drm/i915/huc: Fix fence not released on early probe errors

[ Upstream commit e3ea2eae70692a455e256787e4f54153fb739b90 ]

HuC delayed loading fence, introduced with commit 27536e03271da
("drm/i915/huc: track delayed HuC load with a fence"), is registered with
object tracker early on driver probe but unregistered only from driver
remove, which is not called on early probe errors.  Since its memory is
allocated under devres, then released anyway, it may happen to be
allocated again to the fence and reused on future driver probes, resulting
in kernel warnings that taint the kernel:

<4> [309.731371] ------------[ cut here ]------------
<3> [309.731373] ODEBUG: init destroyed (active state 0) object: ffff88813d7dd2e0 object type: i915_sw_fence hint: sw_fence_dummy_notify+0x0/0x20 [i915]
<4> [309.731575] WARNING: CPU: 2 PID: 3161 at lib/debugobjects.c:612 debug_print_object+0x93/0xf0
...
<4> [309.731693] CPU: 2 UID: 0 PID: 3161 Comm: i915_module_loa Tainted: G     U             6.14.0-CI_DRM_16362-gf0fd77956987+ #1
...
<4> [309.731700] RIP: 0010:debug_print_object+0x93/0xf0
...
<4> [309.731728] Call Trace:
<4> [309.731730]  <TASK>
...
<4> [309.731949]  __debug_object_init+0x17b/0x1c0
<4> [309.731957]  debug_object_init+0x34/0x50
<4> [309.732126]  __i915_sw_fence_init+0x34/0x60 [i915]
<4> [309.732256]  intel_huc_init_early+0x4b/0x1d0 [i915]
<4> [309.732468]  intel_uc_init_early+0x61/0x680 [i915]
<4> [309.732667]  intel_gt_common_init_early+0x105/0x130 [i915]
<4> [309.732804]  intel_root_gt_init_early+0x63/0x80 [i915]
<4> [309.732938]  i915_driver_probe+0x1fa/0xeb0 [i915]
<4> [309.733075]  i915_pci_probe+0xe6/0x220 [i915]
<4> [309.733198]  local_pci_probe+0x44/0xb0
<4> [309.733203]  pci_device_probe+0xf4/0x270
<4> [309.733209]  really_probe+0xee/0x3c0
<4> [309.733215]  __driver_probe_device+0x8c/0x180
<4> [309.733219]  driver_probe_device+0x24/0xd0
<4> [309.733223]  __driver_attach+0x10f/0x220
<4> [309.733230]  bus_for_each_dev+0x7d/0xe0
<4> [309.733236]  driver_attach+0x1e/0x30
<4> [309.733239]  bus_add_driver+0x151/0x290
<4> [309.733244]  driver_register+0x5e/0x130
<4> [309.733247]  __pci_register_driver+0x7d/0x90
<4> [309.733251]  i915_pci_register_driver+0x23/0x30 [i915]
<4> [309.733413]  i915_init+0x34/0x120 [i915]
<4> [309.733655]  do_one_initcall+0x62/0x3f0
<4> [309.733667]  do_init_module+0x97/0x2a0
<4> [309.733671]  load_module+0x25ff/0x2890
<4> [309.733688]  init_module_from_file+0x97/0xe0
<4> [309.733701]  idempotent_init_module+0x118/0x330
<4> [309.733711]  __x64_sys_finit_module+0x77/0x100
<4> [309.733715]  x64_sys_call+0x1f37/0x2650
<4> [309.733719]  do_syscall_64+0x91/0x180
<4> [309.733763]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
<4> [309.733792]  </TASK>
...
<4> [309.733806] ---[ end trace 0000000000000000 ]---

That scenario is most easily reproducible with
igt@i915_module_load@reload-with-fault-injection.

Fix the issue by moving the cleanup step to driver release path.

Fixes: 27536e03271da ("drm/i915/huc: track delayed HuC load with a fence")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13592
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://lore.kernel.org/r/20250402172057.209924-2-janusz.krzysztofik@linux.intel.com
(cherry picked from commit 795dbde92fe5c6996a02a5b579481de73035e7bf)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index ba9e07fc2b57706d658ddc46eb46dd706842e310..552662953e7a44c28f7c16267f4cbe8e8374151c 100644 (file)
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -316,6 +316,11 @@ void intel_huc_init_early(struct intel_huc *huc)
        }
 }
 
+void intel_huc_fini_late(struct intel_huc *huc)
+{
+       delayed_huc_load_fini(huc);
+}
+
 #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
 static int check_huc_loading_mode(struct intel_huc *huc)
 {
@@ -413,12 +418,6 @@ out:
 
 void intel_huc_fini(struct intel_huc *huc)
 {
-       /*
-        * the fence is initialized in init_early, so we need to clean it up
-        * even if HuC loading is off.
-        */
-       delayed_huc_load_fini(huc);
-
        if (huc->heci_pkt)
                i915_vma_unpin_and_release(&huc->heci_pkt, 0);
 

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index ba5cb08e9e7bf1edb27dfa310e91234f84241097..09aff3148f7ddbf1f5d363a660bf9e4402fa8fb4 100644 (file)
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -55,6 +55,7 @@ struct intel_huc {
 
 int intel_huc_sanitize(struct intel_huc *huc);
 void intel_huc_init_early(struct intel_huc *huc);
+void intel_huc_fini_late(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
 void intel_huc_suspend(struct intel_huc *huc);

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 98b103375b7ab0bdccd6fe85e6d2a3a709121a7c..c29d187ddad1cdca7b1f65a006bc531fc8e1c74c 100644 (file)
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -145,6 +145,7 @@ void intel_uc_init_late(struct intel_uc *uc)
 
 void intel_uc_driver_late_release(struct intel_uc *uc)
 {
+       intel_huc_fini_late(&uc->huc);
 }
 
 /**