netdev - [PATCH v5 net-next 04/14] pds_core: add devlink health facilities

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230322185626.38758-5-shannon.nelson@amd.com>
Date:   Wed, 22 Mar 2023 11:56:16 -0700
From:   Shannon Nelson <shannon.nelson@....com>
To:     <shannon.nelson@....com>, <brett.creeley@....com>,
        <davem@...emloft.net>, <netdev@...r.kernel.org>, <kuba@...nel.org>
CC:     <drivers@...sando.io>, <leon@...nel.org>, <jiri@...nulli.us>
Subject: [PATCH v5 net-next 04/14] 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


Signed-off-by: Shannon Nelson <shannon.nelson@....com>
---
 drivers/net/ethernet/amd/pds_core/core.c    |  6 ++
 drivers/net/ethernet/amd/pds_core/core.h    |  2 +
 drivers/net/ethernet/amd/pds_core/devlink.c | 61 +++++++++++++++++++++
 3 files changed, 69 insertions(+)

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 e73af422fae0..0cf7810ba9de 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;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index a9021bfe680a..a5a243bed5bc 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -14,6 +14,63 @@ static const struct devlink_ops pdsc_dl_ops = {
 static const struct devlink_ops pdsc_dl_vf_ops = {
 };
 
+static 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;
+}
+
+static const struct devlink_health_reporter_ops pdsc_fw_reporter_ops = {
+		.name = "fw",
+		.diagnose = pdsc_fw_reporter_diagnose,
+};
+
+static void pdsc_dl_reporters_create(struct pdsc *pdsc)
+{
+	struct devlink *dl = priv_to_devlink(pdsc);
+	struct devlink_health_reporter *hr;
+
+	hr = devlink_health_reporter_create(dl, &pdsc_fw_reporter_ops, 0, pdsc);
+	if (IS_ERR(pdsc->fw_reporter)) {
+		dev_warn(pdsc->dev, "Failed to create fw reporter, err = %pe\n", hr);
+		return;
+	}
+
+	pdsc->fw_reporter = hr;
+}
+
+static void pdsc_dl_reporters_destroy(struct pdsc *pdsc)
+{
+	if (pdsc->fw_reporter) {
+		devlink_health_reporter_destroy(pdsc->fw_reporter);
+		pdsc->fw_reporter = NULL;
+	}
+}
+
 struct pdsc *pdsc_dl_alloc(struct device *dev, bool is_pf)
 {
 	const struct devlink_ops *ops;
@@ -38,6 +95,9 @@ int pdsc_dl_register(struct pdsc *pdsc)
 {
 	struct devlink *dl = priv_to_devlink(pdsc);
 
+	if (!pdsc->pdev->is_virtfn)
+		pdsc_dl_reporters_create(pdsc);
+
 	devlink_register(dl);
 
 	return 0;
@@ -48,4 +108,5 @@ void pdsc_dl_unregister(struct pdsc *pdsc)
 	struct devlink *dl = priv_to_devlink(pdsc);
 
 	devlink_unregister(dl);
+	pdsc_dl_reporters_destroy(pdsc);
 }
-- 
2.17.1