1 files changed, 161 insertions, 35 deletions

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 96c53b23e58f..a5ac371a3f06 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/libnvdimm.h>
 #include <linux/platform_device.h>
+#include <linux/delay.h>
 
 #include <asm/plpar_wrappers.h>
 
@@ -28,6 +29,7 @@ struct papr_scm_priv {
 	uint64_t blocks;
 	uint64_t block_size;
 	int metadata_size;
+	bool is_volatile;
 
 	uint64_t bound_addr;
 
@@ -42,8 +44,9 @@ struct papr_scm_priv {
 static int drc_pmem_bind(struct papr_scm_priv *p)
 {
 	unsigned long ret[PLPAR_HCALL_BUFSIZE];
-	uint64_t rc, token;
 	uint64_t saved = 0;
+	uint64_t token;
+	int64_t rc;
 
 	/*
 	 * When the hypervisor cannot map all the requested memory in a single
@@ -63,6 +66,10 @@ static int drc_pmem_bind(struct papr_scm_priv *p)
 	} while (rc == H_BUSY);
 
 	if (rc) {
+		/* H_OVERLAP needs a separate error path */
+		if (rc == H_OVERLAP)
+			return -EBUSY;
+
 		dev_err(&p->pdev->dev, "bind err: %lld\n", rc);
 		return -ENXIO;
 	}
@@ -77,61 +84,135 @@ static int drc_pmem_bind(struct papr_scm_priv *p)
 static int drc_pmem_unbind(struct papr_scm_priv *p)
 {
 	unsigned long ret[PLPAR_HCALL_BUFSIZE];
-	uint64_t rc, token;
+	uint64_t token = 0;
+	int64_t rc;
 
-	token = 0;
+	dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index);
 
-	/* NB: unbind has the same retry requirements mentioned above */
+	/* NB: unbind has the same retry requirements as drc_pmem_bind() */
 	do {
-		rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index,
-				p->bound_addr, p->blocks, token);
+
+		/* Unbind of all SCM resources associated with drcIndex */
+		rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC,
+				 p->drc_index, token);
 		token = ret[0];
-		cond_resched();
+
+		/* Check if we are stalled for some time */
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		} else if (rc == H_BUSY) {
+			cond_resched();
+		}
+
 	} while (rc == H_BUSY);
 
 	if (rc)
 		dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
+	else
+		dev_dbg(&p->pdev->dev, "unbind drc %x complete\n",
+			p->drc_index);
 
-	return !!rc;
+	return rc == H_SUCCESS ? 0 : -ENXIO;
 }
 
 static int papr_scm_meta_get(struct papr_scm_priv *p,
-			struct nd_cmd_get_config_data_hdr *hdr)
+			     struct nd_cmd_get_config_data_hdr *hdr)
 {
 	unsigned long data[PLPAR_HCALL_BUFSIZE];
+	unsigned long offset, data_offset;
+	int len, read;
 	int64_t ret;
 
-	if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
 		return -EINVAL;
 
-	ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
-			hdr->in_offset, 1);
-
-	if (ret == H_PARAMETER) /* bad DRC index */
-		return -ENODEV;
-	if (ret)
-		return -EINVAL; /* other invalid parameter */
-
-	hdr->out_buf[0] = data[0] & 0xff;
-
+	for (len = hdr->in_length; len; len -= read) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8)
+			read = 8;
+		else if (len >= 4)
+			read = 4;
+		else if (len >= 2)
+			read = 2;
+		else
+			read = 1;
+
+		ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
+				  offset, read);
+
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+
+		switch (read) {
+		case 8:
+			*(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
+			break;
+		case 4:
+			*(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
+			break;
+
+		case 2:
+			*(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
+			break;
+
+		case 1:
+			*(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
+			break;
+		}
+	}
 	return 0;
 }
 
 static int papr_scm_meta_set(struct papr_scm_priv *p,
-			struct nd_cmd_set_config_hdr *hdr)
+			     struct nd_cmd_set_config_hdr *hdr)
 {
+	unsigned long offset, data_offset;
+	int len, wrote;
+	unsigned long data;
+	__be64 data_be;
 	int64_t ret;
 
-	if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
 		return -EINVAL;
 
