[PATCH 2/2] iommu/io-pgfault: reject partial faults after the device is removed

From: Qihang

Date: Mon Nov 16 2026 - 20:54:55 EST


A report that already holds a reference to the fault_param can still
reach report_partial_fault() after iopf_queue_remove_device() drained
the partial list. The node it queues there leaks: the parameter is no
longer on queue->devices and its final put does not free partial
faults.

Reject late partial insertions under fault_param->lock: add
fault_param->removing, set it in iopf_queue_remove_device() before
the drain, and test it in report_partial_fault() under the same lock
that the insertion takes, so "check" and "link" cannot be separated. A
partial is then either drained or rejected and freed by
report_partial_fault() itself, which returns -ENODEV; as for any
non-last request, no response is sent. removing is never cleared,
since IOPF re-enable allocates a new fault_param.

This only protects partial-list admission; callers must still quiesce
reports for the remaining lifetimes. It is not a general teardown
fix; the cover letter lists the paths it does not cover.

Fixes: a74c077b9021 ("iommu: Use refcount for fault data access")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Qihang <q.h.hack.winter@xxxxxxxxx>
---
This applies on top of "iommu/io-pgfault: unlink partial faults before
freeing them".

drivers/iommu/io-pgfault.c | 12 ++++++++++--
include/linux/iommu.h | 3 +++
2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index 55a3c29..51d0d1a 100644
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -64,6 +64,7 @@ static int report_partial_fault(struct iommu_fault_param *fault_param,
struct iommu_fault *fault)
{
struct iopf_fault *iopf;
+ int ret = 0;

iopf = kzalloc_obj(*iopf);
if (!iopf)
@@ -72,10 +73,16 @@ static int report_partial_fault(struct iommu_fault_param *fault_param,
iopf->fault = *fault;

mutex_lock(&fault_param->lock);
- list_add(&iopf->list, &fault_param->partial);
+ if (fault_param->removing)
+ ret = -ENODEV;
+ else
+ list_add(&iopf->list, &fault_param->partial);
mutex_unlock(&fault_param->lock);

- return 0;
+ if (ret)
+ kfree(iopf);
+
+ return ret;
}

static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param,
@@ -479,6 +486,7 @@ void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
goto unlock;

mutex_lock(&fault_param->lock);
+ fault_param->removing = true;
list_for_each_entry_safe(partial_iopf, next, &fault_param->partial, list) {
list_del(&partial_iopf->list);
kfree(partial_iopf);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ef50437..5d56e66 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -846,6 +846,8 @@ struct iommu_device {
* @partial: faults that are part of a Page Request Group for which the last
* request hasn't been submitted yet.
* @faults: holds the pending faults which need response
+ * @removing: the device is being removed from the queue, no new partial
+ * faults may be queued
*/
struct iommu_fault_param {
struct mutex lock;
@@ -858,6 +860,7 @@ struct iommu_fault_param {

struct list_head partial;
struct list_head faults;
+ bool removing;
};

/**