drm/xe: Fix tlb invalidation when wedging

If GuC fails to load, the driver wedges, but in the process it tries to
do stuff that may not be initialized yet. This moves the
xe_gt_tlb_invalidation_init() to be done earlier: as its own doc says,
it's a software-only initialization and should had been named with the
_early() suffix.

Move it to be called by xe_gt_init_early(), so the locks and seqno are
initialized, avoiding a NULL ptr deref when wedging:

	xe 0000:03:00.0: [drm] *ERROR* GT0: load failed: status: Reset = 0, BootROM = 0x50, UKernel = 0x00, MIA = 0x00, Auth = 0x01
	xe 0000:03:00.0: [drm] *ERROR* GT0: firmware signature verification failed
	xe 0000:03:00.0: [drm] *ERROR* CRITICAL: Xe has declared device 0000:03:00.0 as wedged.
	...
	BUG: kernel NULL pointer dereference, address: 0000000000000000
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	PGD 0 P4D 0
	Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
	CPU: 9 UID: 0 PID: 3908 Comm: modprobe Tainted: G     U  W          6.13.0-rc4-xe+ #3
	Tainted: [U]=USER, [W]=WARN
	Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-S ADP-S DDR5 UDIMM CRB, BIOS ADLSFWI1.R00.3275.A00.2207010640 07/01/2022
	RIP: 0010:xe_gt_tlb_invalidation_reset+0x75/0x110 [xe]

This can be easily triggered by poking the GuC binary to force a
signature failure. There will still be an extra message,

	xe 0000:03:00.0: [drm] *ERROR* GT0: GuC mmio request 0x4100: no reply 0x4100

but that's better than a NULL ptr deref.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3956
Fixes: c9474b726b93 ("drm/xe: Wedge the entire device")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250103001111.331684-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 5001ef3af8f2c972d6fd9c5221a8457556f8bea6)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index d6744be01a687cf7009af18b6340be4c57e91a65..94d468d01253dd5d5cf2957a09e4bd3ea68f6e53 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -387,6 +387,10 @@ int xe_gt_init_early(struct xe_gt *gt)
        xe_force_wake_init_gt(gt, gt_to_fw(gt));
        spin_lock_init(&gt->global_invl_lock);
 
+       err = xe_gt_tlb_invalidation_init_early(gt);
+       if (err)
+               return err;
+
        return 0;
 }
 
@@ -588,10 +592,6 @@ int xe_gt_init(struct xe_gt *gt)
                xe_hw_fence_irq_init(&gt->fence_irq[i]);
        }
 
-       err = xe_gt_tlb_invalidation_init(gt);
-       if (err)
-               return err;
-
        err = xe_gt_pagefault_init(gt);
        if (err)
                return err;

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 6146d1776bdaccf9ef827db0048e3cfe00ae2366..0a0af413770eb28bbbdd479eee3eb86af5e9fe5d 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -106,7 +106,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 }
 
 /**
- * xe_gt_tlb_invalidation_init - Initialize GT TLB invalidation state
+ * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state
  * @gt: graphics tile
  *
  * Initialize GT TLB invalidation state, purely software initialization, should
@@ -114,7 +114,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
  *
  * Return: 0 on success, negative error code on error.
  */
-int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
+int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 {
        gt->tlb_invalidation.seqno = 1;
        INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index 00b1c6c01e8d9591ca30d05d9f8e5a6871c142d6..672acfcdf0d70de210818a0d11d76a1849d67cef 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -14,7 +14,8 @@ struct xe_gt;
 struct xe_guc;
 struct xe_vma;
 
-int xe_gt_tlb_invalidation_init(struct xe_gt *gt);
+int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt);
+
 void xe_gt_tlb_invalidation_reset(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,