diff mbox series

[ndctl,REPOST,v3,1/2] libndctl, intel: Indicate supported smart-inject types

Message ID 164009760609.743207.15606385364785007374.stgit@lep8c.aus.stglabs.ibm.com (mailing list archive)
State Accepted
Commit edcd9b7e10b3b33a9660e412a2db1beab30936d3
Headers show
Series papr: Implement initial support for injecting smart errors | expand

Commit Message

Shivaprasad G Bhat Dec. 21, 2021, 2:40 p.m. UTC
From: Vaibhav Jain <vaibhav@linux.ibm.com>

Presently the inject-smart code assumes support for injecting all
smart-errors namely media-temperature, controller-temperature,
spares-remaining, fatal-health and unsafe-shutdown. This assumption
may break in case of other non-Intel NVDIMM types namely PAPR NVDIMMs
which presently only have support for injecting unsafe-shutdown and
fatal health events.

Trying to inject-smart errors on PAPR NVDIMMs causes problems as
smart_inject() prematurely exits when trying to inject
media-temperature smart-error errors out.

To fix this issue the patch proposes extending the definition of
dimm_op 'smart_inject_supported' to return bitmap of flags indicating
the type of smart-error injections supported by an NVDIMM. These types
are indicated by the newly introduced defines ND_SMART_INJECT_* . A
dimm-ops provide can return an bitmap composed of these flags back
from its implementation of 'smart_inject_supported' to indicate to
dimm_inject_smart() which type of smart-error injection it
supports. In case of an error the dimm-op is still expected to return
a negative error code back to the caller.

The patch updates intel_dimm_smart_inject_supported() to return a
bitmap composed of all ND_SMART_INJECT_* flags to indicate support for
all smart-error types.

Finally the patch also updates smart_inject() to test for specific
ND_START_INJECT_* flags before sending a smart-inject command via
dimm-provider.

Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
 ndctl/inject-smart.c |   31 ++++++++++++++++++++++++-------
 ndctl/lib/intel.c    |    7 ++++++-
 ndctl/libndctl.h     |    8 ++++++++
 3 files changed, 38 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/ndctl/inject-smart.c b/ndctl/inject-smart.c
index 9077bca2..c3c5fa5f 100644
--- a/ndctl/inject-smart.c
+++ b/ndctl/inject-smart.c
@@ -393,18 +393,26 @@  out:
 	} \
 }
 
-static int smart_inject(struct ndctl_dimm *dimm)
+static int smart_inject(struct ndctl_dimm *dimm, unsigned int inject_types)
 {
 	const char *name = ndctl_dimm_get_devname(dimm);
 	struct ndctl_cmd *si_cmd = NULL;
 	int rc = -EOPNOTSUPP;
 
-	send_inject_val(media_temperature)
-	send_inject_val(ctrl_temperature)
-	send_inject_val(spares)
-	send_inject_bool(fatal)
-	send_inject_bool(unsafe_shutdown)
+	if (inject_types & ND_SMART_INJECT_MEDIA_TEMPERATURE)
+		send_inject_val(media_temperature);
 
+	if (inject_types & ND_SMART_INJECT_CTRL_TEMPERATURE)
+		send_inject_val(ctrl_temperature);
+
+	if (inject_types & ND_SMART_INJECT_SPARES_REMAINING)
+		send_inject_val(spares);
+
+	if (inject_types & ND_SMART_INJECT_HEALTH_STATE)
+		send_inject_bool(fatal);
+
+	if (inject_types & ND_SMART_INJECT_UNCLEAN_SHUTDOWN)
+		send_inject_bool(unsafe_shutdown);
 out:
 	ndctl_cmd_unref(si_cmd);
 	return rc;
@@ -415,6 +423,7 @@  static int dimm_inject_smart(struct ndctl_dimm *dimm)
 	struct json_object *jhealth;
 	struct json_object *jdimms;
 	struct json_object *jdimm;
+	unsigned int supported_types;
 	int rc;
 
 	rc = ndctl_dimm_smart_inject_supported(dimm);
@@ -431,6 +440,14 @@  static int dimm_inject_smart(struct ndctl_dimm *dimm)
 		error("%s: smart injection not supported by either platform firmware or the kernel.",
 			ndctl_dimm_get_devname(dimm));
 		return rc;
+	default:
+		if (rc < 0) {
+			error("%s: Unknown error %d while checking for smart injection support",
+			      ndctl_dimm_get_devname(dimm), rc);
+			return rc;
+		}
+		supported_types = rc;
+		break;
 	}
 
 	if (sctx.op_mask & (1 << OP_SET)) {
@@ -439,7 +456,7 @@  static int dimm_inject_smart(struct ndctl_dimm *dimm)
 			goto out;
 	}
 	if (sctx.op_mask & (1 << OP_INJECT)) {
-		rc = smart_inject(dimm);
+		rc = smart_inject(dimm, supported_types);
 		if (rc)
 			goto out;
 	}
diff --git a/ndctl/lib/intel.c b/ndctl/lib/intel.c
index a3df26e6..13148545 100644
--- a/ndctl/lib/intel.c
+++ b/ndctl/lib/intel.c
@@ -455,7 +455,12 @@  static int intel_dimm_smart_inject_supported(struct ndctl_dimm *dimm)
 		return -EIO;
 	}
 
-	return 0;
+	/* Indicate all smart injection types are supported */
+	return ND_SMART_INJECT_SPARES_REMAINING |
+		ND_SMART_INJECT_MEDIA_TEMPERATURE |
+		ND_SMART_INJECT_CTRL_TEMPERATURE |
+		ND_SMART_INJECT_HEALTH_STATE |
+		ND_SMART_INJECT_UNCLEAN_SHUTDOWN;
 }
 
 static const char *intel_cmd_desc(int fn)
diff --git a/ndctl/libndctl.h b/ndctl/libndctl.h
index b59026c1..4d5cdbf6 100644
--- a/ndctl/libndctl.h
+++ b/ndctl/libndctl.h
@@ -69,6 +69,13 @@  extern "C" {
 #define ND_EVENT_HEALTH_STATE		(1 << 3)
 #define ND_EVENT_UNCLEAN_SHUTDOWN	(1 << 4)
 
+/* Flags indicating support for various smart injection types */
+#define ND_SMART_INJECT_SPARES_REMAINING	(1 << 0)
+#define ND_SMART_INJECT_MEDIA_TEMPERATURE	(1 << 1)
+#define ND_SMART_INJECT_CTRL_TEMPERATURE	(1 << 2)
+#define ND_SMART_INJECT_HEALTH_STATE		(1 << 3)
+#define ND_SMART_INJECT_UNCLEAN_SHUTDOWN	(1 << 4)
+
 size_t ndctl_min_namespace_size(void);
 size_t ndctl_sizeof_namespace_index(void);
 size_t ndctl_sizeof_namespace_label(void);
@@ -311,6 +318,7 @@  int ndctl_cmd_smart_inject_spares(struct ndctl_cmd *cmd, bool enable,
 		unsigned int spares);
 int ndctl_cmd_smart_inject_fatal(struct ndctl_cmd *cmd, bool enable);
 int ndctl_cmd_smart_inject_unsafe_shutdown(struct ndctl_cmd *cmd, bool enable);
+/* Returns a bitmap of ND_SMART_INJECT_* supported */
 int ndctl_dimm_smart_inject_supported(struct ndctl_dimm *dimm);
 
 struct ndctl_cmd *ndctl_dimm_cmd_new_vendor_specific(struct ndctl_dimm *dimm,