2021-07-15 08:25:05

by Frank Wunderlich

Subject: [PATCH] iommu: check if group is NULL before remove device

From: Frank Wunderlich <[email protected]>

if probe is failing, iommu_group may be not initialized,
so freeing it will result in NULL pointer access

Fixes: d72e31c93746 ("iommu: IOMMU Groups")
Signed-off-by: Frank Wunderlich <[email protected]>
---
drivers/iommu/iommu.c | 3 +++
1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 5419c4b9f27a..63f0af10c403 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -924,6 +924,9 @@ void iommu_group_remove_device(struct device *dev)
struct iommu_group *group = dev->iommu_group;
struct group_device *tmp_device, *device = NULL;

+ if (!group)
+ return;
+
dev_info(dev, "Removing from iommu group %d\n", group->id);

/* Pre-notify listeners that a device is being removed. */
--
2.25.1

2021-07-15 10:32:23

by Joerg Roedel

Subject: Re: [PATCH] iommu: check if group is NULL before remove device

On Thu, Jul 15, 2021 at 09:11:50AM +0200, Frank Wunderlich wrote:
> From: Frank Wunderlich <[email protected]>
>
> if probe is failing, iommu_group may be not initialized,

Sentences start with capital letters.

IOMMU patch subjects too, after the 'iommu:' prefix.

> so freeing it will result in NULL pointer access

Please describe in more detail how this NULL-ptr dereference is
triggered.

Regards,

Joerg

2021-07-28 10:36:15

by Frank Wunderlich

Subject: Re: [PATCH] iommu: check if group is NULL before remove device

Hi Joerg,

Sorry for late reply, somehow i marked message as read without answering it.

Am 15. Juli 2021 09:20:04 MESZ schrieb Joerg Roedel <[email protected]>:
>On Thu, Jul 15, 2021 at 09:11:50AM +0200, Frank Wunderlich wrote:
>> From: Frank Wunderlich <[email protected]>
>>
>> if probe is failing, iommu_group may be not initialized,
>
>Sentences start with capital letters.
>
>IOMMU patch subjects too, after the 'iommu:' prefix.

Will fix these in v2

>> so freeing it will result in NULL pointer access
>
>Please describe in more detail how this NULL-ptr dereference is
>triggered.

I had this by testing this series:
https://patchwork.kernel.org/project/linux-mediatek/list/?series=515129

Initialization in mtk driver was failed (i guess the iommu group was not yet created), cleanup was started and so this function is called with a NULL group pointer. I can try to find my debug-trace if you need a kind of backtrace.

regards Frank

2021-07-30 13:20:17

by Frank Wunderlich

Subject: Re: [PATCH] iommu: check if group is NULL before remove device

Am 2021-07-15 09:20, schrieb Joerg Roedel:
> On Thu, Jul 15, 2021 at 09:11:50AM +0200, Frank Wunderlich wrote:
>> From: Frank Wunderlich <[email protected]>
>>
>> if probe is failing, iommu_group may be not initialized,
>
> Sentences start with capital letters.
>
> IOMMU patch subjects too, after the 'iommu:' prefix.
>
>> so freeing it will result in NULL pointer access
>
> Please describe in more detail how this NULL-ptr dereference is
> triggered.

in my case probe (mtk_iommu_probe_device called from
__iommu_probe_device) is failing due to fwspec missing and then
dev_iommu_free/iommu_fwspec_free is called, later
iommu_group_remove_device with group=NULL

i think i've found problem:

iommu_probe_device:
group = iommu_group_get(dev);
if (!group) { //group is checked here for NULL but accessed later
ret = -ENODEV;
goto err_release; <<<
}
err_release:<<<
iommu_release_device(dev);

------------------------------------------------------------------------------
void iommu_release_device(struct device *dev)
{
...
iommu_group_remove_device(dev);

------------------------------------------------------------------------------
void iommu_group_remove_device(struct device *dev)
{
struct iommu_group *group = dev->iommu_group;
struct group_device *tmp_device, *device = NULL;
...
dev_info(dev, "Removing from iommu group %d\n", group->id); //crash
as group is NULL and not checked