1 files changed, 293 insertions, 50 deletions

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index f48e87ac89c9..f7c9271bda58 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/ndctl.h>
 #include <linux/sched.h>
@@ -16,9 +17,11 @@
 #include <linux/nd.h>
 
 #include <asm/plpar_wrappers.h>
-#include <asm/papr_pdsm.h>
+#include <uapi/linux/papr_pdsm.h>
+#include <linux/papr_scm.h>
 #include <asm/mce.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
+#include <linux/perf_event.h>
 
 #define BIND_ANY_ADDR (~0ul)
 
@@ -28,46 +31,6 @@
 	 (1ul << ND_CMD_SET_CONFIG_DATA) | \
 	 (1ul << ND_CMD_CALL))
 
-/* DIMM health bitmap bitmap indicators */
-/* SCM device is unable to persist memory contents */
-#define PAPR_PMEM_UNARMED                   (1ULL << (63 - 0))
-/* SCM device failed to persist memory contents */
-#define PAPR_PMEM_SHUTDOWN_DIRTY            (1ULL << (63 - 1))
-/* SCM device contents are persisted from previous IPL */
-#define PAPR_PMEM_SHUTDOWN_CLEAN            (1ULL << (63 - 2))
-/* SCM device contents are not persisted from previous IPL */
-#define PAPR_PMEM_EMPTY                     (1ULL << (63 - 3))
-/* SCM device memory life remaining is critically low */
-#define PAPR_PMEM_HEALTH_CRITICAL           (1ULL << (63 - 4))
-/* SCM device will be garded off next IPL due to failure */
-#define PAPR_PMEM_HEALTH_FATAL              (1ULL << (63 - 5))
-/* SCM contents cannot persist due to current platform health status */
-#define PAPR_PMEM_HEALTH_UNHEALTHY          (1ULL << (63 - 6))
-/* SCM device is unable to persist memory contents in certain conditions */
-#define PAPR_PMEM_HEALTH_NON_CRITICAL       (1ULL << (63 - 7))
-/* SCM device is encrypted */
-#define PAPR_PMEM_ENCRYPTED                 (1ULL << (63 - 8))
-/* SCM device has been scrubbed and locked */
-#define PAPR_PMEM_SCRUBBED_AND_LOCKED       (1ULL << (63 - 9))
-
-/* Bits status indicators for health bitmap indicating unarmed dimm */
-#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED |		\
-				PAPR_PMEM_HEALTH_UNHEALTHY)
-
-/* Bits status indicators for health bitmap indicating unflushed dimm */
-#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY)
-
-/* Bits status indicators for health bitmap indicating unrestored dimm */
-#define PAPR_PMEM_BAD_RESTORE_MASK  (PAPR_PMEM_EMPTY)
-
-/* Bit status indicators for smart event notification */
-#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \
-				    PAPR_PMEM_HEALTH_FATAL |	\
-				    PAPR_PMEM_HEALTH_UNHEALTHY)
-
-#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS)
-#define PAPR_SCM_PERF_STATS_VERSION 0x1
-
 /* Struct holding a single performance metric */
 struct papr_scm_perf_stat {
 	u8 stat_id[8];
@@ -120,6 +83,9 @@ struct papr_scm_priv {
 
 	/* length of the stat buffer as expected by phyp */
 	size_t stat_buffer_len;
+
+	/* The bits which needs to be overridden */
+	u64 health_bitmap_inject_mask;
 };
 
 static int papr_scm_pmem_flush(struct nd_region *nd_region,
@@ -340,6 +306,191 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
 	return 0;
 }
 
