From ab0eec0ff0a421737a37f510ceab5c6ea59cd05a Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Tue, 14 Jul 2026 18:02:22 +0000 Subject: [PATCH 1/2] pds_core: fix deadlock between reset thread and remove pci_reset_function() acquires device_lock before performing the reset. pdsc_remove() is called by the PCI core with device_lock already held. If pdsc_pci_reset_thread() is running when pdsc_remove() is called, destroy_workqueue() will block waiting for the work to complete, while the work is blocked waiting for device_lock - deadlock. Use pci_try_reset_function() which uses pci_dev_trylock() internally. This acquires both the device lock and the PCI config access lock without blocking - if either lock is contended, it returns -EAGAIN immediately. This avoids the deadlock while also ensuring proper config space access serialization during the reset. The pci_dev_get/put calls are also removed as they were unnecessary - the driver-owned workqueue is destroyed in pdsc_remove(), guaranteeing the work completes before remove returns. The PCI core holds its reference to pci_dev throughout the entire unbind sequence. Fixes: 81665adf25d2 ("pds_core: Fix pdsc_check_pci_health function to use work thread") Reported-by: sashiko-bot Closes: https://patchwork.kernel.org/comment/27002369/ Signed-off-by: Nikhil P. Rao Reviewed-by: Harshitha Ramamurthy Link: https://patch.msgid.link/20260714180223.1642792-2-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/core.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 38a2446571af..1074a022a52f 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -606,9 +606,10 @@ 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) From 0ad134881508c36b65c1a8864f8bec53adbd3327 Mon Sep 17 00:00:00 2001 From: "Nikhil P. Rao" Date: Tue, 14 Jul 2026 18:02:23 +0000 Subject: [PATCH 2/2] pds_core: fix use-after-free on workqueue during remove In pdsc_remove(), the workqueue is destroyed before pdsc_teardown() is called. This ordering allows two paths to queue work on the destroyed workqueue: 1. If pdsc_teardown() -> pdsc_devcmd_reset() times out, the error path in pdsc_devcmd_locked() queues health_work. 2. A NotifyQ event can trigger the ISR and queue work before free_irq() is called in pdsc_teardown(). Fix by moving destroy_workqueue() after pdsc_teardown() so the workqueue outlives every queuer; destroy_workqueue() then flushes any work still pending. Draining the queued work also requires ordering the teardown so the resources that work touches are freed last: - In pdsc_qcq_free(), after freeing the interrupt, cancel_work_sync() the queue's work and only then clear qcq->intx, so pdsc_process_adminq()'s read of qcq->intx for interrupt-credit return cannot race with the clear. - Free adminqcq before notifyqcq: the shared adminq ISR is released when adminqcq is freed, and the adminq work accesses notifyqcq, so both must be stopped before notifyqcq is freed. Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands") Reported-by: sashiko-bot Closes: https://patchwork.kernel.org/comment/27002369/ Signed-off-by: Nikhil P. Rao Link: https://patch.msgid.link/20260714180223.1642792-3-nikhil.rao@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/core.c | 14 ++++++++++---- drivers/net/ethernet/amd/pds_core/main.c | 5 +++-- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 1074a022a52f..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 @@ int pdsc_qcq_alloc(struct pdsc *pdsc, unsigned int type, unsigned int index, 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); 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);