13 files changed, 201 insertions, 57 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 66e65ab3942..8f5b45615f7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -115,7 +115,8 @@ config SPARSEMEM_EXTREME
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
         bool "Allow for memory hot-add"
-        depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND
+        depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG
+        depends on (IA64 || X86 || PPC64)
 
 comment "Memory hotplug is currently incompatible with Software Suspend"
         depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND
@@ -145,3 +146,9 @@ config MIGRATION
           while the virtual addresses are not changed. This is useful for
           example on NUMA systems to put pages nearer to the processors accessing
           the page.
+
+config RESOURCES_64BIT
+        bool "64 bit Memory and IO resources (EXPERIMENTAL)" if (!64BIT && EXPERIMENTAL)
+        default 64BIT
+        help
+          This option allows memory and IO resources to be 64 bit.
diff --git a/mm/filemap.c b/mm/filemap.c
index 9c7334bafda..648f2c0c8e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2069,7 +2069,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 {
         struct file *file = iocb->ki_filp;
         struct address_space * mapping = file->f_mapping;
-        struct address_space_operations *a_ops = mapping->a_ops;
+        const struct address_space_operations *a_ops = mapping->a_ops;
         struct inode    *inode = mapping->host;
         long            status = 0;
         struct page     *page;
@@ -2095,14 +2095,21 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
         do {
                 unsigned long index;
                 unsigned long offset;
-                unsigned long maxlen;
                 size_t copied;
 
                 offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
                 index = pos >> PAGE_CACHE_SHIFT;
                 bytes = PAGE_CACHE_SIZE - offset;
-                if (bytes > count)
-                        bytes = count;
+
+                /* Limit the size of the copy to the caller's write size */
+                bytes = min(bytes, count);
+
+                /*
+                 * Limit the size of the copy to that of the current segment,
+                 * because fault_in_pages_readable() doesn't know how to walk
+                 * segments.
+                 */
+                bytes = min(bytes, cur_iov->iov_len - iov_base);
 
                 /*
                  * Bring in the user page that we will copy from _first_.
@@ -2110,10 +2117,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                  * same page as we're writing to, without it being marked
                  * up-to-date.
                  */
-                maxlen = cur_iov->iov_len - iov_base;
-                if (maxlen > bytes)
-                        maxlen = bytes;
-                fault_in_pages_readable(buf, maxlen);
+                fault_in_pages_readable(buf, bytes);
 
                 page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
                 if (!page) {
@@ -2121,6 +2125,12 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                         break;
                 }
 
+                if (unlikely(bytes == 0)) {
+                        status = 0;
+                        copied = 0;
+                        goto zero_length_segment;
+                }
+
                 status = a_ops->prepare_write(file, page, offset, offset+bytes);
                 if (unlikely(status)) {
                         loff_t isize = i_size_read(inode);
@@ -2150,7 +2160,8 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                         page_cache_release(page);
                         continue;
                 }
-                if (likely(copied > 0)) {
+zero_length_segment:
+                if (likely(copied >= 0)) {
                         if (!status)
                                 status = copied;
 
@@ -2215,7 +2226,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
                                 unsigned long nr_segs, loff_t *ppos)
 {
         struct file *file = iocb->ki_filp;
-        struct address_space * mapping = file->f_mapping;
+        const struct address_space * mapping = file->f_mapping;
         size_t ocount;          /* original count */
         size_t count;           /* after file limit checks */
         struct inode    *inode = mapping->host;
diff --git a/mm/filemap.h b/mm/filemap.h
index 536979fb4ba..3f2a343c601 100644
--- a/mm/filemap.h
+++ b/mm/filemap.h
@@ -88,7 +88,7 @@ filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
         const struct iovec *iov = *iovp;
         size_t base = *basep;
 
-        while (bytes) {
+        do {
                 int copy = min(bytes, iov->iov_len - base);
 
                 bytes -= copy;
@@ -97,7 +97,7 @@ filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
                         iov++;
                         base = 0;
                 }
-        }
+        } while (bytes);
         *iovp = iov;
         *basep = base;
 }
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index b960ac8e591..b4fd0d7c9bf 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -273,7 +273,7 @@ __xip_file_write(struct file *filp, const char __user *buf,
                   size_t count, loff_t pos, loff_t *ppos)
 {
         struct address_space * mapping = filp->f_mapping;
-        struct address_space_operations *a_ops = mapping->a_ops;
+        const struct address_space_operations *a_ops = mapping->a_ops;
         struct inode    *inode = mapping->host;
         long            status = 0;
         struct page     *page;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 841a077d5ae..ea4038838b0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,6 +21,7 @@
 #include <linux/memory_hotplug.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
+#include <linux/ioport.h>
 
