[RFC PATCH 7/8] qaic: Implement MHI error status handler

From: Jeffrey Hugo
Date: Thu May 14 2020 - 10:08:31 EST


If the MHI bus has detected some kind of error with the device, it will
invoke the registered status_cb(). We are intrested in both the fatal
error and sys error events.

For a fatal error, the device has essentially gone away, and needs to be
reinited from scratch. We lose all state. The MHI bus expects the
controller to fully handle this scenario

For a sys error, the device can recover by going through the MHI reset
flow, but we lose all state. The MHI bus is going to handle the MHI
reset flow, but we need to still clean up our local state.

Signed-off-by: Jeffrey Hugo <jhugo@xxxxxxxxxxxxxx>
---
drivers/misc/qaic/mhi_controller.c | 27 +++++++++++++++++++++++++++
drivers/misc/qaic/mhi_controller.h | 2 ++
drivers/misc/qaic/qaic.h | 2 ++
drivers/misc/qaic/qaic_drv.c | 16 +++++++++++++++-
4 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/qaic/mhi_controller.c b/drivers/misc/qaic/mhi_controller.c
index 18fc830..c1498d4 100644
--- a/drivers/misc/qaic/mhi_controller.c
+++ b/drivers/misc/qaic/mhi_controller.c
@@ -7,6 +7,8 @@
#include <linux/moduleparam.h>
#include <linux/pci.h>

+#include "qaic.h"
+
static unsigned int mhi_timeout = 20000; /* 20 sec default */
module_param(mhi_timeout, uint, 0600);

@@ -424,6 +426,15 @@ static void mhi_runtime_put(struct mhi_controller *mhi_cntl)
static void mhi_status_cb(struct mhi_controller *mhi_cntl,
enum mhi_callback reason)
{
+ struct qaic_device *qdev = (struct qaic_device *)pci_get_drvdata(
+ to_pci_dev(mhi_cntl->cntrl_dev));
+
+ /* this event occurs in atomic context */
+ if (reason == MHI_CB_FATAL_ERROR && !qdev->in_reset)
+ schedule_work(&qdev->reset_mhi_work);
+ /* this event occurs in non-atomic context */
+ if (reason == MHI_CB_SYS_ERROR && !qdev->in_reset)
+ qaic_dev_reset_clean_local_state(qdev);
}

struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev,
@@ -509,3 +520,19 @@ void qaic_mhi_link_up(struct mhi_controller *mhi_cntl)
if (ret)
pci_err(pci_dev, "mhi_async_power_up failed when link came back %d\n", ret);
}
+
+void qaic_mhi_start_reset(struct mhi_controller *mhi_cntl)
+{
+ mhi_power_down(mhi_cntl, true);
+}
+
+void qaic_mhi_reset_done(struct mhi_controller *mhi_cntl)
+{
+ struct pci_dev *pci_dev = container_of(mhi_cntl->cntrl_dev,
+ struct pci_dev, dev);
+ int ret;
+
+ ret = mhi_async_power_up(mhi_cntl);
+ if (ret)
+ pci_err(pci_dev, "mhi_async_power_up failed after reset %d\n", ret);
+}
diff --git a/drivers/misc/qaic/mhi_controller.h b/drivers/misc/qaic/mhi_controller.h
index 5eca586..1081f0a 100644
--- a/drivers/misc/qaic/mhi_controller.h
+++ b/drivers/misc/qaic/mhi_controller.h
@@ -14,5 +14,7 @@ void qaic_mhi_free_controller(struct mhi_controller *mhi_cntl, bool link_up);

void qaic_mhi_link_down(struct mhi_controller *mhi_cntl);
void qaic_mhi_link_up(struct mhi_controller *mhi_cntl);
+void qaic_mhi_start_reset(struct mhi_controller *mhi_cntl);
+void qaic_mhi_reset_done(struct mhi_controller *mhi_cntl);

#endif /* MHICONTROLLERQAIC_H_ */
diff --git a/drivers/misc/qaic/qaic.h b/drivers/misc/qaic/qaic.h
index 5f774d4..bbb7512 100644
--- a/drivers/misc/qaic/qaic.h
+++ b/drivers/misc/qaic/qaic.h
@@ -68,6 +68,7 @@ struct qaic_device {
struct cdev *cdev;
struct device *dev;
struct dma_bridge_chan dbc[QAIC_NUM_DBC];
+ struct work_struct reset_mhi_work;
struct workqueue_struct *cntl_wq;
bool in_reset;
struct srcu_struct dev_lock;
@@ -106,4 +107,5 @@ void wakeup_dbc(struct qaic_device *qdev, u32 dbc_id);
void release_dbc(struct qaic_device *qdev, u32 dbc_id);

void wake_all_cntl(struct qaic_device *qdev);
+void qaic_dev_reset_clean_local_state(struct qaic_device *qdev);
#endif /* QAICINTERNAL_H_ */
diff --git a/drivers/misc/qaic/qaic_drv.c b/drivers/misc/qaic/qaic_drv.c
index 1c8eefd..010cf88 100644
--- a/drivers/misc/qaic/qaic_drv.c
+++ b/drivers/misc/qaic/qaic_drv.c
@@ -386,6 +386,18 @@ void qaic_dev_reset_clean_local_state(struct qaic_device *qdev)
release_dbc(qdev, i);
}

+static void reset_mhi_work_func(struct work_struct *work)
+{
+ struct qaic_device *qdev;
+
+ qdev = container_of(work, struct qaic_device, reset_mhi_work);
+
+ qaic_dev_reset_clean_local_state(qdev);
+ qaic_mhi_start_reset(qdev->mhi_cntl);
+ qdev->in_reset = false;
+ qaic_mhi_reset_done(qdev->mhi_cntl);
+}
+
static int qaic_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *id)
{
@@ -411,6 +423,7 @@ static int qaic_pci_probe(struct pci_dev *pdev,
qdev->pdev = pdev;
mutex_init(&qdev->cntl_mutex);
INIT_LIST_HEAD(&qdev->cntl_xfer_list);
+ INIT_WORK(&qdev->reset_mhi_work, reset_mhi_work_func);
init_srcu_struct(&qdev->dev_lock);
INIT_LIST_HEAD(&qdev->users);
mutex_init(&qdev->users_mutex);
@@ -541,6 +554,7 @@ static void qaic_pci_remove(struct pci_dev *pdev)
return;

qaic_dev_reset_clean_local_state(qdev);
+ cancel_work_sync(&qdev->reset_mhi_work);
qaic_mhi_free_controller(qdev->mhi_cntl, link_up);
for (i = 0; i < QAIC_NUM_DBC; ++i) {
devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i + 1),
@@ -682,4 +696,4 @@ module_exit(qaic_exit);
MODULE_AUTHOR("Qualcomm Cloud AI 100 Accelerator Kernel Driver Team");
MODULE_DESCRIPTION("Qualcomm Cloud 100 AI Accelerators Driver");
MODULE_LICENSE("GPL v2");
-MODULE_VERSION("0.0.0"); /* MAJOR.MINOR.PATCH */
+MODULE_VERSION("3.0.1"); /* MAJOR.MINOR.PATCH */
--
Qualcomm Technologies, Inc. is a member of the
Code Aurora Forum, a Linux Foundation Collaborative Project.