Merge branch 'next-dlpar' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc into next

Merge series from Nathan Fontenot to do memory hotplug in the kernel.

3 files changed, 601 insertions, 2 deletions

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index c22bb1b4beb8..b4b11096ea8b 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -10,6 +10,8 @@
  * 2 as published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt)	"dlpar: " fmt
+
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
@@ -535,13 +537,125 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 	return count;
 }
 
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
+static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+{
+	int rc;
+
+	/* pseries error logs are in BE format, convert to cpu type */
+	switch (hp_elog->id_type) {
+	case PSERIES_HP_ELOG_ID_DRC_COUNT:
+		hp_elog->_drc_u.drc_count =
+					be32_to_cpu(hp_elog->_drc_u.drc_count);
+		break;
+	case PSERIES_HP_ELOG_ID_DRC_INDEX:
+		hp_elog->_drc_u.drc_index =
+					be32_to_cpu(hp_elog->_drc_u.drc_index);
+	}
+
+	switch (hp_elog->resource) {
+	case PSERIES_HP_ELOG_RESOURCE_MEM:
+		rc = dlpar_memory(hp_elog);
+		break;
+	default:
+		pr_warn_ratelimited("Invalid resource (%d) specified\n",
+				    hp_elog->resource);
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct pseries_hp_errorlog *hp_elog;
+	const char *arg;
+	int rc;
+
+	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
+	if (!hp_elog) {
+		rc = -ENOMEM;
+		goto dlpar_store_out;
+	}
+
+	/* Parse out the request from the user, this will be in the form
+	 * <resource> <action> <id_type> <id>
+	 */
+	arg = buf;
+	if (!strncmp(arg, "memory", 6)) {
+		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
+		arg += strlen("memory ");
+	} else {
+		pr_err("Invalid resource specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	if (!strncmp(arg, "add", 3)) {
+		hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD;
+		arg += strlen("add ");
+	} else if (!strncmp(arg, "remove", 6)) {
+		hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE;
+		arg += strlen("remove ");
+	} else {
+		pr_err("Invalid action specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	if (!strncmp(arg, "index", 5)) {
+		u32 index;
+
+		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
+		arg += strlen("index ");
+		if (kstrtou32(arg, 0, &index)) {
+			rc = -EINVAL;
+			pr_err("Invalid drc_index specified: \"%s\"\n", buf);
+			goto dlpar_store_out;
+		}
+
+		hp_elog->_drc_u.drc_index = cpu_to_be32(index);
+	} else if (!strncmp(arg, "count", 5)) {
+		u32 count;
+
+		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT;
+		arg += strlen("count ");
+		if (kstrtou32(arg, 0, &count)) {
+			rc = -EINVAL;
+			pr_err("Invalid count specified: \"%s\"\n", buf);
+			goto dlpar_store_out;
+		}
+
+		hp_elog->_drc_u.drc_count = cpu_to_be32(count);
+	} else {
+		pr_err("Invalid id_type specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	rc = handle_dlpar_errorlog(hp_elog);
+
+dlpar_store_out:
+	kfree(hp_elog);
+	return rc ? rc : count;
+}
+
+static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store);
+
 static int __init pseries_dlpar_init(void)
 {
+	int rc;
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 	ppc_md.cpu_probe = dlpar_cpu_probe;
 	ppc_md.cpu_release = dlpar_cpu_release;
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
-	return 0;
+	rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
+
+	return rc;
 }
 machine_device_initcall(pseries, pseries_dlpar_init);
 
-#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index fa41f0da5b6f..742ef88ffd7b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -9,11 +9,14 @@
  *      2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt)	"pseries-hotplug-mem: " fmt
+
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/slab.h>
 
 #include <asm/firmware.h>
 #include <asm/machdep.h>
@@ -21,6 +24,8 @@
 #include <asm/sparsemem.h>
 #include "pseries.h"
 
+static bool rtas_hp_event;
+
 unsigned long pseries_memory_block_size(void)
 {
 	struct device_node *np;
@@ -64,6 +69,67 @@ unsigned long pseries_memory_block_size(void)
 	return memblock_size;
 }
 
