powerpc/papr_scm: Add support for reporting dirty-shutdown-count

Persistent memory devices like NVDIMMs can loose cached writes in case
something prevents flush on power-fail. Such situations are termed as
dirty shutdown and are exposed to applications as
last-shutdown-state (LSS) flag and a dirty-shutdown-counter(DSC) as
described at [1]. The latter being useful in conditions where multiple
applications want to detect a dirty shutdown event without racing with
one another.

PAPR-NVDIMMs have so far only exposed LSS style flags to indicate a
dirty-shutdown-state. This patch further adds support for DSC via the
"ibm,persistence-failed-count" device tree property of an NVDIMM. This
property is a monotonic increasing 64-bit counter thats an indication
of number of times an NVDIMM has encountered a dirty-shutdown event
causing persistence loss.

Since this value is not expected to change after system-boot hence
papr_scm reads & caches its value during NVDIMM probe and exposes it
as a PAPR sysfs attributed named 'dirty_shutdown' to match the name of
similarly named NFIT sysfs attribute. Also this value is available to
libnvdimm via PAPR_PDSM_HEALTH payload. 'struct nd_papr_pdsm_health'
has been extended to add a new member called 'dimm_dsc' presence of
which is indicated by the newly introduced PDSM_DIMM_DSC_VALID flag.

References:
[1] https://pmem.io/documents/Dirty_Shutdown_Handling-V1.0.pdf

Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210624080621.252038-1-vaibhav@linux.ibm.com

2 files changed, 36 insertions, 0 deletions

diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h
index 50ef95e2f5b1..82488b1e7276 100644
--- a/arch/powerpc/include/uapi/asm/papr_pdsm.h
+++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h
@@ -77,6 +77,9 @@
 /* Indicate that the 'dimm_fuel_gauge' field is valid */
 #define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1
 
+/* Indicate that the 'dimm_dsc' field is valid */
+#define PDSM_DIMM_DSC_VALID 2
+
 /*
  * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH
  * Various flags indicate the health status of the dimm.
@@ -105,6 +108,9 @@ struct nd_papr_pdsm_health {
 
 			/* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */
 			__u16 dimm_fuel_gauge;
+
+			/* Extension flag PDSM_DIMM_DSC_VALID */
+			__u64 dimm_dsc;
 		};
 		__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
 	};
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index daa11600d34b..4b93c20b24b5 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -115,6 +115,9 @@ struct papr_scm_priv {
 	/* Health information for the dimm */
 	u64 health_bitmap;
 
+	/* Holds the last known dirty shutdown counter value */
+	u64 dirty_shutdown_counter;
+
 	/* length of the stat buffer as expected by phyp */
 	size_t stat_buffer_len;
 };
@@ -604,6 +607,16 @@ free_stats:
 	return rc;
 }
 
+/* Add the dirty-shutdown-counter value to the pdsm */
+static int papr_pdsm_dsc(struct papr_scm_priv *p,
+			 union nd_pdsm_payload *payload)
+{
+	payload->health.extension_flags |= PDSM_DIMM_DSC_VALID;
+	payload->health.dimm_dsc = p->dirty_shutdown_counter;
+
+	return sizeof(struct nd_papr_pdsm_health);
+}
+
 /* Fetch the DIMM health info and populate it in provided package. */
 static int papr_pdsm_health(struct papr_scm_priv *p,
 			    union nd_pdsm_payload *payload)
@@ -647,6 +660,8 @@ static int papr_pdsm_health(struct papr_scm_priv *p,
 
 	/* Populate the fuel gauge meter in the payload */
 	papr_pdsm_fuel_gauge(p, payload);
+	/* Populate the dirty-shutdown-counter field */
+	papr_pdsm_dsc(p, payload);
 
 	rc = sizeof(struct nd_papr_pdsm_health);
 
@@ -908,6 +923,16 @@ static ssize_t flags_show(struct device *dev,
 }
 DEVICE_ATTR_RO(flags);
 
+static ssize_t dirty_shutdown_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *dimm = to_nvdimm(dev);
+	struct papr_scm_priv *p = nvdimm_provider_data(dimm);
+
+	return sysfs_emit(buf, "%llu\n", p->dirty_shutdown_counter);
+}
+DEVICE_ATTR_RO(dirty_shutdown);
+
 static umode_t papr_nd_attribute_visible(struct kobject *kobj,
 					 struct attribute *attr, int n)
 {
@@ -926,6 +951,7 @@ static umode_t papr_nd_attribute_visible(struct kobject *kobj,
 static struct attribute *papr_nd_attributes[] = {
 	&dev_attr_flags.attr,
 	&dev_attr_perf_stats.attr,
+	&dev_attr_dirty_shutdown.attr,
 	NULL,
 };
 
@@ -1151,6 +1177,10 @@ static int papr_scm_probe(struct platform_device *pdev)
 	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
 	p->hcall_flush_required = of_property_read_bool(dn, "ibm,hcall-flush-required");
 
+	if (of_property_read_u64(dn, "ibm,persistence-failed-count",
+				 &p->dirty_shutdown_counter))
+		p->dirty_shutdown_counter = 0;
+
 	/* We just need to ensure that set cookies are unique across */
 	uuid_parse(uuid_str, &uuid);