6 files changed, 266 insertions, 11 deletions

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index c66637392bbc..b5b8ba512b28 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_FW_LOADER)	+= firmware_class.o
 obj-$(CONFIG_NUMA)      += node.o
 obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
 obj-$(CONFIG_SMP)       += topology.o
+obj-$(CONFIG_IOMMU_API) += iommu.o
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_MODULES)   += module.o
 endif
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 64f5d54f7edc..719ee5c1c8d9 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -109,7 +109,7 @@ static SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL);
  */
 static ssize_t print_cpus_map(char *buf, cpumask_t *map)
 {
-        int n = cpulist_scnprintf(buf, PAGE_SIZE-2, *map);
+        int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map);
 
         buf[n++] = '\n';
         buf[n] = '\0';
@@ -128,10 +128,54 @@ print_cpus_func(online);
 print_cpus_func(possible);
 print_cpus_func(present);
 
+/*
+ * Print values for NR_CPUS and offlined cpus
+ */
+static ssize_t print_cpus_kernel_max(struct sysdev_class *class, char *buf)
+{
+        int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1);
+        return n;
+}
+static SYSDEV_CLASS_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL);
+
+/* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */
+unsigned int total_cpus;
+
+static ssize_t print_cpus_offline(struct sysdev_class *class, char *buf)
+{
+        int n = 0, len = PAGE_SIZE-2;
+        cpumask_var_t offline;
+
+        /* display offline cpus < nr_cpu_ids */
+        if (!alloc_cpumask_var(&offline, GFP_KERNEL))
+                return -ENOMEM;
+        cpumask_complement(offline, cpu_online_mask);
+        n = cpulist_scnprintf(buf, len, offline);
+        free_cpumask_var(offline);
+
+        /* display offline cpus >= nr_cpu_ids */
+        if (total_cpus && nr_cpu_ids < total_cpus) {
+                if (n && n < len)
+                        buf[n++] = ',';
+
+                if (nr_cpu_ids == total_cpus-1)
+                        n += snprintf(&buf[n], len - n, "%d", nr_cpu_ids);
+                else
+                        n += snprintf(&buf[n], len - n, "%d-%d",
+                                                      nr_cpu_ids, total_cpus-1);
+        }
+
+        n += snprintf(&buf[n], len - n, "\n");
+        return n;
+}
+static SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL);
+
 static struct sysdev_class_attribute *cpu_state_attr[] = {
         &attr_online_map,
         &attr_possible_map,
         &attr_present_map,
+        &attr_kernel_max,
+        &attr_offline,
 };
 
 static int cpu_states_init(void)
diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c
new file mode 100644
index 000000000000..5e039d4f877c
--- /dev/null
+++ b/drivers/base/iommu.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/iommu.h>
+
+static struct iommu_ops *iommu_ops;
+
+void register_iommu(struct iommu_ops *ops)
+{
+        if (iommu_ops)
+                BUG();
+
+        iommu_ops = ops;
+}
+
+bool iommu_found()
+{
+        return iommu_ops != NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_found);
+
+struct iommu_domain *iommu_domain_alloc(void)
+{
+        struct iommu_domain *domain;
+        int ret;
+
+        domain = kmalloc(sizeof(*domain), GFP_KERNEL);
+        if (!domain)
+                return NULL;
+
+        ret = iommu_ops->domain_init(domain);
+        if (ret)
+                goto out_free;
+
+        return domain;
+
+out_free:
+        kfree(domain);
+
+        return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_domain_alloc);
+
+void iommu_domain_free(struct iommu_domain *domain)
+{
+        iommu_ops->domain_destroy(domain);
+        kfree(domain);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_free);
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+        return iommu_ops->attach_dev(domain, dev);
+}
+EXPORT_SYMBOL_GPL(iommu_attach_device);
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+        iommu_ops->detach_dev(domain, dev);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_device);
+
+int iommu_map_range(struct iommu_domain *domain, unsigned long iova,
+                    phys_addr_t paddr, size_t size, int prot)
+{
+        return iommu_ops->map(domain, iova, paddr, size, prot);
+}
+EXPORT_SYMBOL_GPL(iommu_map_range);
+
+void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
+                      size_t size)
+{
+        iommu_ops->unmap(domain, iova, size);
+}
+EXPORT_SYMBOL_GPL(iommu_unmap_range);
+
+phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
+                               unsigned long iova)
+{
+        return iommu_ops->iova_to_phys(domain, iova);
+}
+EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 5260e9e0df48..989429cfed88 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -347,8 +347,9 @@ static inline int memory_probe_init(void)
  * section belongs to...
  */
 