+static void dlpar_free_drconf_property(struct property *prop)
+{
+	kfree(prop->name);
+	kfree(prop->value);
+	kfree(prop);
+}
+
+static struct property *dlpar_clone_drconf_property(struct device_node *dn)
+{
+	struct property *prop, *new_prop;
+	struct of_drconf_cell *lmbs;
+	u32 num_lmbs, *p;
+	int i;
+
+	prop = of_find_property(dn, "ibm,dynamic-memory", NULL);
+	if (!prop)
+		return NULL;
+
+	new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL);
+	if (!new_prop)
+		return NULL;
+
+	new_prop->name = kstrdup(prop->name, GFP_KERNEL);
+	new_prop->value = kmalloc(prop->length, GFP_KERNEL);
+	if (!new_prop->name || !new_prop->value) {
+		dlpar_free_drconf_property(new_prop);
+		return NULL;
+	}
+
+	memcpy(new_prop->value, prop->value, prop->length);
+	new_prop->length = prop->length;
+
+	/* Convert the property to cpu endian-ness */
+	p = new_prop->value;
+	*p = be32_to_cpu(*p);
+
+	num_lmbs = *p++;
+	lmbs = (struct of_drconf_cell *)p;
+
+	for (i = 0; i < num_lmbs; i++) {
+		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
+		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
+	}
+
+	return new_prop;
+}
+
+static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
+{
+	unsigned long section_nr;
+	struct mem_section *mem_sect;
+	struct memory_block *mem_block;
+
+	section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
+	mem_sect = __nr_to_section(section_nr);
+
+	mem_block = find_memory_block(mem_sect);
+	return mem_block;
+}
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
@@ -122,6 +188,173 @@ static int pseries_remove_mem_node(struct device_node *np)
 	pseries_remove_memblock(base, lmb_size);
 	return 0;
 }
+
+static bool lmb_is_removable(struct of_drconf_cell *lmb)
+{
+	int i, scns_per_block;
+	int rc = 1;
+	unsigned long pfn, block_sz;
+	u64 phys_addr;
+
+	if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
+		return false;
+
+	block_sz = memory_block_size_bytes();
+	scns_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+	phys_addr = lmb->base_addr;
+
+	for (i = 0; i < scns_per_block; i++) {
+		pfn = PFN_DOWN(phys_addr);
+		if (!pfn_present(pfn))
+			continue;
+
+		rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+		phys_addr += MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return rc ? true : false;
+}
+
+static int dlpar_add_lmb(struct of_drconf_cell *);
+
+static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
+{
+	struct memory_block *mem_block;
+	unsigned long block_sz;
+	int nid, rc;
+
+	if (!lmb_is_removable(lmb))
+		return -EINVAL;
+
+	mem_block = lmb_to_memblock(lmb);
+	if (!mem_block)
+		return -EINVAL;
+
+	rc = device_offline(&mem_block->dev);
+	put_device(&mem_block->dev);
+	if (rc)
+		return rc;
+
+	block_sz = pseries_memory_block_size();
+	nid = memory_add_physaddr_to_nid(lmb->base_addr);
+
+	remove_memory(nid, lmb->base_addr, block_sz);
+
+	/* Update memory regions for memory remove */
+	memblock_remove(lmb->base_addr, block_sz);
+
+	dlpar_release_drc(lmb->drc_index);
+
+	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
+	return 0;
+}
+
+static int dlpar_memory_remove_by_count(u32 lmbs_to_remove,
+					struct property *prop)
+{
+	struct of_drconf_cell *lmbs;
+	int lmbs_removed = 0;
+	int lmbs_available = 0;
+	u32 num_lmbs, *p;
+	int i, rc;
+
+	pr_info("Attempting to hot-remove %d LMB(s)\n", lmbs_to_remove);
+
+	if (lmbs_to_remove == 0)
+		return -EINVAL;
+
+	p = prop->value;
+	num_lmbs = *p++;
+	lmbs = (struct of_drconf_cell *)p;
+
+	/* Validate that there are enough LMBs to satisfy the request */
+	for (i = 0; i < num_lmbs; i++) {
+		if (lmbs[i].flags & DRCONF_MEM_ASSIGNED)
+			lmbs_available++;
+	}
+
+	if (lmbs_available < lmbs_to_remove)
+		return -EINVAL;
+
+	for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) {
+		rc = dlpar_remove_lmb(&lmbs[i]);
+		if (rc)
+			continue;
+
+		lmbs_removed++;
+
+		/* Mark this lmb so we can add it later if all of the
+		 * requested LMBs cannot be removed.
+		 */
+		lmbs[i].reserved = 1;
+	}
+
