@@ -123,6 +123,7 @@ struct nd_pdsm_cmd_pkg {
*/
enum papr_scm_pdsm {
PAPR_SCM_PDSM_MIN = 0x0,
+ PAPR_SCM_PDSM_HEALTH,
PAPR_SCM_PDSM_MAX,
};
@@ -150,4 +151,42 @@ static void *pdsm_cmd_to_payload(struct nd_pdsm_cmd_pkg *pcmd)
return (void *)((__u8 *) pcmd + pcmd->payload_offset);
}
+/* Various scm-dimm health indicators */
+#define PAPR_PDSM_DIMM_HEALTHY 0
+#define PAPR_PDSM_DIMM_UNHEALTHY 1
+#define PAPR_PDSM_DIMM_CRITICAL 2
+#define PAPR_PDSM_DIMM_FATAL 3
+
+/*
+ * Struct exchanged between kernel & ndctl in for PAPR_SCM_PDSM_HEALTH
+ * Various flags indicate the health status of the dimm.
+ *
+ * dimm_unarmed : Dimm not armed. So contents wont persist.
+ * dimm_bad_shutdown : Previous shutdown did not persist contents.
+ * dimm_bad_restore : Contents from previous shutdown werent restored.
+ * dimm_scrubbed : Contents of the dimm have been scrubbed.
+ * dimm_locked : Contents of the dimm cant be modified until CEC reboot
+ * dimm_encrypted : Contents of dimm are encrypted.
+ * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX
+ */
+struct nd_papr_pdsm_health_v1 {
+ __u8 dimm_unarmed;
+ __u8 dimm_bad_shutdown;
+ __u8 dimm_bad_restore;
+ __u8 dimm_scrubbed;
+ __u8 dimm_locked;
+ __u8 dimm_encrypted;
+ __u16 dimm_health;
+} __packed;
+
+/*
+ * Typedef the current struct for dimm_health so that any application
+ * or kernel recompiled after introducing a new version automatically
+ * supports the new version.
+ */
+#define nd_papr_pdsm_health nd_papr_pdsm_health_v1
+
+/* Current version number for the dimm health struct */
+#define ND_PAPR_PDSM_HEALTH_VERSION 1
+
#endif /* _UAPI_ASM_POWERPC_PAPR_SCM_PDSM_H_ */
@@ -50,7 +50,7 @@ struct papr_scm_priv {
unsigned long lasthealth_jiffies;
/* Health information for the dimm */
- u64 health_bitmap;
+ struct nd_papr_pdsm_health health;
};
static int drc_pmem_bind(struct papr_scm_priv *p)
@@ -170,6 +170,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p, bool force)
unsigned long ret[PLPAR_HCALL_BUFSIZE];
s64 rc;
unsigned long cache_timeout;
+ u64 health;
/* Protect concurrent modifications to papr_scm_priv */
rc = mutex_lock_interruptible(&p->dimm_mutex);
@@ -196,12 +197,41 @@ static int drc_pmem_query_health(struct papr_scm_priv *p, bool force)
}
p->lasthealth_jiffies = jiffies;
- p->health_bitmap = ret[0] & ret[1];
+ health = ret[0] & ret[1];
dev_dbg(&p->pdev->dev,
"Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n",
ret[0], ret[1]);
+ memset(&p->health, 0, sizeof(p->health));
+
+ /* Check for various masks in bitmap and set the buffer */
+ if (health & PAPR_SCM_DIMM_UNARMED_MASK)
+ p->health.dimm_unarmed = 1;
+
+ if (health & PAPR_SCM_DIMM_BAD_SHUTDOWN_MASK)
+ p->health.dimm_bad_shutdown = 1;
+
+ if (health & PAPR_SCM_DIMM_BAD_RESTORE_MASK)
+ p->health.dimm_bad_restore = 1;
+
+ if (health & PAPR_SCM_DIMM_ENCRYPTED)
+ p->health.dimm_encrypted = 1;
+
+ if (health & PAPR_SCM_DIMM_SCRUBBED_AND_LOCKED) {
+ p->health.dimm_locked = 1;
+ p->health.dimm_scrubbed = 1;
+ }
+
+ if (health & PAPR_SCM_DIMM_HEALTH_UNHEALTHY)
+ p->health.dimm_health = PAPR_PDSM_DIMM_UNHEALTHY;
+
+ if (health & PAPR_SCM_DIMM_HEALTH_CRITICAL)
+ p->health.dimm_health = PAPR_PDSM_DIMM_CRITICAL;
+
+ if (health & PAPR_SCM_DIMM_HEALTH_FATAL)
+ p->health.dimm_health = PAPR_PDSM_DIMM_FATAL;
+
out:
mutex_unlock(&p->dimm_mutex);
return rc;
@@ -359,6 +389,61 @@ static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
return 0;
}
+/* Fetch the DIMM health info and populate it in provided package. */
+static int papr_scm_get_health(struct papr_scm_priv *p,
+ struct nd_pdsm_cmd_pkg *pkg)
+{
+ int rc;
+ size_t copysize = sizeof(p->health);
+
+ /* Always fetch upto date dimm health data ignoring cached values */
+ rc = drc_pmem_query_health(p, true);
+ if (rc)
+ goto out;
+ /*
+ * If the requested payload version is greater than one we know
+ * about, return the payload version we know about and let
+ * caller/userspace handle.