-static int add_memory_block(unsigned long node_id, struct mem_section *section,
-                     unsigned long state, int phys_device)
+static int add_memory_block(int nid, struct mem_section *section,
+                        unsigned long state, int phys_device,
+                        enum mem_add_context context)
 {
         struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
         int ret = 0;
@@ -370,6 +371,10 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section,
                 ret = mem_create_simple_file(mem, phys_device);
         if (!ret)
                 ret = mem_create_simple_file(mem, removable);
+        if (!ret) {
+                if (context == HOTPLUG)
+                        ret = register_mem_sect_under_node(mem, nid);
+        }
 
         return ret;
 }
@@ -382,7 +387,7 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section,
  *
  * This could be made generic for all sysdev classes.
  */
-static struct memory_block *find_memory_block(struct mem_section *section)
+struct memory_block *find_memory_block(struct mem_section *section)
 {
         struct kobject *kobj;
         struct sys_device *sysdev;
@@ -411,6 +416,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
         struct memory_block *mem;
 
         mem = find_memory_block(section);
+        unregister_mem_sect_under_nodes(mem);
         mem_remove_simple_file(mem, phys_index);
         mem_remove_simple_file(mem, state);
         mem_remove_simple_file(mem, phys_device);
@@ -424,9 +430,9 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
  */
-int register_new_memory(struct mem_section *section)
+int register_new_memory(int nid, struct mem_section *section)
 {
-        return add_memory_block(0, section, MEM_OFFLINE, 0);
+        return add_memory_block(nid, section, MEM_OFFLINE, 0, HOTPLUG);
 }
 
 int unregister_memory_section(struct mem_section *section)
@@ -458,7 +464,8 @@ int __init memory_dev_init(void)
         for (i = 0; i < NR_MEM_SECTIONS; i++) {
                 if (!present_section_nr(i))
                         continue;
-                err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0);
+                err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
+                                        0, BOOT);
                 if (!ret)
                         ret = err;
         }
diff --git a/drivers/base/node.c b/drivers/base/node.c
index f5207090885a..43fa90b837ee 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/memory.h>
 #include <linux/node.h>
 #include <linux/hugetlb.h>
 #include <linux/cpumask.h>
@@ -30,8 +31,8 @@ static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
         BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
 
         len = type?
-                cpulist_scnprintf(buf, PAGE_SIZE-2, *mask):
-                cpumask_scnprintf(buf, PAGE_SIZE-2, *mask);
+                cpulist_scnprintf(buf, PAGE_SIZE-2, mask) :
+                cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
         buf[len++] = '\n';
         buf[len] = '\0';
         return len;
@@ -248,6 +249,105 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
         return 0;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#define page_initialized(page)  (page->lru.next)
+
+static int get_nid_for_pfn(unsigned long pfn)
+{
+        struct page *page;
+
+        if (!pfn_valid_within(pfn))
+                return -1;
+        page = pfn_to_page(pfn);
+        if (!page_initialized(page))
+                return -1;
+        return pfn_to_nid(pfn);
+}
+
+/* register memory section under specified node if it spans that node */
+int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
+{
+        unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+        if (!mem_blk)
+                return -EFAULT;
+        if (!node_online(nid))
+                return 0;
+        sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+        sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+        for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+                int page_nid;
+
+                page_nid = get_nid_for_pfn(pfn);
+                if (page_nid < 0)
+                        continue;
+                if (page_nid != nid)
+                        continue;
+                return sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj,
+                                        &mem_blk->sysdev.kobj,
+                                        kobject_name(&mem_blk->sysdev.kobj));
+        }
+        /* mem section does not span the specified node */
+        return 0;
+}
+
+/* unregister memory section under all nodes that it spans */
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+{
+        nodemask_t unlinked_nodes;
+        unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+        if (!mem_blk)
+                return -EFAULT;
+        nodes_clear(unlinked_nodes);
+        sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+        sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+        for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+                unsigned int nid;
+
+                nid = get_nid_for_pfn(pfn);
+                if (nid < 0)
+                        continue;
+                if (!node_online(nid))
+                        continue;
+                if (node_test_and_set(nid, unlinked_nodes))
+                        continue;
+                sysfs_remove_link(&node_devices[nid].sysdev.kobj,
+                         kobject_name(&mem_blk->sysdev.kobj));
+        }
+        return 0;
+}
+
+static int link_mem_sections(int nid)
+{
+        unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
+        unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages;
+        unsigned long pfn;
+        int err = 0;
+
+        for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+                unsigned long section_nr = pfn_to_section_nr(pfn);
+                struct mem_section *mem_sect;
+                struct memory_block *mem_blk;
+                int ret;
+
+                if (!present_section_nr(section_nr))
+                        continue;
+                mem_sect = __nr_to_section(section_nr);
+                mem_blk = find_memory_block(mem_sect);
+                ret = register_mem_sect_under_node(mem_blk, nid);
+                if (!err)
+                        err = ret;
+
+                /* discard ref obtained in find_memory_block() */
+                kobject_put(&mem_blk->sysdev.kobj);
+        }
+        return err;
+}
+#else
+static int link_mem_sections(int nid) { return 0; }
+#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+
 int register_one_node(int nid)
 {
         int error = 0;
@@ -267,6 +367,9 @@ int register_one_node(int nid)
                         if (cpu_to_node(cpu) == nid)
                                 register_cpu_under_node(cpu, nid);
                 }
+
+                /* link memory sections under this node */
+                error = link_mem_sections(nid);
         }
 
         return error;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 199cd97e32e6..a8bc1cbcfa7c 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -49,8 +49,8 @@ static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
 
         if (len > 1) {
                 n = type?
-                        cpulist_scnprintf(buf, len-2, *mask):
-                        cpumask_scnprintf(buf, len-2, *mask);
+                        cpulist_scnprintf(buf, len-2, mask) :
+                        cpumask_scnprintf(buf, len-2, mask);
                 buf[n++] = '\n';
                 buf[n] = '\0';
         }