+	if (lmbs_removed != lmbs_to_remove) {
+		pr_err("Memory hot-remove failed, adding LMB's back\n");
+
+		for (i = 0; i < num_lmbs; i++) {
+			if (!lmbs[i].reserved)
+				continue;
+
+			rc = dlpar_add_lmb(&lmbs[i]);
+			if (rc)
+				pr_err("Failed to add LMB back, drc index %x\n",
+				       lmbs[i].drc_index);
+
+			lmbs[i].reserved = 0;
+		}
+
+		rc = -EINVAL;
+	} else {
+		for (i = 0; i < num_lmbs; i++) {
+			if (!lmbs[i].reserved)
+				continue;
+
+			pr_info("Memory at %llx was hot-removed\n",
+				lmbs[i].base_addr);
+
+			lmbs[i].reserved = 0;
+		}
+		rc = 0;
+	}
+
+	return rc;
+}
+
+static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop)
+{
+	struct of_drconf_cell *lmbs;
+	u32 num_lmbs, *p;
+	int lmb_found;
+	int i, rc;
+
+	pr_info("Attempting to hot-remove LMB, drc index %x\n", drc_index);
+
+	p = prop->value;
+	num_lmbs = *p++;
+	lmbs = (struct of_drconf_cell *)p;
+
+	lmb_found = 0;
+	for (i = 0; i < num_lmbs; i++) {
+		if (lmbs[i].drc_index == drc_index) {
+			lmb_found = 1;
+			rc = dlpar_remove_lmb(&lmbs[i]);
+			break;
+		}
+	}
+
+	if (!lmb_found)
+		rc = -EINVAL;
+
+	if (rc)
+		pr_info("Failed to hot-remove memory at %llx\n",
+			lmbs[i].base_addr);
+	else
+		pr_info("Memory at %llx was hot-removed\n", lmbs[i].base_addr);
+
+	return rc;
+}
+
 #else
 static inline int pseries_remove_memblock(unsigned long base,
 					  unsigned int memblock_size)
@@ -132,8 +365,245 @@ static inline int pseries_remove_mem_node(struct device_node *np)
 {
 	return 0;
 }
+static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
+static int dlpar_add_lmb(struct of_drconf_cell *lmb)
+{
+	struct memory_block *mem_block;
+	unsigned long block_sz;
+	int nid, rc;
+
+	if (lmb->flags & DRCONF_MEM_ASSIGNED)
+		return -EINVAL;
+
+	block_sz = memory_block_size_bytes();
+
+	rc = dlpar_acquire_drc(lmb->drc_index);
+	if (rc)
+		return rc;
+
+	/* Find the node id for this address */
+	nid = memory_add_physaddr_to_nid(lmb->base_addr);
+
+	/* Add the memory */
+	rc = add_memory(nid, lmb->base_addr, block_sz);
+	if (rc) {
+		dlpar_release_drc(lmb->drc_index);
+		return rc;
+	}
+
+	/* Register this block of memory */
+	rc = memblock_add(lmb->base_addr, block_sz);
+	if (rc) {
+		remove_memory(nid, lmb->base_addr, block_sz);
+		dlpar_release_drc(lmb->drc_index);
+		return rc;
+	}
+
+	mem_block = lmb_to_memblock(lmb);
+	if (!mem_block) {
+		remove_memory(nid, lmb->base_addr, block_sz);
+		dlpar_release_drc(lmb->drc_index);
+		return -EINVAL;
+	}
+
+	rc = device_online(&mem_block->dev);
+	put_device(&mem_block->dev);
+	if (rc) {
+		remove_memory(nid, lmb->base_addr, block_sz);
+		dlpar_release_drc(lmb->drc_index);
+		return rc;
+	}
+
+	lmb->flags |= DRCONF_MEM_ASSIGNED;
+	return 0;
+}
+
+static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop)
+{
+	struct of_drconf_cell *lmbs;
+	u32 num_lmbs, *p;
+	int lmbs_available = 0;
+	int lmbs_added = 0;
+	int i, rc;
+
+	pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add);
+
+	if (lmbs_to_add == 0)
+		return -EINVAL;
+
+	p = prop->value;
+	num_lmbs = *p++;
+	lmbs = (struct of_drconf_cell *)p;
+
+	/* Validate that there are enough LMBs to satisfy the request */
+	for (i = 0; i < num_lmbs; i++) {
+		if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED))
+			lmbs_available++;
+	}
+
+	if (lmbs_available < lmbs_to_add)
+		return -EINVAL;
+
+	for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) {
+		rc = dlpar_add_lmb(&lmbs[i]);
+		if (rc)
+			continue;
+
+		lmbs_added++;
+
+		/* Mark this lmb so we can remove it later if all of the
+		 * requested LMBs cannot be added.
+		 */
+		lmbs[i].reserved = 1;
+	}
+
+	if (lmbs_added != lmbs_to_add) {
+		pr_err("Memory hot-add failed, removing any added LMBs\n");
+
+		for (i = 0; i < num_lmbs; i++) {
+			if (!lmbs[i].reserved)
+				continue;
+
+			rc = dlpar_remove_lmb(&lmbs[i]);
+			if (rc)
+				pr_err("Failed to remove LMB, drc index %x\n",
+				       be32_to_cpu(lmbs[i].drc_index));
+		}
+		rc = -EINVAL;
+	} else {