 #include <asm/tlbflush.h>
 
@@ -126,6 +127,9 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         unsigned long i;
         unsigned long flags;
         unsigned long onlined_pages = 0;
+        struct resource res;
+        u64 section_end;
+        unsigned long start_pfn;
         struct zone *zone;
         int need_zonelists_rebuild = 0;
 
@@ -148,10 +152,27 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         if (!populated_zone(zone))
                 need_zonelists_rebuild = 1;
 
-        for (i = 0; i < nr_pages; i++) {
-                struct page *page = pfn_to_page(pfn + i);
-                online_page(page);
-                onlined_pages++;
+        res.start = (u64)pfn << PAGE_SHIFT;
+        res.end = res.start + ((u64)nr_pages << PAGE_SHIFT) - 1;
+        res.flags = IORESOURCE_MEM; /* we just need system ram */
+        section_end = res.end;
+
+        while (find_next_system_ram(&res) >= 0) {
+                start_pfn = (unsigned long)(res.start >> PAGE_SHIFT);
+                nr_pages = (unsigned long)
+                           ((res.end + 1 - res.start) >> PAGE_SHIFT);
+
+                if (PageReserved(pfn_to_page(start_pfn))) {
+                        /* this region's page is not onlined now */
+                        for (i = 0; i < nr_pages; i++) {
+                                struct page *page = pfn_to_page(start_pfn + i);
+                                online_page(page);
+                                onlined_pages++;
+                        }
+                }
+
+                res.start = res.end + 1;
+                res.end = section_end;
         }
         zone->present_pages += onlined_pages;
         zone->zone_pgdat->node_present_pages += onlined_pages;
@@ -163,3 +184,100 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         vm_total_pages = nr_free_pagecache_pages();
         return 0;
 }
+
+static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+{
+        struct pglist_data *pgdat;
+        unsigned long zones_size[MAX_NR_ZONES] = {0};
+        unsigned long zholes_size[MAX_NR_ZONES] = {0};
+        unsigned long start_pfn = start >> PAGE_SHIFT;
+
+        pgdat = arch_alloc_nodedata(nid);
+        if (!pgdat)
+                return NULL;
+
+        arch_refresh_nodedata(nid, pgdat);
+
+        /* we can use NODE_DATA(nid) from here */
+
+        /* init node's zones as empty zones, we don't have any present pages.*/
+        free_area_init_node(nid, pgdat, zones_size, start_pfn, zholes_size);
+
+        return pgdat;
+}
+
+static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
+{
+        arch_refresh_nodedata(nid, NULL);
+        arch_free_nodedata(pgdat);
+        return;
+}
+
+/* add this memory to iomem resource */
+static void register_memory_resource(u64 start, u64 size)
+{
+        struct resource *res;
+
+        res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+        BUG_ON(!res);
+
+        res->name = "System RAM";
+        res->start = start;
+        res->end = start + size - 1;
+        res->flags = IORESOURCE_MEM;
+        if (request_resource(&iomem_resource, res) < 0) {
+                printk("System RAM resource %llx - %llx cannot be added\n",
+                (unsigned long long)res->start, (unsigned long long)res->end);
+                kfree(res);
+        }
+}
+
+
+
+int add_memory(int nid, u64 start, u64 size)
+{
+        pg_data_t *pgdat = NULL;
+        int new_pgdat = 0;
+        int ret;
+
+        if (!node_online(nid)) {
+                pgdat = hotadd_new_pgdat(nid, start);
+                if (!pgdat)
+                        return -ENOMEM;
+                new_pgdat = 1;
+                ret = kswapd_run(nid);
+                if (ret)
+                        goto error;
+        }
+
+        /* call arch's memory hotadd */
+        ret = arch_add_memory(nid, start, size);
+
+        if (ret < 0)
+                goto error;
+
+        /* we online node here. we can't roll back from here. */
+        node_set_online(nid);
+
+        if (new_pgdat) {
+                ret = register_one_node(nid);
+                /*
+                 * If sysfs file of new node can't create, cpu on the node
+                 * can't be hot-added. There is no rollback way now.
+                 * So, check by BUG_ON() to catch it reluctantly..
+                 */
+                BUG_ON(ret);
+        }
+
+        /* register this memory as resource */
+        register_memory_resource(start, size);
+
+        return ret;
+error:
+        /* rollback pgdat allocation and others */
+        if (new_pgdat)
+                rollback_node_hotadd(nid, pgdat);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(add_memory);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8ccf6f1b147..4ec7026c7ba 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -516,14 +516,14 @@ static void set_ratelimit(void)
                 ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
 }
 