-	ret = plpar_hcall_norets(H_SCM_WRITE_METADATA,
-			p->drc_index, hdr->in_offset, hdr->in_buf[0], 1);
-
-	if (ret == H_PARAMETER) /* bad DRC index */
-		return -ENODEV;
-	if (ret)
-		return -EINVAL; /* other invalid parameter */
+	for (len = hdr->in_length; len; len -= wrote) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8) {
+			data = *(uint64_t *)(hdr->in_buf + data_offset);
+			data_be = cpu_to_be64(data);
+			wrote = 8;
+		} else if (len >= 4) {
+			data = *(uint32_t *)(hdr->in_buf + data_offset);
+			data &= 0xffffffff;
+			data_be = cpu_to_be32(data);
+			wrote = 4;
+		} else if (len >= 2) {
+			data = *(uint16_t *)(hdr->in_buf + data_offset);
+			data &= 0xffff;
+			data_be = cpu_to_be16(data);
+			wrote = 2;
+		} else {
+			data_be = *(uint8_t *)(hdr->in_buf + data_offset);
+			data_be &= 0xff;
+			wrote = 1;
+		}
+
+		ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
+					 offset, data_be, wrote);
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+	}
 
 	return 0;
 }
@@ -153,7 +234,7 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		get_size_hdr = buf;
 
 		get_size_hdr->status = 0;
-		get_size_hdr->max_xfer = 1;
+		get_size_hdr->max_xfer = 8;
 		get_size_hdr->config_size = p->metadata_size;
 		*cmd_rc = 0;
 		break;
@@ -194,12 +275,32 @@ static const struct attribute_group *papr_scm_dimm_groups[] = {
 	NULL,
 };
 
+static inline int papr_scm_node(int node)
+{
+	int min_dist = INT_MAX, dist;
+	int nid, min_node;
+
+	if ((node == NUMA_NO_NODE) || node_online(node))
+		return node;
+
+	min_node = first_online_node;
+	for_each_online_node(nid) {
+		dist = node_distance(node, nid);
+		if (dist < min_dist) {
+			min_dist = dist;
+			min_node = nid;
+		}
+	}
+	return min_node;
+}
+
 static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 {
 	struct device *dev = &p->pdev->dev;
 	struct nd_mapping_desc mapping;
 	struct nd_region_desc ndr_desc;
 	unsigned long dimm_flags;
+	int target_nid, online_nid;
 
 	p->bus_desc.ndctl = papr_scm_ndctl;
 	p->bus_desc.module = THIS_MODULE;
@@ -238,8 +339,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	ndr_desc.attr_groups = region_attr_groups;
-	ndr_desc.numa_node = dev_to_node(&p->pdev->dev);
-	ndr_desc.target_node = ndr_desc.numa_node;
+	target_nid = dev_to_node(&p->pdev->dev);
+	online_nid = papr_scm_node(target_nid);
+	ndr_desc.numa_node = online_nid;
+	ndr_desc.target_node = target_nid;
 	ndr_desc.res = &p->res;
 	ndr_desc.of_node = p->dn;
 	ndr_desc.provider_data = p;
@@ -248,12 +351,18 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	ndr_desc.nd_set = &p->nd_set;
 	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 
-	p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
+	if (p->is_volatile)
+		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
+	else
+		p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
 	if (!p->region) {
 		dev_err(dev, "Error registering region %pR from %pOF\n",
 				ndr_desc.res, p->dn);
 		goto err;
 	}
+	if (target_nid != online_nid)
+		dev_info(dev, "Region registered with target node %d and online node %d",
+			 target_nid, online_nid);
 
 	return 0;
 
@@ -293,6 +402,7 @@ static int papr_scm_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
@@ -304,11 +414,19 @@ static int papr_scm_probe(struct platform_device *pdev)
 	p->drc_index = drc_index;
 	p->block_size = block_size;
 	p->blocks = blocks;
+	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
 
 	/* We just need to ensure that set cookies are unique across */
 	uuid_parse(uuid_str, (uuid_t *) uuid);
-	p->nd_set.cookie1 = uuid[0];
-	p->nd_set.cookie2 = uuid[1];
+	/*
+	 * cookie1 and cookie2 are not really little endian
+	 * we store a little endian representation of the
+	 * uuid str so that we can compare this with the label
+	 * area cookie irrespective of the endian config with which
+	 * the kernel is built.
+	 */
+	p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
+	p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
 
 	/* might be zero */
 	p->metadata_size = metadata_size;
@@ -316,6 +434,14 @@ static int papr_scm_probe(struct platform_device *pdev)
 
 	/* request the hypervisor to bind this region to somewhere in memory */
 	rc = drc_pmem_bind(p);
+
+	/* If phyp says drc memory still bound then force unbound and retry */
+	if (rc == -EBUSY) {
+		dev_warn(&pdev->dev, "Retrying bind after unbinding\n");
+		drc_pmem_unbind(p);
+		rc = drc_pmem_bind(p);
+	}
+
 	if (rc)
 		goto err;