mhi: pci_generic: Add health-check

If the modem crashes for any reason, we may not be able to detect
it at MHI level (MHI registers not reachable anymore).

This patch implements a health-check mechanism to check regularly
that device is alive (MHI layer can communicate with). If device
is not alive (because a crash or unexpected reset), the recovery
procedure is triggered.

Tested successfully with Telit FN980m module.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Hemant Kumar <hemantk@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>

drivers/bus/mhi/pci_generic.c

@@ -14,11 +14,15 @@
 #include <linux/mhi.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/timer.h>
 #include <linux/workqueue.h>
 
 #define MHI_PCI_DEFAULT_BAR_NUM 0
 
 #define MHI_POST_RESET_DELAY_MS 500
+
+#define HEALTH_CHECK_PERIOD (HZ * 2)
+
 /**
  * struct mhi_pci_dev_info - MHI PCI device specific information
  * @config: MHI controller configuration
@@ -189,6 +193,7 @@ struct mhi_pci_device {
 	struct mhi_controller mhi_cntrl;
 	struct pci_saved_state *pci_state;
 	struct work_struct recovery_work;
+	struct timer_list health_check_timer;
 	unsigned long status;
 };
 
@@ -326,6 +331,8 @@ static void mhi_pci_recovery_work(struct work_struct *work)
 
 	dev_warn(&pdev->dev, "device recovery started\n");
 
+	del_timer(&mhi_pdev->health_check_timer);
+
 	/* Clean up MHI state */
 	if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) {
 		mhi_power_down(mhi_cntrl, false);
@@ -351,6 +358,7 @@ static void mhi_pci_recovery_work(struct work_struct *work)
 	dev_dbg(&pdev->dev, "Recovery completed\n");
 
 	set_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status);
+	mod_timer(&mhi_pdev->health_check_timer, jiffies + HEALTH_CHECK_PERIOD);
 	return;
 
 err_unprepare:
@@ -360,6 +368,21 @@ err_try_reset:
 		dev_err(&pdev->dev, "Recovery failed\n");
 }
 
+static void health_check(struct timer_list *t)
+{
+	struct mhi_pci_device *mhi_pdev = from_timer(mhi_pdev, t, health_check_timer);
+	struct mhi_controller *mhi_cntrl = &mhi_pdev->mhi_cntrl;
+
+	if (!mhi_pci_is_alive(mhi_cntrl)) {
+		dev_err(mhi_cntrl->cntrl_dev, "Device died\n");
+		queue_work(system_long_wq, &mhi_pdev->recovery_work);
+		return;
+	}
+
+	/* reschedule in two seconds */
+	mod_timer(&mhi_pdev->health_check_timer, jiffies + HEALTH_CHECK_PERIOD);
+}
+
 static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const struct mhi_pci_dev_info *info = (struct mhi_pci_dev_info *) id->driver_data;
@@ -376,6 +399,7 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	INIT_WORK(&mhi_pdev->recovery_work, mhi_pci_recovery_work);
+	timer_setup(&mhi_pdev->health_check_timer, health_check, 0);
 
 	mhi_cntrl_config = info->config;
 	mhi_cntrl = &mhi_pdev->mhi_cntrl;
@@ -427,6 +451,9 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	set_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status);
 
+	/* start health check */
+	mod_timer(&mhi_pdev->health_check_timer, jiffies + HEALTH_CHECK_PERIOD);
+
 	return 0;
 
 err_unprepare:
@@ -442,6 +469,7 @@ static void mhi_pci_remove(struct pci_dev *pdev)
 	struct mhi_pci_device *mhi_pdev = pci_get_drvdata(pdev);
 	struct mhi_controller *mhi_cntrl = &mhi_pdev->mhi_cntrl;
 
+	del_timer(&mhi_pdev->health_check_timer);
 	cancel_work_sync(&mhi_pdev->recovery_work);
 
 	if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) {
@@ -459,6 +487,8 @@ static void mhi_pci_reset_prepare(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev, "reset\n");
 
+	del_timer(&mhi_pdev->health_check_timer);
+
 	/* Clean up MHI state */
 	if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) {
 		mhi_power_down(mhi_cntrl, false);
@@ -502,6 +532,7 @@ static void mhi_pci_reset_done(struct pci_dev *pdev)
 	}
 
 	set_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status);
+	mod_timer(&mhi_pdev->health_check_timer, jiffies + HEALTH_CHECK_PERIOD);
 }
 
 static pci_ers_result_t mhi_pci_error_detected(struct pci_dev *pdev,
@@ -562,6 +593,7 @@ static int  __maybe_unused mhi_pci_suspend(struct device *dev)
 	struct mhi_pci_device *mhi_pdev = dev_get_drvdata(dev);
 	struct mhi_controller *mhi_cntrl = &mhi_pdev->mhi_cntrl;
 
+	del_timer(&mhi_pdev->health_check_timer);
 	cancel_work_sync(&mhi_pdev->recovery_work);
 
 	/* Transition to M3 state */
@@ -597,6 +629,9 @@ static int __maybe_unused mhi_pci_resume(struct device *dev)
 		goto err_recovery;
 	}
 
+	/* Resume health check */
+	mod_timer(&mhi_pdev->health_check_timer, jiffies + HEALTH_CHECK_PERIOD);
+
 	return 0;
 
 err_recovery: