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>
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
=======
obj-$(CONFIG_PDS_CORE) := pds_core.o
pds_core-y := main.o \
+ devlink.o \
dev.o \
core.o
int pdsc_setup(struct pdsc *pdsc, bool init)
{
- int err = 0;
+ int err;
if (init)
err = pdsc_dev_init(pdsc);
return;
}
+ devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
+
pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
}
if (err)
goto err_out;
+ pdsc->fw_recoveries++;
+ devlink_health_reporter_state_update(pdsc->fw_reporter,
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
return;
err_out:
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;
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);
--- /dev/null
+// 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);
+}
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;
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);
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);
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) {