-static int
+static int __cpuinit
 ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
 {
         set_ratelimit();
         return 0;
 }
 
-static struct notifier_block ratelimit_nb = {
+static struct notifier_block __cpuinitdata ratelimit_nb = {
         .notifier_call  = ratelimit_handler,
         .next           = NULL,
 };
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6c1174fcf52..084a2de7e52 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -266,7 +266,7 @@ static inline void rmv_page_order(struct page *page)
  * satisfies the following equation:
  *     P = B & ~(1 << O)
  *
- * Assumption: *_mem_map is contigious at least up to MAX_ORDER
+ * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
  */
 static inline struct page *
 __page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
@@ -446,8 +446,8 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 
         arch_free_page(page, order);
         if (!PageHighMem(page))
-                mutex_debug_check_no_locks_freed(page_address(page),
-                                                 PAGE_SIZE<<order);
+                debug_check_no_locks_freed(page_address(page),
+                                           PAGE_SIZE<<order);
 
         for (i = 0 ; i < (1 << order) ; ++i)
                 reserved += free_pages_check(page + i);
@@ -2009,7 +2009,7 @@ static inline void free_zone_pagesets(int cpu)
         }
 }
 
-static int pageset_cpuup_callback(struct notifier_block *nfb,
+static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
                 unsigned long action,
                 void *hcpu)
 {
@@ -2031,7 +2031,7 @@ static int pageset_cpuup_callback(struct notifier_block *nfb,
         return ret;
 }
 
-static struct notifier_block pageset_notifier =
+static struct notifier_block __cpuinitdata pageset_notifier =
         { &pageset_cpuup_callback, NULL, 0 };
 
 void __init setup_per_cpu_pageset(void)
diff --git a/mm/readahead.c b/mm/readahead.c
index e39e416860d..aa7ec424656 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -390,8 +390,8 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
  * Read 'nr_to_read' pages starting at page 'offset'. If the flag 'block'
  * is set wait till the read completes.  Otherwise attempt to read without
  * blocking.
- * Returns 1 meaning 'success' if read is succesfull without switching off
- * readhaead mode. Otherwise return failure.
+ * Returns 1 meaning 'success' if read is successful without switching off
+ * readahead mode. Otherwise return failure.
  */
 static int
 blockable_page_cache_readahead(struct address_space *mapping, struct file *filp,
diff --git a/mm/shmem.c b/mm/shmem.c
index 355904712a8..b14ff817d16 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -173,7 +173,7 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 }
 
 static struct super_operations shmem_ops;
-static struct address_space_operations shmem_aops;
+static const struct address_space_operations shmem_aops;
 static struct file_operations shmem_file_operations;
 static struct inode_operations shmem_inode_operations;
 static struct inode_operations shmem_dir_inode_operations;
@@ -2161,7 +2161,7 @@ static void destroy_inodecache(void)
                 printk(KERN_INFO "shmem_inode_cache: not all structures were freed\n");
 }
 
-static struct address_space_operations shmem_aops = {
+static const struct address_space_operations shmem_aops = {
         .writepage      = shmem_writepage,
         .set_page_dirty = __set_page_dirty_nobuffers,
 #ifdef CONFIG_TMPFS
diff --git a/mm/slab.c b/mm/slab.c
index 98ac20bc0de..233e39d14ca 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -89,6 +89,7 @@
 #include        <linux/config.h>
 #include        <linux/slab.h>
 #include        <linux/mm.h>
+#include        <linux/poison.h>
 #include        <linux/swap.h>
 #include        <linux/cache.h>
 #include        <linux/interrupt.h>
@@ -106,6 +107,7 @@
 #include        <linux/nodemask.h>
 #include        <linux/mempolicy.h>
 #include        <linux/mutex.h>
+#include        <linux/rtmutex.h>
 
 #include        <asm/uaccess.h>
 #include        <asm/cacheflush.h>
@@ -492,17 +494,6 @@ struct kmem_cache {
 #endif
 