+#ifdef CONFIG_PERF_EVENTS
+#define to_nvdimm_pmu(_pmu)	container_of(_pmu, struct nvdimm_pmu, pmu)
+
+static const char * const nvdimm_events_map[] = {
+	[1] = "CtlResCt",
+	[2] = "CtlResTm",
+	[3] = "PonSecs ",
+	[4] = "MemLife ",
+	[5] = "CritRscU",
+	[6] = "HostLCnt",
+	[7] = "HostSCnt",
+	[8] = "HostSDur",
+	[9] = "HostLDur",
+	[10] = "MedRCnt ",
+	[11] = "MedWCnt ",
+	[12] = "MedRDur ",
+	[13] = "MedWDur ",
+	[14] = "CchRHCnt",
+	[15] = "CchWHCnt",
+	[16] = "FastWCnt",
+};
+
+static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count)
+{
+	struct papr_scm_perf_stat *stat;
+	struct papr_scm_perf_stats *stats;
+	struct papr_scm_priv *p = dev_get_drvdata(dev);
+	int rc, size;
+
+	/* Invalid eventcode */
+	if (event->attr.config == 0 || event->attr.config >= ARRAY_SIZE(nvdimm_events_map))
+		return -EINVAL;
+
+	/* Allocate request buffer enough to hold single performance stat */
+	size = sizeof(struct papr_scm_perf_stats) +
+		sizeof(struct papr_scm_perf_stat);
+
+	if (!p)
+		return -EINVAL;
+
+	stats = kzalloc(size, GFP_KERNEL);
+	if (!stats)
+		return -ENOMEM;
+
+	stat = &stats->scm_statistic[0];
+	memcpy(&stat->stat_id,
+	       nvdimm_events_map[event->attr.config],
+		sizeof(stat->stat_id));
+	stat->stat_val = 0;
+
+	rc = drc_pmem_query_stats(p, stats, 1);
+	if (rc < 0) {
+		kfree(stats);
+		return rc;
+	}
+
+	*count = be64_to_cpu(stat->stat_val);
+	kfree(stats);
+	return 0;
+}
+
+static int papr_scm_pmu_event_init(struct perf_event *event)
+{
+	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);
+	struct papr_scm_priv *p;
+
+	if (!nd_pmu)
+		return -EINVAL;
+
+	/* test the event attr type for PMU enumeration */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* it does not support event sampling mode */
+	if (is_sampling_event(event))
+		return -EOPNOTSUPP;
+
+	/* no branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	p = (struct papr_scm_priv *)nd_pmu->dev->driver_data;
+	if (!p)
+		return -EINVAL;
+
+	/* Invalid eventcode */
+	if (event->attr.config == 0 || event->attr.config > 16)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int papr_scm_pmu_add(struct perf_event *event, int flags)
+{
+	u64 count;
+	int rc;
+	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);
+
+	if (!nd_pmu)
+		return -EINVAL;
+
+	if (flags & PERF_EF_START) {
+		rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &count);
+		if (rc)
+			return rc;
+
+		local64_set(&event->hw.prev_count, count);
+	}
+
+	return 0;
+}
+
+static void papr_scm_pmu_read(struct perf_event *event)
+{
+	u64 prev, now;
+	int rc;
+	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);
+
+	if (!nd_pmu)
+		return;
+
+	rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &now);
+	if (rc)
+		return;
+
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
+}
+
+static void papr_scm_pmu_del(struct perf_event *event, int flags)
+{
+	papr_scm_pmu_read(event);
+}
+
+static void papr_scm_pmu_register(struct papr_scm_priv *p)
+{
+	struct nvdimm_pmu *nd_pmu;
+	int rc, nodeid;
+
+	nd_pmu = kzalloc(sizeof(*nd_pmu), GFP_KERNEL);
+	if (!nd_pmu) {
+		rc = -ENOMEM;
+		goto pmu_err_print;
+	}
+
+	if (!p->stat_buffer_len) {
+		rc = -ENOENT;
+		goto pmu_check_events_err;
+	}
+
+	nd_pmu->pmu.task_ctx_nr = perf_invalid_context;
+	nd_pmu->pmu.name = nvdimm_name(p->nvdimm);
+	nd_pmu->pmu.event_init = papr_scm_pmu_event_init;
+	nd_pmu->pmu.read = papr_scm_pmu_read;
+	nd_pmu->pmu.add = papr_scm_pmu_add;
+	nd_pmu->pmu.del = papr_scm_pmu_del;
+
+	nd_pmu->pmu.capabilities = PERF_PMU_CAP_NO_INTERRUPT |
+				PERF_PMU_CAP_NO_EXCLUDE;
+
+	/*updating the cpumask variable */
+	nodeid = numa_map_to_online_node(dev_to_node(&p->pdev->dev));
+	nd_pmu->arch_cpumask = *cpumask_of_node(nodeid);
+
+	rc = register_nvdimm_pmu(nd_pmu, p->pdev);
+	if (rc)
+		goto pmu_check_events_err;
+
+	/*
+	 * Set archdata.priv value to nvdimm_pmu structure, to handle the
+	 * unregistering of pmu device.
+	 */
+	p->pdev->archdata.priv = nd_pmu;
+	return;
+
+pmu_check_events_err:
+	kfree(nd_pmu);
+pmu_err_print:
+	dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc);
+}
+
+#else
+static void papr_scm_pmu_register(struct papr_scm_priv *p) { }
+#endif
+
 /*
  * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the
  * health information.
@@ -347,19 +498,29 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
 static int __drc_pmem_query_health(struct papr_scm_priv *p)
 {
 	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	u64 bitmap = 0;
 	long rc;
 