+ */
+ if (pkg->payload_version > ND_PAPR_PDSM_HEALTH_VERSION)
+ pkg->payload_version = ND_PAPR_PDSM_HEALTH_VERSION;
+
+ if (pkg->hdr.nd_size_out < copysize) {
+ dev_dbg(&p->pdev->dev, "Truncated payload (%u). Expected (%lu)",
+ pkg->hdr.nd_size_out, copysize);
+ rc = -ENOSPC;
+ goto out;
+ }
+
+ dev_dbg(&p->pdev->dev, "Copying payload size=%lu version=0x%x\n",
+ copysize, pkg->payload_version);
+
+ /*
+ * Copy a subset of health struct based on copysize ensuring dimm mutex
+ * is locked to prevent a simultaneous read/write of health data
+ */
+ rc = mutex_lock_interruptible(&p->dimm_mutex);
+ if (rc)
+ goto out;
+
+ /* Copy the health struct to the payload */
+ memcpy(pdsm_cmd_to_payload(pkg), &p->health, copysize);
+
+ mutex_unlock(&p->dimm_mutex);
+
+ pkg->hdr.nd_fw_size = copysize;
+
+out:
+ /*
+ * Put the error in out package and return success from function
+ * so that errors if any are propogated back to userspace.
+ */
+ pkg->cmd_status = rc;
+ dev_dbg(&p->pdev->dev, "completion code = %d\n", rc);
+
+ return 0;
+}
+
static int papr_scm_service_pdsm(struct papr_scm_priv *p,
struct nd_pdsm_cmd_pkg *call_pkg)
{
@@ -373,6 +458,9 @@ static int papr_scm_service_pdsm(struct papr_scm_priv *p,
/* Depending on the DSM command call appropriate service routine */
switch (call_pkg->hdr.nd_command) {
+ case PAPR_SCM_PDSM_HEALTH:
+ return papr_scm_get_health(p, call_pkg);
+
default:
dev_dbg(&p->pdev->dev, "Unsupported PDSM request 0x%llx\n",
call_pkg->hdr.nd_command);
@@ -459,39 +547,41 @@ static ssize_t flags_show(struct device *dev,
struct nvdimm *dimm = to_nvdimm(dev);
struct papr_scm_priv *p = nvdimm_provider_data(dimm);
int rc;
- u64 health;
rc = drc_pmem_query_health(p, false);
if (rc)
return rc;
- /*
- * Copy the LE byte-ordered health_bitmap locally, check for various
- * masks and update the sysfs out buffer.
- */
- health = p->health_bitmap;
+ /* Protect against concurrent modifications to papr_scm_priv */
+ rc = mutex_lock_interruptible(&p->dimm_mutex);
+ if (rc)
+ return rc;
- if (health & PAPR_SCM_DIMM_UNARMED_MASK)
+ if (p->health.dimm_unarmed)
rc += sprintf(buf, "not_armed ");
- if (health & PAPR_SCM_DIMM_BAD_SHUTDOWN_MASK)
- rc += sprintf(buf + rc, "save_fail ");
+ if (p->health.dimm_bad_shutdown)
+ rc += sprintf(buf + rc, "flush_fail ");
- if (health & PAPR_SCM_DIMM_BAD_RESTORE_MASK)
+ if (p->health.dimm_bad_restore)
rc += sprintf(buf + rc, "restore_fail ");
- if (health & PAPR_SCM_DIMM_ENCRYPTED)
+ if (p->health.dimm_encrypted)
rc += sprintf(buf + rc, "encrypted ");
- if (health & PAPR_SCM_DIMM_SMART_EVENT_MASK)
+ if (p->health.dimm_health)
rc += sprintf(buf + rc, "smart_notify ");
- if (health & PAPR_SCM_DIMM_SCRUBBED_AND_LOCKED)
- rc += sprintf(buf + rc, "scrubbed locked ");
+ if (p->health.dimm_scrubbed)
+ rc += sprintf(buf + rc, "scrubbed ");
+
+ if (p->health.dimm_locked)
+ rc += sprintf(buf + rc, "locked ");
if (rc > 0)
rc += sprintf(buf + rc, "\n");
+ mutex_unlock(&p->dimm_mutex);
return rc;
}
DEVICE_ATTR_RO(flags);
This patch implements support for PDSM request 'PAPR_SCM_PDSM_HEALTH' that returns a newly introduced 'struct nd_papr_pdsm_health' instance containing dimm health information back to user space in response to ND_CMD_CALL. This functionality is implemented in newly introduced papr_scm_get_health() that queries the scm-dimm health information and then copies this information to the package payload whose layout is defined by 'struct nd_papr_pdsm_health'. The patch also introduces a new member 'struct papr_scm_priv.health' thats an instance of 'struct nd_papr_pdsm_health' to cache the health information of a nvdimm. As a result functions drc_pmem_query_health() and flags_show() are updated to populate and use this new struct instead of a u64 integer that was earlier used. Cc: Dan Williams <dan.j.williams@intel.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com> --- Changelog: v5..v6: * Added attribute '__packed' to 'struct nd_papr_pdsm_health_v1' to gaurd against possibility of different compilers adding different paddings to the struct [ Dan Williams ] * Updated 'struct nd_papr_pdsm_health_v1' to use __u8 instead of 'bool' and also updated drc_pmem_query_health() to take this into account. [ Dan Williams ] v4..v5: * None v3..v4: * Call the DSM_PAPR_SCM_HEALTH service function from papr_scm_service_dsm() instead of papr_scm_ndctl(). [Aneesh] v2..v3: * Updated struct nd_papr_scm_dimm_health_stat_v1 to use '__xx' types as its exported to the userspace [Aneesh] * Changed the constants DSM_PAPR_SCM_DIMM_XX indicating dimm health from enum to #defines [Aneesh] v1..v2: * New patch in the series --- arch/powerpc/include/uapi/asm/papr_scm_pdsm.h | 39 ++++++ arch/powerpc/platforms/pseries/papr_scm.c | 122 +++++++++++++++--- 2 files changed, 145 insertions(+), 16 deletions(-)