[v8,net-next,04/14] pds_core: add devlink health facilities

Commit Message

Nelson, Shannon March 30, 2023, 11:46 p.m. UTC

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


Signed-off-by: Shannon Nelson <[e-mail]>
---
 drivers/net/ethernet/amd/pds_core/Makefile  |  1 +
 drivers/net/ethernet/amd/pds_core/core.c    |  6 ++++
 drivers/net/ethernet/amd/pds_core/core.h    |  5 +++
 drivers/net/ethernet/amd/pds_core/devlink.c | 37 +++++++++++++++++++++
 drivers/net/ethernet/amd/pds_core/main.c    | 22 ++++++++++++
 5 files changed, 71 insertions(+)
 create mode 100644 drivers/net/ethernet/amd/pds_core/devlink.c

Patch

diff --git a/drivers/net/ethernet/amd/pds_core/Makefile b/drivers/net/ethernet/amd/pds_core/Makefile
index 95a6c31e92d2..eaca8557ba66 100644
--- a/drivers/net/ethernet/amd/pds_core/Makefile
+++ b/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
 
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 39e9a215f638..a9918c34018f 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -45,6 +45,8 @@  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);
 
 	mutex_unlock(&pdsc->config_lock);
@@ -68,6 +70,10 @@  static void pdsc_fw_up(struct pdsc *pdsc)
 
 	mutex_unlock(&pdsc->config_lock);
 
+	pdsc->fw_recoveries++;
+	devlink_health_reporter_state_update(pdsc->fw_reporter,
+					     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
 	return;
 
 err_out:
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 8ff65f2aa7f0..d111354234fa 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/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;
@@ -89,6 +91,9 @@  struct pdsc {
 };
 
 void pdsc_queue_health_check(struct pdsc *pdsc);
+int pdsc_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			      struct devlink_fmsg *fmsg,
+			      struct netlink_ext_ack *extack);
 
 #ifdef CONFIG_DEBUG_FS
 void pdsc_debugfs_create(void);
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
new file mode 100644
index 000000000000..717fcbf91aee
--- /dev/null
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -0,0 +1,37 @@ 
+// 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 = 0;
+
+	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");
+	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;
+	err = devlink_fmsg_u32_pair_put(fmsg, "Recoveries",
+					pdsc->fw_recoveries);
+	if (err)
+		return err;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index c73862898fb9..4920f3a2fbfb 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -162,10 +162,16 @@  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;
@@ -204,6 +210,16 @@  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);
 
@@ -212,6 +228,8 @@  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);
@@ -318,6 +336,10 @@  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) {