pds_core: add devlink health facilities

Add devlink health reporting on top of our fw watchdog.

Example:
  # devlink health show pci/0000:2b:00.0 reporter fw
  pci/0000:2b:00.0:
    reporter fw
      state healthy error 0 recover 0
  # devlink health diagnose pci/0000:2b:00.0 reporter fw
   Status: healthy State: 1 Generation: 0 Recoveries: 0
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/device_drivers/ethernet/amd/pds_core.rst

@@ -26,6 +26,18 @@ messages such as these::
   pds_core 0000:b6:00.0: 252.048 Gb/s available PCIe bandwidth (16.0 GT/s PCIe x16 link)
   pds_core 0000:b6:00.0: FW: 1.60.0-73
 
+Health Reporters
+================
+
+The driver supports a devlink health reporter for FW status::
+
+  # devlink health show pci/0000:2b:00.0 reporter fw
+  pci/0000:2b:00.0:
+    reporter fw
+      state healthy error 0 recover 0
+  # devlink health diagnose pci/0000:2b:00.0 reporter fw
+   Status: healthy State: 1 Generation: 0 Recoveries: 0
+
 Support
 =======
 

drivers/net/ethernet/amd/pds_core/Makefile

@@ -4,6 +4,7 @@
 obj-$(CONFIG_PDS_CORE) := pds_core.o
 
 pds_core-y := main.o \
+	      devlink.o \
 	      dev.o \
 	      core.o
 

drivers/net/ethernet/amd/pds_core/core.c

@@ -5,7 +5,7 @@
 
 int pdsc_setup(struct pdsc *pdsc, bool init)
 {
-	int err = 0;
+	int err;
 
 	if (init)
 		err = pdsc_dev_init(pdsc);
@@ -42,6 +42,8 @@ static void pdsc_fw_down(struct pdsc *pdsc)
 		return;
 	}
 
+	devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
+
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
 }
 
@@ -58,6 +60,10 @@ static void pdsc_fw_up(struct pdsc *pdsc)
 	if (err)
 		goto err_out;
 
+	pdsc->fw_recoveries++;
+	devlink_health_reporter_state_update(pdsc->fw_reporter,
+					     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
 	return;
 
 err_out:

drivers/net/ethernet/amd/pds_core/core.h

@@ -68,6 +68,8 @@ struct pdsc {
 	struct timer_list wdtimer;
 	unsigned int wdtimer_period;
 	struct work_struct health_work;
+	struct devlink_health_reporter *fw_reporter;
+	u32 fw_recoveries;
 
 	struct pdsc_devinfo dev_info;
 	struct pds_core_dev_identity dev_ident;
@@ -88,6 +90,10 @@ struct pdsc {
 	u64 __iomem *kern_dbpage;
 };
 
+int pdsc_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			      struct devlink_fmsg *fmsg,
+			      struct netlink_ext_ack *extack);
+
 void pdsc_debugfs_create(void);
 void pdsc_debugfs_destroy(void);
 void pdsc_debugfs_add_dev(struct pdsc *pdsc);

drivers/net/ethernet/amd/pds_core/devlink.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#include "core.h"
+
+int pdsc_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			      struct devlink_fmsg *fmsg,
+			      struct netlink_ext_ack *extack)
+{
+	struct pdsc *pdsc = devlink_health_reporter_priv(reporter);
+	int err;
+
+	mutex_lock(&pdsc->config_lock);
+
+	if (test_bit(PDSC_S_FW_DEAD, &pdsc->state))
+		err = devlink_fmsg_string_pair_put(fmsg, "Status", "dead");
+	else if (!pdsc_is_fw_good(pdsc))
+		err = devlink_fmsg_string_pair_put(fmsg, "Status", "unhealthy");
+	else
+		err = devlink_fmsg_string_pair_put(fmsg, "Status", "healthy");
+
+	mutex_unlock(&pdsc->config_lock);
+
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "State",
+					pdsc->fw_status &
+						~PDS_CORE_FW_STS_F_GENERATION);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "Generation",
+					pdsc->fw_generation >> 4);
+	if (err)
+		return err;
+
+	return devlink_fmsg_u32_pair_put(fmsg, "Recoveries",
+					 pdsc->fw_recoveries);
+}

drivers/net/ethernet/amd/pds_core/main.c

@@ -130,10 +130,16 @@ static int pdsc_init_vf(struct pdsc *vf)
 	return -1;
 }
 
+static const struct devlink_health_reporter_ops pdsc_fw_reporter_ops = {
+	.name = "fw",
+	.diagnose = pdsc_fw_reporter_diagnose,
+};
+
 #define PDSC_WQ_NAME_LEN 24
 
 static int pdsc_init_pf(struct pdsc *pdsc)
 {
+	struct devlink_health_reporter *hr;
 	char wq_name[PDSC_WQ_NAME_LEN];
 	struct devlink *dl;
 	int err;
@@ -172,6 +178,16 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 
 	dl = priv_to_devlink(pdsc);
 	devl_lock(dl);
+
+	hr = devl_health_reporter_create(dl, &pdsc_fw_reporter_ops, 0, pdsc);
+	if (IS_ERR(hr)) {
+		dev_warn(pdsc->dev, "Failed to create fw reporter: %pe\n", hr);
+		err = PTR_ERR(hr);
+		devl_unlock(dl);
+		goto err_out_teardown;
+	}
+	pdsc->fw_reporter = hr;
+
 	devl_register(dl);
 	devl_unlock(dl);
 
@@ -180,6 +196,8 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 
 	return 0;
 
+err_out_teardown:
+	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
 	mutex_unlock(&pdsc->config_lock);
 	del_timer_sync(&pdsc->wdtimer);
@@ -283,6 +301,10 @@ static void pdsc_remove(struct pci_dev *pdev)
 	dl = priv_to_devlink(pdsc);
 	devl_lock(dl);
 	devl_unregister(dl);
+	if (pdsc->fw_reporter) {
+		devl_health_reporter_destroy(pdsc->fw_reporter);
+		pdsc->fw_reporter = NULL;
+	}
 	devl_unlock(dl);
 
 	if (!pdev->is_virtfn) {