| Message ID | 20240417051642.788740-1-ashutosh.dixit@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v4] drm/i915/hwmon: Get rid of devm | expand |
Hi Ashutosh, > @@ -839,16 +837,38 @@ void i915_hwmon_register(struct drm_i915_private *i915) > if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) > continue; > > - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, > - ddat_gt, > - &hwm_gt_chip_info, > - NULL); > - if (!IS_ERR(hwmon_dev)) > - ddat_gt->hwmon_dev = hwmon_dev; > + hwmon_dev = hwmon_device_register_with_info(dev, ddat_gt->name, > + ddat_gt, > + &hwm_gt_chip_info, > + NULL); > + if (IS_ERR(hwmon_dev)) > + goto err; here the logic is changing, though. Before we were not leaving if hwmon_device_register_with_info() was returning error. Is this wanted? And why isn't it described in the log? Thanks, Andi > + > + ddat_gt->hwmon_dev = hwmon_dev; > }
On Wed, 17 Apr 2024 01:28:48 -0700, Andi Shyti wrote: > Hi Andi, > > @@ -839,16 +837,38 @@ void i915_hwmon_register(struct drm_i915_private *i915) > > if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) > > continue; > > > > - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, > > - ddat_gt, > > - &hwm_gt_chip_info, > > - NULL); > > - if (!IS_ERR(hwmon_dev)) > > - ddat_gt->hwmon_dev = hwmon_dev; > > + hwmon_dev = hwmon_device_register_with_info(dev, ddat_gt->name, > > + ddat_gt, > > + &hwm_gt_chip_info, > > + NULL); > > + if (IS_ERR(hwmon_dev)) > > + goto err; > > here the logic is changing, though. Before we were not leaving if > hwmon_device_register_with_info() was returning error. > > Is this wanted? And why isn't it described in the log? Not sure if the previous logic was intentional or not, anyway I have restored it in v5 (where I once again forgot to add "PATCH v5" to the Subject but v5 is there in the version log :/). Thanks. -- Ashutosh
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index b758fd110c20..1551a40a675e 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -793,7 +793,7 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!IS_DGFX(i915)) return; - hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL); + hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL); if (!hwmon) return; @@ -819,14 +819,12 @@ void i915_hwmon_register(struct drm_i915_private *i915) hwm_get_preregistration_info(i915); /* hwmon_dev points to device hwmon<i> */ - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat->name, - ddat, - &hwm_chip_info, - hwm_groups); - if (IS_ERR(hwmon_dev)) { - i915->hwmon = NULL; - return; - } + hwmon_dev = hwmon_device_register_with_info(dev, ddat->name, + ddat, + &hwm_chip_info, + hwm_groups); + if (IS_ERR(hwmon_dev)) + goto err; ddat->hwmon_dev = hwmon_dev; @@ -839,16 +837,38 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) continue; - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, - ddat_gt, - &hwm_gt_chip_info, - NULL); - if (!IS_ERR(hwmon_dev)) - ddat_gt->hwmon_dev = hwmon_dev; + hwmon_dev = hwmon_device_register_with_info(dev, ddat_gt->name, + ddat_gt, + &hwm_gt_chip_info, + NULL); + if (IS_ERR(hwmon_dev)) + goto err; + + ddat_gt->hwmon_dev = hwmon_dev; } + return; +err: + i915_hwmon_unregister(i915); } void i915_hwmon_unregister(struct drm_i915_private *i915) { - fetch_and_zero(&i915->hwmon); + struct i915_hwmon *hwmon = i915->hwmon; + struct intel_gt *gt; + int i; + + if (!hwmon) + return; + + for_each_gt(gt, i915, i) + if (hwmon->ddat_gt[i].hwmon_dev) + hwmon_device_unregister(hwmon->ddat_gt[i].hwmon_dev); + + if (hwmon->ddat.hwmon_dev) + hwmon_device_unregister(hwmon->ddat.hwmon_dev); + + mutex_destroy(&hwmon->hwmon_lock); + + kfree(i915->hwmon); + i915->hwmon = NULL; }
When both hwmon and hwmon drvdata (on which hwmon depends) are device managed resources, the expectation, on device unbind, is that hwmon will be released before drvdata. However, in i915 there are two separate code paths, which both release either drvdata or hwmon and either can be released before the other. These code paths (for device unbind) are as follows (see also the bug referenced below): Call Trace: release_nodes+0x11/0x70 devres_release_group+0xb2/0x110 component_unbind_all+0x8d/0xa0 component_del+0xa5/0x140 intel_pxp_tee_component_fini+0x29/0x40 [i915] intel_pxp_fini+0x33/0x80 [i915] i915_driver_remove+0x4c/0x120 [i915] i915_pci_remove+0x19/0x30 [i915] pci_device_remove+0x32/0xa0 device_release_driver_internal+0x19c/0x200 unbind_store+0x9c/0xb0 and Call Trace: release_nodes+0x11/0x70 devres_release_all+0x8a/0xc0 device_unbind_cleanup+0x9/0x70 device_release_driver_internal+0x1c1/0x200 unbind_store+0x9c/0xb0 This means that in i915, if use devm, we cannot gurantee that hwmon will always be released before drvdata. Which means that we have a uaf if hwmon sysfs is accessed when drvdata has been released but hwmon hasn't. The only way out of this seems to be do get rid of devm_ and release/free everything explicitly during device unbind. v2: Change commit message and other minor code changes v3: Cleanup from i915_hwmon_register on error (Armin Wolf) v4: Eliminate potential static analyzer warning (Rodrigo) Eliminate fetch_and_zero (Jani) Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10366 Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com> --- drivers/gpu/drm/i915/i915_hwmon.c | 52 +++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 16 deletions(-)