +670,15 @@ int xe_device_probe(struct xe_device *xe)
 
 err_fini_display:
        xe_display_driver_remove(xe);
+
+err_fini_gt:
+       for_each_gt(gt, xe, id) {
+               if (id < last_gt)
+                       xe_gt_remove(gt);
+               else
+                       break;
+       }
+
 err_irq_shutdown:
        xe_irq_shutdown(xe);
 err:
@@ -684,12 +696,18 @@ static void xe_device_remove_display(struct xe_device *xe)
 
 void xe_device_remove(struct xe_device *xe)
 {
+       struct xe_gt *gt;
+       u8 id;
+
        xe_device_remove_display(xe);
 
        xe_display_fini(xe);
 
        xe_heci_gsc_fini(xe);
 
+       for_each_gt(gt, xe, id)
+               xe_gt_remove(gt);
+
        xe_irq_shutdown(xe);
 }
 

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 9e9da887f4ca36c1fa78194357a58d70f3ae25f8..0a1e04fe2690f85e162543e6bef956d30ffa27a4 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -93,14 +93,16 @@ void xe_gt_sanitize(struct xe_gt *gt)
        gt->uc.guc.submission_state.enabled = false;
 }
 
-/*
- * Clean up the GT structures before driver removal. This function should only
- * act on objects/structures that must be cleaned before the driver removal
- * callback is complete and therefore can't be deferred to a drmm action.
+/**
+ * xe_gt_remove() - Clean up the GT structures before driver removal
+ * @gt: the GT object
+ *
+ * This function should only act on objects/structures that must be cleaned
+ * before the driver removal callback is complete and therefore can't be
+ * deferred to a drmm action.
  */
-static void gt_remove(void *arg)
+void xe_gt_remove(struct xe_gt *gt)
 {
-       struct xe_gt *gt = arg;
        int i;
 
        xe_uc_remove(&gt->uc);
@@ -566,7 +568,7 @@ int xe_gt_init(struct xe_gt *gt)
 
        xe_gt_record_user_engines(gt);
 
-       return devm_add_action_or_reset(gt_to_xe(gt)->drm.dev, gt_remove, gt);
+       return 0;
 }
 
 void xe_gt_record_user_engines(struct xe_gt *gt)

diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
index d0747edfe0200f897e403051f31a8b2959cf44c1..9073ac68a7771a1203271526d8c22a8d4f445133 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.h
+++ b/drivers/gpu/drm/xe/xe_gt.h
@@ -56,6 +56,7 @@ int xe_gt_suspend(struct xe_gt *gt);
 int xe_gt_resume(struct xe_gt *gt);
 void xe_gt_reset_async(struct xe_gt *gt);
 void xe_gt_sanitize(struct xe_gt *gt);
+void xe_gt_remove(struct xe_gt *gt);
 
 /**
  * xe_gt_any_hw_engine_by_reset_domain - scan the list of engines and return the