 #if DEBUG
-/*
- * Magic nums for obj red zoning.
- * Placed in the first word before and the first word after an obj.
- */
-#define RED_INACTIVE    0x5A2CF071UL    /* when obj is inactive */
-#define RED_ACTIVE      0x170FC2A5UL    /* when obj is active */
-
-/* ...and for poisoning */
-#define POISON_INUSE    0x5a    /* for use-uninitialised poisoning */
-#define POISON_FREE     0x6b    /* for use-after-free poisoning */
-#define POISON_END      0xa5    /* end-byte of poisoning */
 
 /*
  * memory layout of objects:
@@ -1083,7 +1074,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 
 #endif
 
-static int cpuup_callback(struct notifier_block *nfb,
+static int __devinit cpuup_callback(struct notifier_block *nfb,
                                     unsigned long action, void *hcpu)
 {
         long cpu = (long)hcpu;
@@ -1265,7 +1256,9 @@ bad:
         return NOTIFY_BAD;
 }
 
-static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };
+static struct notifier_block __cpuinitdata cpucache_notifier = {
+        &cpuup_callback, NULL, 0
+};
 
 /*
  * swap the static kmem_list3 with kmalloced memory
@@ -3405,7 +3398,7 @@ void kfree(const void *objp)
         local_irq_save(flags);
         kfree_debugcheck(objp);
         c = virt_to_cache(objp);
-        mutex_debug_check_no_locks_freed(objp, obj_size(c));
+        debug_check_no_locks_freed(objp, obj_size(c));
         __cache_free(c, (void *)objp);
         local_irq_restore(flags);
 }
diff --git a/mm/sparse.c b/mm/sparse.c
index e0a3fe48aa3..c7a2b3a0e46 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -45,7 +45,7 @@ static struct mem_section *sparse_index_alloc(int nid)
 
 static int sparse_index_init(unsigned long section_nr, int nid)
 {
-        static spinlock_t index_init_lock = SPIN_LOCK_UNLOCKED;
+        static DEFINE_SPINLOCK(index_init_lock);
         unsigned long root = SECTION_NR_TO_ROOT(section_nr);
         struct mem_section *section;
         int ret = 0;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e0e1583f32c..7535211bb49 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -24,7 +24,7 @@
  * vmscan's shrink_list, to make sync_page look nicer, and to allow
  * future use of radix_tree tags in the swap cache.
  */
-static struct address_space_operations swap_aops = {
+static const struct address_space_operations swap_aops = {
         .writepage      = swap_writepage,
         .sync_page      = block_sync_page,
         .set_page_dirty = __set_page_dirty_nobuffers,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 72babac71de..eeacb0d695c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -34,6 +34,7 @@
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/delay.h>
+#include <linux/kthread.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1223,7 +1224,6 @@ static int kswapd(void *p)
         };
         cpumask_t cpumask;
 
-        daemonize("kswapd%d", pgdat->node_id);
         cpumask = node_to_cpumask(pgdat->node_id);
         if (!cpus_empty(cpumask))
                 set_cpus_allowed(tsk, cpumask);
@@ -1450,7 +1450,7 @@ out:
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
-static int cpu_callback(struct notifier_block *nfb,
+static int __devinit cpu_callback(struct notifier_block *nfb,
                                   unsigned long action, void *hcpu)
 {
         pg_data_t *pgdat;
@@ -1468,20 +1468,35 @@ static int cpu_callback(struct notifier_block *nfb,
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+/*
+ * This kswapd start function will be called by init and node-hot-add.
+ * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
+ */
+int kswapd_run(int nid)
+{
+        pg_data_t *pgdat = NODE_DATA(nid);
+        int ret = 0;
+
+        if (pgdat->kswapd)
+                return 0;
+
+        pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+        if (IS_ERR(pgdat->kswapd)) {
+                /* failure at boot is fatal */
+                BUG_ON(system_state == SYSTEM_BOOTING);
+                printk("Failed to start kswapd on node %d\n",nid);
+                ret = -1;
+        }
+        return ret;
+}
+
 static int __init kswapd_init(void)
 {
-        pg_data_t *pgdat;
+        int nid;
 
         swap_setup();
-        for_each_online_pgdat(pgdat) {
-                pid_t pid;
-
-                pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
-                BUG_ON(pid < 0);
-                read_lock(&tasklist_lock);
-                pgdat->kswapd = find_task_by_pid(pid);
-                read_unlock(&tasklist_lock);
-        }
+        for_each_online_node(nid)
+                kswapd_run(nid);
         hotcpu_notifier(cpu_callback, 0);
         return 0;
 }