drm/xe/nvm: Manage nvm aux cleanup with devres

Move nvm teardown to a devm-managed action registered from xe_nvm_init().
This ensures the auxiliary NVM device is deleted on probe failure and
device detach without requiring explicit calls from remove paths.

As part of this, drop xe_nvm_fini() from xe_device_remove() and from the
survivability sysfs teardown, and remove the public xe_nvm_fini() API from
the header.

This is to fix below warn message when there is probe failure after
xe_nvm_init(), then xe_device_probe() is called again:
"
[  207.318152] sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:01.0/0000:01:00.0/0000:02:01.0/0000:03:00.0/xe.nvm.768'
[  207.318157] CPU: 5 UID: 0 PID: 10261 Comm: modprobe Tainted: G    B   W           6.19.0-rc2-lgci-xe-kernel+ #223 PREEMPT(voluntary)
[  207.318160] Tainted: [B]=BAD_PAGE, [W]=WARN
[  207.318161] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 0812 02/24/2023
[  207.318163] Call Trace:
[  207.318163]  <TASK>
[  207.318165]  dump_stack_lvl+0xa0/0xc0
[  207.318170]  dump_stack+0x10/0x20
[  207.318171]  sysfs_warn_dup+0xd5/0x110
[  207.318175]  sysfs_create_dir_ns+0x1f6/0x280
[  207.318177]  ? __pfx_sysfs_create_dir_ns+0x10/0x10
[  207.318179]  ? lock_acquire+0x1a4/0x2e0
[  207.318182]  ? __kasan_check_read+0x11/0x20
[  207.318185]  ? do_raw_spin_unlock+0x5c/0x240
[  207.318187]  kobject_add_internal+0x28d/0x8e0
[  207.318189]  kobject_add+0x11f/0x1f0
[  207.318191]  ? __pfx_kobject_add+0x10/0x10
[  207.318193]  ? lockdep_init_map_type+0x4b/0x230
[  207.318195]  ? get_device_parent.isra.0+0x43/0x4c0
[  207.318197]  ? kobject_get+0x55/0xf0
[  207.318199]  device_add+0x2d7/0x1500
[  207.318201]  ? __pfx_device_add+0x10/0x10
[  207.318203]  ? lockdep_init_map_type+0x4b/0x230
[  207.318205]  __auxiliary_device_add+0x99/0x140
[  207.318208]  xe_nvm_init+0x7a2/0xef0 [xe]
[  207.318333]  ? xe_devcoredump_init+0x80/0x110 [xe]
[  207.318452]  ? __devm_add_action+0x82/0xc0
[  207.318454]  ? fs_reclaim_release+0xc0/0x110
[  207.318457]  xe_device_probe+0x17dd/0x2c40 [xe]
[  207.318574]  ? __pfx___drm_dev_dbg+0x10/0x10
[  207.318576]  ? add_dr+0x180/0x220
[  207.318579]  ? __pfx___drmm_mutex_release+0x10/0x10
[  207.318582]  ? __pfx_xe_device_probe+0x10/0x10 [xe]
[  207.318697]  ? xe_pm_init_early+0x33a/0x410 [xe]
[  207.318850]  xe_pci_probe+0x936/0x1250 [xe]
[  207.318999]  ? lock_acquire+0x1a4/0x2e0
[  207.319003]  ? __pfx_xe_pci_probe+0x10/0x10 [xe]
[  207.319151]  local_pci_probe+0xe6/0x1a0
[  207.319154]  pci_device_probe+0x523/0x840
[  207.319157]  ? __pfx_pci_device_probe+0x10/0x10
[  207.319159]  ? sysfs_do_create_link_sd.isra.0+0x8c/0x110
[  207.319162]  ? sysfs_create_link+0x48/0xc0
...
"

Fixes: c28bfb107dac ("drm/xe/nvm: add on-die non-volatile memory device")
Reviewed-by: Alexander Usyskin <alexander.usyskin@intel.com>
Reviewed-by: Brian Nguyen <brian3.nguyen@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Riana Tauro <riana.tauro@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patch.msgid.link/20260120183239.2966782-6-shuicheng.lin@intel.com
(cherry picked from commit 11035eab1b7d88daa7904440046e64d3810b1ca1)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index cf29e259861f95cfd3b72390521cdd40df5491b7..9a6d49fcd8e49bd81923e00542ac560fdf1248e4 100644 (file)
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -984,8 +984,6 @@ void xe_device_remove(struct xe_device *xe)
 {
        xe_display_unregister(xe);
 
-       xe_nvm_fini(xe);
-
        drm_dev_unplug(&xe->drm);
 
        xe_bo_pci_dev_remove_all(xe);

diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c
index 33f4ac82fc80ab517ec3732da176d59e15e82d9c..1fff24dbc7cd4964a60d4615af5e9a5f95311f8e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_nvm.c
+++ b/drivers/gpu/drm/xe/xe_nvm.c
@@ -83,6 +83,27 @@ static bool xe_nvm_writable_override(struct xe_device *xe)
        return writable_override;
 }
 
+static void xe_nvm_fini(void *arg)
+{
+       struct xe_device *xe = arg;
+       struct intel_dg_nvm_dev *nvm = xe->nvm;
+
+       if (!xe->info.has_gsc_nvm)
+               return;
+
+       /* No access to internal NVM from VFs */
+       if (IS_SRIOV_VF(xe))
+               return;
+
+       /* Nvm pointer should not be NULL here */
+       if (WARN_ON(!nvm))
+               return;
+
+       auxiliary_device_delete(&nvm->aux_dev);
+       auxiliary_device_uninit(&nvm->aux_dev);
+       xe->nvm = NULL;
+}
+
 int xe_nvm_init(struct xe_device *xe)
 {
        struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -141,30 +162,10 @@ int xe_nvm_init(struct xe_device *xe)
                auxiliary_device_uninit(aux_dev);
                goto err;
        }
-       return 0;
+       return devm_add_action_or_reset(xe->drm.dev, xe_nvm_fini, xe);
 
 err:
        kfree(nvm);
        xe->nvm = NULL;
        return ret;
 }
-
-void xe_nvm_fini(struct xe_device *xe)
-{
-       struct intel_dg_nvm_dev *nvm = xe->nvm;
-
-       if (!xe->info.has_gsc_nvm)
-               return;
-
-       /* No access to internal NVM from VFs */
-       if (IS_SRIOV_VF(xe))
-               return;
-
-       /* Nvm pointer should not be NULL here */
-       if (WARN_ON(!nvm))
-               return;
-
-       auxiliary_device_delete(&nvm->aux_dev);
-       auxiliary_device_uninit(&nvm->aux_dev);
-       xe->nvm = NULL;
-}

diff --git a/drivers/gpu/drm/xe/xe_nvm.h b/drivers/gpu/drm/xe/xe_nvm.h
index 7f3d5f57bed088fb527a010735f1802dc9c7e78f..fd3467ad35a4d9d978be4618862fd6cb48de1a10 100644 (file)
--- a/drivers/gpu/drm/xe/xe_nvm.h
+++ b/drivers/gpu/drm/xe/xe_nvm.h
@@ -10,6 +10,4 @@ struct xe_device;
 
 int xe_nvm_init(struct xe_device *xe);
 
-void xe_nvm_fini(struct xe_device *xe);
-
 #endif