crypto: qat - re-enable sriov after pf reset

When a Physical Function (PF) is reset, SR-IOV gets disabled, making the
associated Virtual Functions (VFs) unavailable. Even after reset and
using pci_restore_state, VFs remain uncreated because the numvfs still
at 0. Therefore, it's necessary to reconfigure SR-IOV to re-enable VFs.

This commit introduces the ADF_SRIOV_ENABLED configuration flag to cache
the SR-IOV enablement state. SR-IOV is only re-enabled if it was
previously configured.

This commit also introduces a dedicated workqueue without
`WQ_MEM_RECLAIM` flag for enabling SR-IOV during Heartbeat and CPM error
resets, preventing workqueue flushing warning.

This patch is based on earlier work done by Shashank Gupta.

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

@@ -15,6 +15,7 @@ struct adf_fatal_error_data {
 };
 
 static struct workqueue_struct *device_reset_wq;
+static struct workqueue_struct *device_sriov_wq;
 
 static pci_ers_result_t adf_error_detected(struct pci_dev *pdev,
 					   pci_channel_state_t state)
@@ -43,6 +44,13 @@ struct adf_reset_dev_data {
 	struct work_struct reset_work;
 };
 
+/* sriov dev data */
+struct adf_sriov_dev_data {
+	struct adf_accel_dev *accel_dev;
+	struct completion compl;
+	struct work_struct sriov_work;
+};
+
 void adf_reset_sbr(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
@@ -88,11 +96,22 @@ void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	}
 }
 
+static void adf_device_sriov_worker(struct work_struct *work)
+{
+	struct adf_sriov_dev_data *sriov_data =
+		container_of(work, struct adf_sriov_dev_data, sriov_work);
+
+	adf_reenable_sriov(sriov_data->accel_dev);
+	complete(&sriov_data->compl);
+}
+
 static void adf_device_reset_worker(struct work_struct *work)
 {
 	struct adf_reset_dev_data *reset_data =
 		  container_of(work, struct adf_reset_dev_data, reset_work);
 	struct adf_accel_dev *accel_dev = reset_data->accel_dev;
+	unsigned long wait_jiffies = msecs_to_jiffies(10000);
+	struct adf_sriov_dev_data sriov_data;
 
 	adf_dev_restarting_notify(accel_dev);
 	if (adf_dev_restart(accel_dev)) {
@@ -103,6 +122,14 @@ static void adf_device_reset_worker(struct work_struct *work)
 		WARN(1, "QAT: device restart failed. Device is unusable\n");
 		return;
 	}
+
+	sriov_data.accel_dev = accel_dev;
+	init_completion(&sriov_data.compl);
+	INIT_WORK(&sriov_data.sriov_work, adf_device_sriov_worker);
+	queue_work(device_sriov_wq, &sriov_data.sriov_work);
+	if (wait_for_completion_timeout(&sriov_data.compl, wait_jiffies))
+		adf_pf2vf_notify_restarted(accel_dev);
+
 	adf_dev_restarted_notify(accel_dev);
 	clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
 
@@ -216,7 +243,14 @@ int adf_init_aer(void)
 {
 	device_reset_wq = alloc_workqueue("qat_device_reset_wq",
 					  WQ_MEM_RECLAIM, 0);
-	return !device_reset_wq ? -EFAULT : 0;
+	if (!device_reset_wq)
+		return -EFAULT;
+
+	device_sriov_wq = alloc_workqueue("qat_device_sriov_wq", 0, 0);
+	if (!device_sriov_wq)
+		return -EFAULT;
+
+	return 0;
 }
 
 void adf_exit_aer(void)
@@ -224,4 +258,8 @@ void adf_exit_aer(void)
 	if (device_reset_wq)
 		destroy_workqueue(device_reset_wq);
 	device_reset_wq = NULL;
+
+	if (device_sriov_wq)
+		destroy_workqueue(device_sriov_wq);
+	device_sriov_wq = NULL;
 }

drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h

@@ -49,5 +49,6 @@
 	ADF_ETRMGR_BANK "%d" ADF_ETRMGR_CORE_AFFINITY
 #define ADF_ACCEL_STR "Accelerator%d"
 #define ADF_HEARTBEAT_TIMER  "HeartbeatTimer"
+#define ADF_SRIOV_ENABLED "SriovEnabled"
 
 #endif

drivers/crypto/intel/qat/qat_common/adf_common_drv.h

@@ -192,6 +192,7 @@ bool adf_misc_wq_queue_delayed_work(struct delayed_work *work,
 #if defined(CONFIG_PCI_IOV)
 int adf_sriov_configure(struct pci_dev *pdev, int numvfs);
 void adf_disable_sriov(struct adf_accel_dev *accel_dev);
+void adf_reenable_sriov(struct adf_accel_dev *accel_dev);
 void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask);
 void adf_disable_all_vf2pf_interrupts(struct adf_accel_dev *accel_dev);
 bool adf_recv_and_handle_pf2vf_msg(struct adf_accel_dev *accel_dev);
@@ -212,6 +213,10 @@ static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 {
 }
 
+static inline void adf_reenable_sriov(struct adf_accel_dev *accel_dev)
+{
+}
+
 static inline int adf_init_pf_wq(void)
 {
 	return 0;

drivers/crypto/intel/qat/qat_common/adf_sriov.c

@@ -60,7 +60,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev)
 		/* This ptr will be populated when VFs will be created */
 		vf_info->accel_dev = accel_dev;
 		vf_info->vf_nr = i;
-		vf_info->vf_compat_ver = 0;
 
 		mutex_init(&vf_info->pf2vf_lock);
 		ratelimit_state_init(&vf_info->vf2pf_ratelimit,
@@ -84,6 +83,32 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev)
 	return pci_enable_sriov(pdev, totalvfs);
 }
 
+void adf_reenable_sriov(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	char cfg[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0};
+	unsigned long val = 0;
+
+	if (adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC,
+				    ADF_SRIOV_ENABLED, cfg))
+		return;
+
+	if (!accel_dev->pf.vf_info)
+		return;
+
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY,
+					&val, ADF_DEC))
+		return;
+
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC,
+					&val, ADF_DEC))
+		return;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	dev_dbg(&pdev->dev, "Re-enabling SRIOV\n");
+	adf_enable_sriov(accel_dev);
+}
+
 /**
  * adf_disable_sriov() - Disable SRIOV for the device
  * @accel_dev:  Pointer to accel device.
@@ -116,8 +141,10 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 	for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++)
 		mutex_destroy(&vf->pf2vf_lock);
 
-	kfree(accel_dev->pf.vf_info);
-	accel_dev->pf.vf_info = NULL;
+	if (!test_bit(ADF_STATUS_RESTARTING, &accel_dev->status)) {
+		kfree(accel_dev->pf.vf_info);
+		accel_dev->pf.vf_info = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(adf_disable_sriov);
 
@@ -195,6 +222,10 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 	if (ret)
 		return ret;
 
+	val = 1;
+	adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, ADF_SRIOV_ENABLED,
+				    &val, ADF_DEC);
+
 	return numvfs;
 }
 EXPORT_SYMBOL_GPL(adf_sriov_configure);