[PATCH net-next] net/mlx5: Add reset_prepare and reset_done callbacks

[PATCH net-next] net/mlx5: Add reset_prepare and reset_done callbacks

[Tariq Toukan]

From: Akiva Goldberger <agoldberger@nvidia.com>

Currently, the mlx5_core driver registers only the error_detected,
slot_reset and resume PCI error handlers. Add the reset_prepare and
reset_done callbacks, which are triggered by the PCI core before and
after a PCI reset, respectively. These callbacks let mlx5 quiesce and
restore device resources and commands around a PCI reset, so the driver
no longer relies on the reset happening while the device is otherwise
idle.

Additionally, add a device flag to indicate when a PCI reset is in
progress to serialize PCI reset flows with other reset flows, namely FW
reset. This flag also indicates to the reset_prepare and reset_done
callbacks when to do a full unload/reload of the driver. When the
callbacks are triggered by the hot-reset FW reset method, they leave the
teardown and reload to the FW reset.

Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/fw_reset.c    |  7 ++
 .../net/ethernet/mellanox/mlx5/core/main.c    | 89 ++++++++++++++++++-
 include/linux/mlx5/driver.h                   |  1 +
 3 files changed, 96 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 7c0585fe1ee7..2ba2f6dac263 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -501,6 +501,13 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 		return;
 	}
 
+	if (dev->pci_reset_in_progress) {
+		err = mlx5_fw_reset_set_reset_sync_nack(dev);
+		mlx5_core_warn(dev, "PCI reset in progress, Sync FW Update Reset Nack %s",
+			       err ? "Failed" : "Sent");
+		goto unlock;
+	}
+
 	if (mlx5_sync_reset_set_reset_requested(dev))
 		goto unlock;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 1a45474ce03d..fe7c0331b183 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2138,10 +2138,97 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 		       !err ? "recovered" : "Failed");
 }
 
+static void mlx5_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+	struct devlink *devlink;
+	bool fw_reset_in_prog;
+
+	if (!dev)
+		return;
+
+	devlink = priv_to_devlink(dev);
+
+	devl_lock(devlink);
+	fw_reset_in_prog = mlx5_fw_reset_in_progress(dev);
+	if (!fw_reset_in_prog)
+		dev->pci_reset_in_progress = true;
+	devl_unlock(devlink);
+
+	if (fw_reset_in_prog) {
+		mlx5_core_info(dev,
+			       "%s: fw reset in progress, leaving drain to fw_reset flow\n",
+			       __func__);
+		return;
+	}
+
+	mlx5_core_info(dev, "%s: resetting, device state = %d, pci_status = %d, intf_state = 0x%lx\n",
+		       __func__, dev->state, dev->pci_status, dev->intf_state);
+
+	mlx5_enter_error_state(dev, true);
+	mlx5_drain_health_wq(dev);
+	mlx5_unload_one(dev, false);
+	mlx5_pci_disable_device(dev);
+}
+
+static void mlx5_pci_reset_done(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+	struct devlink *devlink;
+	int err;
+
+	if (!dev)
+		return;
+
+	devlink = priv_to_devlink(dev);
+
+	if (!dev->pci_reset_in_progress) {
+		mlx5_core_info(dev,
+			       "%s: reset owned by fw_reset flow, leaving reload to it\n",
+			       __func__);
+		return;
+	}
+
+	err = mlx5_pci_enable_device(dev);
+	if (err) {
+		mlx5_core_err(dev, "%s: mlx5_pci_enable_device failed, err = %d\n",
+			      __func__, err);
+		goto clear_pci_reset_flag;
+	}
+
+	pci_set_master(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		mlx5_core_err(dev, "%s: wait_vital failed, err = %d\n",
+			      __func__, err);
+		goto disable;
+	}
+
+	err = mlx5_load_one(dev, true);
+	if (err) {
+		mlx5_core_err(dev, "%s: mlx5_load_one failed, err = %d\n",
+			      __func__, err);
+		goto disable;
+	}
+
+	mlx5_core_info(dev, "%s: reset done, device state = %d, pci_status = %d\n",
+		       __func__, dev->state, dev->pci_status);
+	goto clear_pci_reset_flag;
+
+disable:
+	mlx5_pci_disable_device(dev);
+clear_pci_reset_flag:
+	devl_lock(devlink);
+	dev->pci_reset_in_progress = false;
+	devl_unlock(devlink);
+}
+
 static const struct pci_error_handlers mlx5_err_handler = {
 	.error_detected = mlx5_pci_err_detected,
 	.slot_reset	= mlx5_pci_slot_reset,
-	.resume		= mlx5_pci_resume
+	.resume		= mlx5_pci_resume,
+	.reset_prepare	= mlx5_pci_reset_prepare,
+	.reset_done	= mlx5_pci_reset_done,
 };
 
 static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index abb99371ff13..7b9f3cd23e0b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -746,6 +746,7 @@ struct mlx5_core_dev {
 	/* sync pci state */
 	struct mutex		pci_status_mutex;
 	enum mlx5_pci_status	pci_status;
+	bool			pci_reset_in_progress;
 	u8			rev_id;
 	char			board_id[MLX5_BOARD_ID_LEN];
 	struct mlx5_cmd		cmd;

base-commit: d8674294aefef02266c4d47ad10131f1bffbe534
-- 
2.44.0