 	/* issue the hcall */
 	rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index);
-	if (rc != H_SUCCESS) {
+	if (rc == H_SUCCESS)
+		bitmap = ret[0] & ret[1];
+	else if (rc == H_FUNCTION)
+		dev_info_once(&p->pdev->dev,
+			      "Hcall H_SCM_HEALTH not implemented, assuming empty health bitmap");
+	else {
+
 		dev_err(&p->pdev->dev,
 			"Failed to query health information, Err:%ld\n", rc);
 		return -ENXIO;
 	}
 
 	p->lasthealth_jiffies = jiffies;
-	p->health_bitmap = ret[0] & ret[1];
-
+	/* Allow injecting specific health bits via inject mask. */
+	if (p->health_bitmap_inject_mask)
+		bitmap = (bitmap & ~p->health_bitmap_inject_mask) |
+			p->health_bitmap_inject_mask;
+	WRITE_ONCE(p->health_bitmap, bitmap);
 	dev_dbg(&p->pdev->dev,
 		"Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n",
 		ret[0], ret[1]);
@@ -383,7 +544,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p)
 
 	/* Jiffies offset for which the health data is assumed to be same */
 	cache_timeout = p->lasthealth_jiffies +
-		msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);
+		secs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL);
 
 	/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
 	if (time_after(jiffies, cache_timeout))
@@ -669,6 +830,56 @@ out:
 	return rc;
 }
 
