From 9567d3dc760931afc38f7f1144c66dd8c4b8c680 Mon Sep 17 00:00:00 2001 From: Mun Chun Yep <mun.chun.yep@intel.com> Date: Fri, 2 Feb 2024 18:53:24 +0800 Subject: [PATCH] crypto: qat - improve aer error reset handling Rework the AER reset and recovery flow to take into account root port integrated devices that gets reset between the error detected and the slot reset callbacks. In adf_error_detected() the devices is gracefully shut down. The worker threads are disabled, the error conditions are notified to listeners and through PFVF comms and finally the device is reset as part of adf_dev_down(). In adf_slot_reset(), the device is brought up again. If SRIOV VFs were enabled before reset, these are re-enabled and VFs are notified of restarting through PFVF comms. Signed-off-by: Mun Chun Yep <mun.chun.yep@intel.com> Reviewed-by: Ahsan Atta <ahsan.atta@intel.com> Reviewed-by: Markas Rapoportas <markas.rapoportas@intel.com> Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> --- drivers/crypto/intel/qat/qat_common/adf_aer.c | 26 ++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/intel/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c index b3d4b6b99c65a..3597e7605a143 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_aer.c +++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c @@ -33,6 +33,19 @@ static pci_ers_result_t adf_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_DISCONNECT; } + set_bit(ADF_STATUS_RESTARTING, &accel_dev->status); + if (accel_dev->hw_device->exit_arb) { + dev_dbg(&pdev->dev, "Disabling arbitration\n"); + accel_dev->hw_device->exit_arb(accel_dev); + } + adf_error_notifier(accel_dev); + adf_pf2vf_notify_fatal_error(accel_dev); + adf_dev_restarting_notify(accel_dev); + adf_pf2vf_notify_restarting(accel_dev); + adf_pf2vf_wait_for_restarting_complete(accel_dev); + pci_clear_master(pdev); + adf_dev_down(accel_dev, false); + return PCI_ERS_RESULT_NEED_RESET; } @@ -180,14 +193,25 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, static pci_ers_result_t adf_slot_reset(struct pci_dev *pdev) { struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev); + int res = 0; if (!accel_dev) { pr_err("QAT: Can't find acceleration device\n"); return PCI_ERS_RESULT_DISCONNECT; } - if (adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_SYNC)) + + if (!pdev->is_busmaster) + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + res = adf_dev_up(accel_dev, false); + if (res && res != -EALREADY) return PCI_ERS_RESULT_DISCONNECT; + adf_reenable_sriov(accel_dev); + adf_pf2vf_notify_restarted(accel_dev); + adf_dev_restarted_notify(accel_dev); + clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); return PCI_ERS_RESULT_RECOVERED; } -- GitLab