[PATCH 1/2] accel/habanalabs: add pcie reset prepare/done hooks

[Oded Gabbay]

From: farah kassabri <fkassabri at habana.ai>

When working on a bare-metal system, if FLR will happen the firmware
will handle it and driver will have no knowledge of it, and this will
cause two issues:

1.The driver will be in operational state while it should be in reset.
  This will cause the heartbeat mechanism to keep sending messages to FW
  while pci device is in reset. Eventually heartbeat will fail and
  the device will end up in non-operational state.

2. After FW handles the FLR, and due to the reset it'll go back to
   preboot stage, and driver need to perform hard reset in order to
   load the boot fit binary.

This patch will add reset_prepare hook that will set the device to
be in disabled state, so it'll be not operational, and also
reset_done hook which will be called after the actual FLR handling,
then it will perform hard reset.

Signed-off-by: farah kassabri <fkassabri at habana.ai>
Reviewed-by: Oded Gabbay <ogabbay at kernel.org>
Signed-off-by: Oded Gabbay <ogabbay at kernel.org>
---
 .../accel/habanalabs/common/habanalabs_drv.c  | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 306a5bc9bf89..35ae0ff347f5 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -670,6 +670,38 @@ static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+static void hl_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	hdev->disabled = true;
+}
+
+static void hl_pci_reset_done(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+	u32 flags;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	/*
+	 * Schedule a thread to trigger hard reset.
+	 * The reason for this handler, is for rare cases where the driver is up
+	 * and FLR occurs. This is valid only when working with no VM, so FW handles FLR
+	 * and resets the device. FW will go back preboot stage, so driver needs to perform
+	 * hard reset in order to load FW fit again.
+	 */
+	flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW;
+
+	hl_device_reset(hdev, flags);
+}
+
 static const struct dev_pm_ops hl_pm_ops = {
 	.suspend = hl_pmops_suspend,
 	.resume = hl_pmops_resume,
@@ -679,6 +711,8 @@ static const struct pci_error_handlers hl_pci_err_handler = {
 	.error_detected = hl_pci_err_detected,
 	.slot_reset = hl_pci_err_slot_reset,
 	.resume = hl_pci_err_resume,
+	.reset_prepare = hl_pci_reset_prepare,
+	.reset_done = hl_pci_reset_done,
 };
 
 static struct pci_driver hl_pci_driver = {
-- 
2.34.1