+/* Inject a smart error Add the dirty-shutdown-counter value to the pdsm */
+static int papr_pdsm_smart_inject(struct papr_scm_priv *p,
+				  union nd_pdsm_payload *payload)
+{
+	int rc;
+	u32 supported_flags = 0;
+	u64 inject_mask = 0, clear_mask = 0;
+	u64 mask;
+
+	/* Check for individual smart error flags and update inject/clear masks */
+	if (payload->smart_inject.flags & PDSM_SMART_INJECT_HEALTH_FATAL) {
+		supported_flags |= PDSM_SMART_INJECT_HEALTH_FATAL;
+		if (payload->smart_inject.fatal_enable)
+			inject_mask |= PAPR_PMEM_HEALTH_FATAL;
+		else
+			clear_mask |= PAPR_PMEM_HEALTH_FATAL;
+	}
+
+	if (payload->smart_inject.flags & PDSM_SMART_INJECT_BAD_SHUTDOWN) {
+		supported_flags |= PDSM_SMART_INJECT_BAD_SHUTDOWN;
+		if (payload->smart_inject.unsafe_shutdown_enable)
+			inject_mask |= PAPR_PMEM_SHUTDOWN_DIRTY;
+		else
+			clear_mask |= PAPR_PMEM_SHUTDOWN_DIRTY;
+	}
+
+	dev_dbg(&p->pdev->dev, "[Smart-inject] inject_mask=%#llx clear_mask=%#llx\n",
+		inject_mask, clear_mask);
+
+	/* Prevent concurrent access to dimm health bitmap related members */
+	rc = mutex_lock_interruptible(&p->health_mutex);
+	if (rc)
+		return rc;
+
+	/* Use inject/clear masks to set health_bitmap_inject_mask */
+	mask = READ_ONCE(p->health_bitmap_inject_mask);
+	mask = (mask & ~clear_mask) | inject_mask;
+	WRITE_ONCE(p->health_bitmap_inject_mask, mask);
+
+	/* Invalidate cached health bitmap */
+	p->lasthealth_jiffies = 0;
+
+	mutex_unlock(&p->health_mutex);
+
+	/* Return the supported flags back to userspace */
+	payload->smart_inject.flags = supported_flags;
+
+	return sizeof(struct nd_papr_pdsm_health);
+}
+
 /*
  * 'struct pdsm_cmd_desc'
  * Identifies supported PDSMs' expected length of in/out payloads
@@ -702,6 +913,12 @@ static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = {
 		.size_out = sizeof(struct nd_papr_pdsm_health),
 		.service = papr_pdsm_health,
 	},
+
+	[PAPR_PDSM_SMART_INJECT] = {
+		.size_in = sizeof(struct nd_papr_pdsm_smart_inject),
+		.size_out = sizeof(struct nd_papr_pdsm_smart_inject),
+		.service = papr_pdsm_smart_inject,
+	},
 	/* Empty */
 	[PAPR_PDSM_MAX] = {
 		.size_in = 0,
@@ -838,6 +1055,19 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
+static ssize_t health_bitmap_inject_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 sprintf(buf, "%#llx\n",
+		       READ_ONCE(p->health_bitmap_inject_mask));
+}
+
+static DEVICE_ATTR_ADMIN_RO(health_bitmap_inject);
+
 static ssize_t perf_stats_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -952,10 +1182,11 @@ static struct attribute *papr_nd_attributes[] = {
 	&dev_attr_flags.attr,
 	&dev_attr_perf_stats.attr,
 	&dev_attr_dirty_shutdown.attr,
+	&dev_attr_health_bitmap_inject.attr,
 	NULL,
 };
 
-static struct attribute_group papr_nd_attribute_group = {
+static const struct attribute_group papr_nd_attribute_group = {
 	.name = "papr",
 	.is_visible = papr_nd_attribute_visible,
 	.attrs = papr_nd_attributes,
@@ -1159,6 +1390,13 @@ static int papr_scm_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	/*
+	 * open firmware platform device create won't update the NUMA 
+	 * distance table. For PAPR SCM devices we use numa_map_to_online_node()
+	 * to find the nearest online NUMA node and that requires correct
+	 * distance table information.
+	 */
+	update_numa_distance(dn);
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
@@ -1236,6 +1474,7 @@ static int papr_scm_probe(struct platform_device *pdev)
 		goto err2;
 
 	platform_set_drvdata(pdev, p);
+	papr_scm_pmu_register(p);
 
 	return 0;
 
@@ -1244,7 +1483,7 @@ err:	kfree(p);
 	return rc;
 }
 
-static int papr_scm_remove(struct platform_device *pdev)
+static void papr_scm_remove(struct platform_device *pdev)
 {
 	struct papr_scm_priv *p = platform_get_drvdata(pdev);
 
@@ -1254,10 +1493,13 @@ static int papr_scm_remove(struct platform_device *pdev)
 
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
+
+	if (pdev->archdata.priv)
+		unregister_nvdimm_pmu(pdev->archdata.priv);
+
+	pdev->archdata.priv = NULL;
 	kfree(p->bus_desc.provider_name);
 	kfree(p);
-
-	return 0;
 }
 
 static const struct of_device_id papr_scm_match[] = {
@@ -1295,5 +1537,6 @@ static void __exit papr_scm_exit(void)
 module_exit(papr_scm_exit);
 
 MODULE_DEVICE_TABLE(of, papr_scm_match);
+MODULE_DESCRIPTION("PAPR Storage Class Memory interface driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("IBM Corporation");