Merge branch 'pds_core-fix-use-after-free-on-workqueue-during-remove'

Nikhil P. Rao says:

====================
pds_core: fix use-after-free on workqueue during remove

This series fixes a use-after-free on the workqueue during driver remove.

Patch 1 fixes a pre-existing deadlock between the PCI reset worker and
pdsc_remove() that was identified during review of v1.

Patch 2 is the reworked UAF fix that moves destroy_workqueue() after
pdsc_teardown() and adds proper work synchronization.
====================

Link: https://patch.msgid.link/20260714180223.1642792-1-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 17 insertions, 9 deletions

diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 38a2446571af..e39b2c9beb20 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -110,7 +110,6 @@ static void pdsc_qcq_intr_free(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		return;
 
 	pdsc_intr_free(pdsc, qcq->intx);
-	qcq->intx = PDS_CORE_INTR_INDEX_NOT_ASSIGNED;
 }
 
 static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq)
@@ -145,6 +144,12 @@ void pdsc_qcq_free(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 
 	pdsc_qcq_intr_free(pdsc, qcq);
 
+	/* Drain any work queued by ISR before it was freed above */
+	if (qcq->work.func)
+		cancel_work_sync(&qcq->work);
+
+	qcq->intx = PDS_CORE_INTR_INDEX_NOT_ASSIGNED;
+
 	if (qcq->q_base)
 		dma_free_coherent(dev, qcq->q_size,
 				  qcq->q_base, qcq->q_base_pa);
@@ -304,8 +309,11 @@ err_out:
 
 static void pdsc_core_uninit(struct pdsc *pdsc)
 {
-	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
+	/* Free adminqcq first: its work accesses notifyqcq, so we must
+	 * disable its IRQ and drain its work before freeing notifyqcq.
+	 */
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
+	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 
 	if (pdsc->kern_dbpage) {
 		iounmap(pdsc->kern_dbpage);
@@ -479,8 +487,6 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 {
 	if (!pdsc->pdev->is_virtfn)
 		pdsc_devcmd_reset(pdsc);
-	if (pdsc->adminqcq.work.func)
-		cancel_work_sync(&pdsc->adminqcq.work);
 
 	pci_clear_master(pdsc->pdev);
 
@@ -606,9 +612,10 @@ void pdsc_pci_reset_thread(struct work_struct *work)
 	struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work);
 	struct pci_dev *pdev = pdsc->pdev;
 
-	pci_dev_get(pdev);
-	pci_reset_function(pdev);
-	pci_dev_put(pdev);
+	/* Use try variant to avoid deadlock with pdsc_remove().
+	 * If lock is contended, the watchdog timer will retry.
+	 */
+	pci_try_reset_function(pdev);
 }
 
 static void pdsc_check_pci_health(struct pdsc *pdsc)
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 22db78343eb0..638b9c7a509d 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -435,8 +435,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev);
 
 		timer_shutdown_sync(&pdsc->wdtimer);
-		if (pdsc->wq)
-			destroy_workqueue(pdsc->wq);
 
 		mutex_lock(&pdsc->config_lock);
 		set_bit(PDSC_S_STOPPING_DRIVER, &pdsc->state);
@@ -444,6 +442,9 @@ static void pdsc_remove(struct pci_dev *pdev)
 		pdsc_stop(pdsc);
 		pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 		mutex_unlock(&pdsc->config_lock);
+
+		if (pdsc->wq)
+			destroy_workqueue(pdsc->wq);
 		mutex_destroy(&pdsc->config_lock);
 		mutex_destroy(&pdsc->devcmd_lock);