+		for (i = 0; i < num_lmbs; i++) {
+			if (!lmbs[i].reserved)
+				continue;
+
+			pr_info("Memory at %llx (drc index %x) was hot-added\n",
+				lmbs[i].base_addr, lmbs[i].drc_index);
+			lmbs[i].reserved = 0;
+		}
+	}
+
+	return rc;
+}
+
+static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop)
+{
+	struct of_drconf_cell *lmbs;
+	u32 num_lmbs, *p;
+	int i, lmb_found;
+	int rc;
+
+	pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index);
+
+	p = prop->value;
+	num_lmbs = *p++;
+	lmbs = (struct of_drconf_cell *)p;
+
+	lmb_found = 0;
+	for (i = 0; i < num_lmbs; i++) {
+		if (lmbs[i].drc_index == drc_index) {
+			lmb_found = 1;
+			rc = dlpar_add_lmb(&lmbs[i]);
+			break;
+		}
+	}
+
+	if (!lmb_found)
+		rc = -EINVAL;
+
+	if (rc)
+		pr_info("Failed to hot-add memory, drc index %x\n", drc_index);
+	else
+		pr_info("Memory at %llx (drc index %x) was hot-added\n",
+			lmbs[i].base_addr, drc_index);
+
+	return rc;
+}
+
+static void dlpar_update_drconf_property(struct device_node *dn,
+					 struct property *prop)
+{
+	struct of_drconf_cell *lmbs;
+	u32 num_lmbs, *p;
+	int i;
+
+	/* Convert the property back to BE */
+	p = prop->value;
+	num_lmbs = *p;
+	*p = cpu_to_be32(*p);
+	p++;
+
+	lmbs = (struct of_drconf_cell *)p;
+	for (i = 0; i < num_lmbs; i++) {
+		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
+		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
+	}
+
+	rtas_hp_event = true;
+	of_update_property(dn, prop);
+	rtas_hp_event = false;
+}
+
+int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
+{
+	struct device_node *dn;
+	struct property *prop;
+	u32 count, drc_index;
+	int rc;
+
+	count = hp_elog->_drc_u.drc_count;
+	drc_index = hp_elog->_drc_u.drc_index;
+
+	lock_device_hotplug();
+
+	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (!dn)
+		return -EINVAL;
+
+	prop = dlpar_clone_drconf_property(dn);
+	if (!prop) {
+		of_node_put(dn);
+		return -EINVAL;
+	}
+
+	switch (hp_elog->action) {
+	case PSERIES_HP_ELOG_ACTION_ADD:
+		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT)
+			rc = dlpar_memory_add_by_count(count, prop);
+		else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX)
+			rc = dlpar_memory_add_by_index(drc_index, prop);
+		else
+			rc = -EINVAL;
+		break;
+	case PSERIES_HP_ELOG_ACTION_REMOVE:
+		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT)
+			rc = dlpar_memory_remove_by_count(count, prop);
+		else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX)
+			rc = dlpar_memory_remove_by_index(drc_index, prop);
+		else
+			rc = -EINVAL;
+		break;
+	default:
+		pr_err("Invalid action (%d) specified\n", hp_elog->action);
+		rc = -EINVAL;
+		break;
+	}
+
+	if (rc)
+		dlpar_free_drconf_property(prop);
+	else
+		dlpar_update_drconf_property(dn, prop);
+
+	of_node_put(dn);
+	unlock_device_hotplug();
+	return rc;
+}
+
 static int pseries_add_mem_node(struct device_node *np)
 {
 	const char *type;
@@ -174,6 +644,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
 	__be32 *p;
 	int i, rc = -EINVAL;
 
+	if (rtas_hp_event)
+		return 0;
+
 	memblock_size = pseries_memory_block_size();
 	if (!memblock_size)
 		return -EINVAL;
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index cd64672e24f8..8411c27293e4 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -11,6 +11,7 @@
 #define _PSERIES_PSERIES_H
 
 #include <linux/interrupt.h>
+#include <asm/rtas.h>
 
 struct device_node;
 
@@ -60,6 +61,17 @@ extern struct device_node *dlpar_configure_connector(__be32,
 						struct device_node *);
 extern int dlpar_attach_node(struct device_node *);
 extern int dlpar_detach_node(struct device_node *);
+extern int dlpar_acquire_drc(u32 drc_index);
+extern int dlpar_release_drc(u32 drc_index);
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int dlpar_memory(struct pseries_hp_errorlog *hp_elog);
+#else
+static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
+{
+	return -EOPNOTSUPP;
+}
+#endif
 
 /* PCI root bridge prepare function override for pseries */
 struct pci_host_bridge;