Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v4 0/3] Fix nvm aux resource cleanup
@ 2026-01-20 18:32 Shuicheng Lin
  2026-01-20 18:32 ` [PATCH v4 1/3] drm/xe/nvm: Manage nvm aux cleanup with devres Shuicheng Lin
                   ` (6 more replies)
  0 siblings, 7 replies; 12+ messages in thread
From: Shuicheng Lin @ 2026-01-20 18:32 UTC (permalink / raw)
  To: intel-xe; +Cc: Shuicheng Lin

v2: create patch2 to "Fix double-free on aux add failure".
         
v3: drop goto in patch2 and create patch3 to drop the clear of xe->nvm.

v4: re-send series to fix patch apply failure.

Shuicheng Lin (3):
  drm/xe/nvm: Manage nvm aux cleanup with devres
  drm/xe/nvm: Fix double-free on aux add failure
  drm/xe/nvm: Defer xe->nvm assignment until init succeeds

 drivers/gpu/drm/xe/xe_device.c             |  2 -
 drivers/gpu/drm/xe/xe_nvm.c                | 59 ++++++++++------------
 drivers/gpu/drm/xe/xe_nvm.h                |  2 -
 drivers/gpu/drm/xe/xe_survivability_mode.c |  4 --
 4 files changed, 28 insertions(+), 39 deletions(-)

-- 
2.50.1


^ permalink raw reply	[flat|nested] 12+ messages in thread
* [PATCH] drm/xe: Manage nvm aux cleanup with devres
@ 2026-01-09 22:00 Shuicheng Lin
  2026-01-20 18:28 ` [PATCH v4 0/3] Fix nvm aux resource cleanup Shuicheng Lin
  0 siblings, 1 reply; 12+ messages in thread
From: Shuicheng Lin @ 2026-01-09 22:00 UTC (permalink / raw)
  To: intel-xe; +Cc: Shuicheng Lin, Alexander Usyskin, Rodrigo Vivi, Riana Tauro

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")
Cc: Alexander Usyskin <alexander.usyskin@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>
---
 drivers/gpu/drm/xe/xe_device.c             |  2 -
 drivers/gpu/drm/xe/xe_nvm.c                | 43 +++++++++++-----------
 drivers/gpu/drm/xe/xe_nvm.h                |  2 -
 drivers/gpu/drm/xe/xe_survivability_mode.c |  4 --
 4 files changed, 22 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 329d17fd6100..e08d95554f2a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1068,8 +1068,6 @@ 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 01510061d4d4..1202a7abc46f 100644
--- a/drivers/gpu/drm/xe/xe_nvm.c
+++ b/drivers/gpu/drm/xe/xe_nvm.c
@@ -95,6 +95,27 @@ 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);
@@ -153,30 +174,10 @@ 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 7f3d5f57bed0..fd3467ad35a4 100644
--- 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
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 31456f432fc8..ff406e9a82cb 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -234,13 +234,9 @@ static SURVIVABILITY_ATTR_RO(fdo_mode, FDO_INFO);
 static void xe_survivability_mode_fini(void *arg)
 {
 	struct xe_device *xe = arg;
-	struct xe_survivability *survivability = &xe->survivability;
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	struct device *dev = &pdev->dev;
 
-	if (survivability->fdo_mode)
-		xe_nvm_fini(xe);
-
 	device_remove_file(dev, &dev_attr_survivability_mode);
 }
 
-- 
2.50.1


^ permalink raw reply related	[flat|nested] 12+ messages in thread
end of thread, other threads:[~2026-01-26 18:49 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-01-20 18:32 [PATCH v4 0/3] Fix nvm aux resource cleanup Shuicheng Lin
2026-01-20 18:32 ` [PATCH v4 1/3] drm/xe/nvm: Manage nvm aux cleanup with devres Shuicheng Lin
2026-01-20 18:32 ` [PATCH v4 2/3] drm/xe/nvm: Fix double-free on aux add failure Shuicheng Lin
2026-01-20 18:32 ` [PATCH v4 3/3] drm/xe/nvm: Defer xe->nvm assignment until init succeeds Shuicheng Lin
2026-01-20 23:41   ` Nguyen, Brian3
2026-01-21  7:02   ` Usyskin, Alexander
2026-01-21 16:05     ` Lin, Shuicheng
2026-01-20 18:42 ` ✓ CI.KUnit: success for Fix nvm aux resource cleanup Patchwork
2026-01-20 19:23 ` ✓ Xe.CI.BAT: " Patchwork
2026-01-21  1:12 ` ✓ Xe.CI.Full: " Patchwork
2026-01-26 18:48 ` [PATCH v4 0/3] " Lin, Shuicheng
  -- strict thread matches above, loose matches on Subject: below --
2026-01-09 22:00 [PATCH] drm/xe: Manage nvm aux cleanup with devres Shuicheng Lin
2026-01-20 18:28 ` [PATCH v4 0/3] Fix nvm aux resource cleanup Shuicheng Lin
2026-01-20 18:28   ` [PATCH v4 3/3] drm/xe/nvm: Defer xe->nvm assignment until init succeeds Shuicheng Lin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox