From: Eddie James <eajames@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: linux-hwmon@vger.kernel.org, devicetree@vger.kernel.org,
linux-doc@vger.kernel.org, linux@roeck-us.net, jdelvare@suse.com,
corbet@lwn.net, mark.rutland@arm.com, robh+dt@kernel.org,
cbostic@linux.vnet.ibm.com, jk@ozlabs.org, joel@jms.id.au,
andrew@aj.id.au, eajames@linux.vnet.ibm.com,
"Edward A. James" <eajames@us.ibm.com>
Subject: [PATCH v2 07/10] drivers/hwmon/occ: Add error handling
Date: Thu, 27 Jul 2017 09:30:26 -0500 [thread overview]
Message-ID: <1501165829-12395-8-git-send-email-eajames@linux.vnet.ibm.com> (raw)
In-Reply-To: <1501165829-12395-1-git-send-email-eajames@linux.vnet.ibm.com>
From: "Edward A. James" <eajames@us.ibm.com>
Add logic to detect a number of error scenarios on the OCC. Export any
errors through an additional non-hwmon device attribute. The error
counting and state verification are required by the OCC hardware
specification.
Signed-off-by: Edward A. James <eajames@us.ibm.com>
---
drivers/hwmon/occ/common.c | 82 ++++++++++++++++++++++++++++++++++++++++++++--
drivers/hwmon/occ/common.h | 4 +++
2 files changed, 84 insertions(+), 2 deletions(-)
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 2459e12..970b31f 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -17,6 +17,11 @@
#include "common.h"
+#define OCC_ERROR_COUNT_THRESHOLD 2 /* OCC HW defined */
+
+#define OCC_STATE_SAFE 4
+#define OCC_SAFE_TIMEOUT msecs_to_jiffies(60000) /* 1 min */
+
#define OCC_UPDATE_FREQUENCY msecs_to_jiffies(1000)
/* OCC status bits */
@@ -126,10 +131,33 @@ struct extended_sensor {
u8 data[6];
} __packed;
+static atomic_t occs_present = ATOMIC_INIT(0);
+
+static ssize_t occ_show_error(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct occ *occ = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE - 1, "%d\n", occ->error);
+}
+
+static DEVICE_ATTR(occ_error, 0444, occ_show_error, NULL);
+
+/* Notify user if we have an error and a change in error state. */
+static void occ_notify_error(struct occ *occ, int old_error)
+{
+ /* check hwmon pointer to verify error attribute has been added */
+ if (occ->error != old_error && occ->error && occ->hwmon)
+ sysfs_notify(&occ->bus_dev->kobj, NULL,
+ dev_attr_occ_error.attr.name);
+}
+
static int occ_poll(struct occ *occ)
{
+ struct occ_poll_response_header *header;
u16 checksum = occ->poll_cmd_data + 1;
u8 cmd[8];
+ int rc, old_error = occ->error;
/* big endian */
cmd[0] = 0; /* sequence number */
@@ -142,12 +170,47 @@ static int occ_poll(struct occ *occ)
cmd[7] = 0;
/* mutex should already be locked if necessary */
- return occ->send_cmd(occ, cmd);
+ rc = occ->send_cmd(occ, cmd);
+ if (rc) {
+ if (occ->error_count++ > OCC_ERROR_COUNT_THRESHOLD)
+ occ->error = rc;
+
+ goto done;
+ }
+
+ /* clear error since communication was successful */
+ occ->error_count = 0;
+ occ->error = 0;
+
+ header = (struct occ_poll_response_header *)occ->resp.data;
+ /* check for safe state */
+ if (header->occ_state == OCC_STATE_SAFE) {
+ if (occ->last_safe) {
+ if (time_after(jiffies,
+ occ->last_safe + OCC_SAFE_TIMEOUT))
+ occ->error = -EHOSTDOWN;
+ } else {
+ occ->last_safe = jiffies;
+ }
+ } else {
+ occ->last_safe = 0;
+ }
+
+ if (header->status & OCC_STAT_MASTER) {
+ /* check if we're missing any OCCs */
+ if (hweight8(header->occs_present) !=
+ atomic_read(&occs_present))
+ occ->error = -ENXIO;
+ }
+
+done:
+ occ_notify_error(occ, old_error);
+ return rc;
}
static int occ_set_user_power_cap(struct occ *occ, u16 user_power_cap)
{
- int rc;
+ int rc, old_error = occ->error;
u8 cmd[8];
u16 checksum = 0x24;
__be16 user_power_cap_be = cpu_to_be16(user_power_cap);
@@ -171,6 +234,16 @@ static int occ_set_user_power_cap(struct occ *occ, u16 user_power_cap)
mutex_unlock(&occ->lock);
+ if (rc) {
+ if (occ->error_count++ > OCC_ERROR_COUNT_THRESHOLD)
+ occ->error = rc;
+ } else {
+ /* successful communication so clear the error */
+ occ->error_count = 0;
+ occ->error = 0;
+ }
+
+ occ_notify_error(occ, old_error);
return rc;
}
@@ -1110,6 +1183,7 @@ static ssize_t occ_show_status(struct device *dev,
&sensor_dev_attr_occ_mem_throttle.dev_attr.attr,
&sensor_dev_attr_occ_quick_drop.dev_attr.attr,
&sensor_dev_attr_occ_status.dev_attr.attr,
+ &dev_attr_occ_error.attr,
NULL
};
@@ -1197,6 +1271,8 @@ int occ_setup(struct occ *occ, const char *name)
return rc;
}
+ atomic_inc(&occs_present);
+
rc = sysfs_create_group(&occ->bus_dev->kobj, &occ_attr_group);
if (rc)
dev_warn(occ->bus_dev, "failed to create status attrs: %d\n",
@@ -1208,4 +1284,6 @@ int occ_setup(struct occ *occ, const char *name)
void occ_shutdown(struct occ *occ)
{
sysfs_remove_group(&occ->bus_dev->kobj, &occ_attr_group);
+
+ atomic_dec(&occs_present);
}
diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h
index dc9e06d..cef2174 100644
--- a/drivers/hwmon/occ/common.h
+++ b/drivers/hwmon/occ/common.h
@@ -107,6 +107,10 @@ struct occ {
struct occ_attribute *attrs;
struct attribute_group group;
const struct attribute_group *groups[2];
+
+ int error;
+ unsigned int error_count; /* number of errors observed */
+ unsigned long last_safe; /* time OCC entered safe state */
};
int occ_setup(struct occ *occ, const char *name);
--
1.8.3.1
next prev parent reply other threads:[~2017-07-27 14:31 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-27 14:30 [PATCH v2 00/10] drivers/hwmon: Add On-Chip Controller (OCC) hwmon driver Eddie James
2017-07-27 14:30 ` [PATCH v2 01/10] " Eddie James
2017-07-27 14:30 ` [PATCH v2 02/10] drivers/hwmon/occ: Add command transport method for P8 and P9 Eddie James
2017-07-29 16:48 ` kbuild test robot
2017-07-27 14:30 ` [PATCH v2 03/10] drivers/hwmon/occ: Parse OCC poll response Eddie James
2017-07-27 14:30 ` [PATCH v2 04/10] drivers/hwmon/occ: Add sensor types and versions Eddie James
2017-07-27 14:30 ` [PATCH v2 05/10] drivers/hwmon/occ: Add sensor attributes and register hwmon device Eddie James
2017-07-27 14:30 ` [PATCH v2 06/10] drivers/hwmon/occ: Add non-hwmon attributes Eddie James
2017-07-27 14:30 ` Eddie James [this message]
2017-07-27 14:30 ` [PATCH v2 08/10] Documentation: hwmon: Add OCC documentation Eddie James
2017-07-27 14:30 ` [PATCH v2 09/10] Documentation: ABI: Add occ-hwmon driver sysfs documentation Eddie James
2017-07-27 14:30 ` [PATCH v2 10/10] dt-bindings: i2c: Add P8 OCC hwmon driver documentation Eddie James
2017-08-03 20:24 ` Rob Herring
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1501165829-12395-8-git-send-email-eajames@linux.vnet.ibm.com \
--to=eajames@linux.vnet.ibm.com \
--cc=andrew@aj.id.au \
--cc=cbostic@linux.vnet.ibm.com \
--cc=corbet@lwn.net \
--cc=devicetree@vger.kernel.org \
--cc=eajames@us.ibm.com \
--cc=jdelvare@suse.com \
--cc=jk@ozlabs.org \
--cc=joel@jms.id.au \
--cc=linux-doc@vger.kernel.org \
--cc=linux-hwmon@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@roeck-us.net \
--cc=mark.rutland@arm.com \
--cc=robh+dt@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).