8 files changed, 147 insertions, 82 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index d84eecacbeaf..3e1239e4b303 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -438,7 +438,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
                 jiffies_to_clock_t(it_real_value),
                 start_time,
                 vsize,
-                mm ? get_mm_counter(mm, rss) : 0, /* you might want to shift this left 3 */
+                mm ? get_mm_rss(mm) : 0,
                 rsslim,
                 mm ? mm->start_code : 0,
                 mm ? mm->end_code : 0,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index fb34f88a4a74..634355e16986 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -70,6 +70,7 @@
 #include <linux/seccomp.h>
 #include <linux/cpuset.h>
 #include <linux/audit.h>
+#include <linux/poll.h>
 #include "internal.h"
 
 /*
@@ -103,7 +104,9 @@ enum pid_directory_inos {
         PROC_TGID_NUMA_MAPS,
         PROC_TGID_MOUNTS,
         PROC_TGID_WCHAN,
+#ifdef CONFIG_MMU
         PROC_TGID_SMAPS,
+#endif
 #ifdef CONFIG_SCHEDSTATS
         PROC_TGID_SCHEDSTAT,
 #endif
@@ -141,7 +144,9 @@ enum pid_directory_inos {
         PROC_TID_NUMA_MAPS,
         PROC_TID_MOUNTS,
         PROC_TID_WCHAN,
+#ifdef CONFIG_MMU
         PROC_TID_SMAPS,
+#endif
 #ifdef CONFIG_SCHEDSTATS
         PROC_TID_SCHEDSTAT,
 #endif
@@ -195,7 +200,9 @@ static struct pid_entry tgid_base_stuff[] = {
         E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
         E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
         E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
+#ifdef CONFIG_MMU
         E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
+#endif
 #ifdef CONFIG_SECURITY
         E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -235,7 +242,9 @@ static struct pid_entry tid_base_stuff[] = {
         E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
         E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
         E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
+#ifdef CONFIG_MMU
         E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUGO),
+#endif
 #ifdef CONFIG_SECURITY
         E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -343,7 +352,8 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf
 
 /* Same as proc_root_link, but this addionally tries to get fs from other
  * threads in the group */
-static int proc_task_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static int proc_task_root_link(struct inode *inode, struct dentry **dentry,
+                                struct vfsmount **mnt)
 {
         struct fs_struct *fs;
         int result = -ENOENT;
@@ -357,9 +367,10 @@ static int proc_task_root_link(struct inode *inode, struct dentry **dentry, stru
         } else {
                 /* Try to get fs from other threads */
                 task_unlock(leader);
-                struct task_struct *task = leader;
                 read_lock(&tasklist_lock);
-                if (pid_alive(task)) {
+                if (pid_alive(leader)) {
+                        struct task_struct *task = leader;
+
                         while ((task = next_thread(task)) != leader) {
                                 task_lock(task);
                                 fs = task->fs;
@@ -628,6 +639,7 @@ static struct file_operations proc_numa_maps_operations = {
 };
 #endif
 
+#ifdef CONFIG_MMU
 extern struct seq_operations proc_pid_smaps_op;
 static int smaps_open(struct inode *inode, struct file *file)
 {
@@ -646,28 +658,41 @@ static struct file_operations proc_smaps_operations = {
         .llseek         = seq_lseek,
         .release        = seq_release,
 };
+#endif
 
 extern struct seq_operations mounts_op;
+struct proc_mounts {
+        struct seq_file m;
+        int event;
+};
+
 static int mounts_open(struct inode *inode, struct file *file)
 {
         struct task_struct *task = proc_task(inode);
-        int ret = seq_open(file, &mounts_op);
+        struct namespace *namespace;
+        struct proc_mounts *p;
+        int ret = -EINVAL;
 
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-                struct namespace *namespace;
-                task_lock(task);
-                namespace = task->namespace;
-                if (namespace)
-                        get_namespace(namespace);
-                task_unlock(task);
-
-                if (namespace)
-                        m->private = namespace;
-                else {
-                        seq_release(inode, file);
-                        ret = -EINVAL;
+        task_lock(task);
+        namespace = task->namespace;
+        if (namespace)
+                get_namespace(namespace);
+        task_unlock(task);
+
+        if (namespace) {
+                ret = -ENOMEM;
+                p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
+                if (p) {
+                        file->private_data = &p->m;
+                        ret = seq_open(file, &mounts_op);
+                        if (!ret) {
+                                p->m.private = namespace;
+                                p->event = namespace->event;
+                                return 0;
+                        }
+                        kfree(p);
                 }
+                put_namespace(namespace);
         }
         return ret;
 }
@@ -680,11 +705,30 @@ static int mounts_release(struct inode *inode, struct file *file)
         return seq_release(inode, file);
 }
 
+static unsigned mounts_poll(struct file *file, poll_table *wait)
+{
+        struct proc_mounts *p = file->private_data;
+        struct namespace *ns = p->m.private;
+        unsigned res = 0;
+
+        poll_wait(file, &ns->poll, wait);
+
+        spin_lock(&vfsmount_lock);
+        if (p->event != ns->event) {
+                p->event = ns->event;
+                res = POLLERR;
+        }
+        spin_unlock(&vfsmount_lock);
+
+        return res;
+}
+
 static struct file_operations proc_mounts_operations = {
         .open           = mounts_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
         .release        = mounts_release,
+        .poll           = mounts_poll,
 };
 
 #define PROC_BLOCK_SIZE (3*1024)                /* 4K page size but our output routines use some slack for overruns */
@@ -1679,10 +1723,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
                 case PROC_TGID_MOUNTS:
                         inode->i_fop = &proc_mounts_operations;
                         break;
+#ifdef CONFIG_MMU
                 case PROC_TID_SMAPS:
                 case PROC_TGID_SMAPS:
                         inode->i_fop = &proc_smaps_operations;
                         break;
+#endif
 #ifdef CONFIG_SECURITY
                 case PROC_TID_ATTR:
                         inode->i_nlink = 2;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8a8c34461d48..b638fb500743 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -533,7 +533,7 @@ static void proc_kill_inodes(struct proc_dir_entry *de)
          */
         file_list_lock();
         list_for_each(p, &sb->s_files) {
-                struct file * filp = list_entry(p, struct file, f_list);
+                struct file * filp = list_entry(p, struct file, f_u.fu_list);
                 struct dentry * dentry = filp->f_dentry;
                 struct inode * inode;
                 struct file_operations *fops;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index effa6c0c467a..e6a818a93f3d 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -156,10 +156,13 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 
         WARN_ON(de && de->deleted);
 
+        if (de != NULL && !try_module_get(de->owner))
+                goto out_mod;
+
         inode = iget(sb, ino);
         if (!inode)
-                goto out_fail;
-        
+                goto out_ino;
+
         PROC_I(inode)->pde = de;
         if (de) {
                 if (de->mode) {
@@ -171,20 +174,20 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
                         inode->i_size = de->size;
                 if (de->nlink)
                         inode->i_nlink = de->nlink;
-                if (!try_module_get(de->owner))
-                        goto out_fail;
                 if (de->proc_iops)
                         inode->i_op = de->proc_iops;
                 if (de->proc_fops)
                         inode->i_fop = de->proc_fops;
         }
 
-out:
         return inode;
 
-out_fail:
+out_ino:
+        if (de != NULL)
+                module_put(de->owner);
+out_mod:
         de_put(de);
-        goto out;
+        return NULL;
 }                       
 
 int proc_fill_super(struct super_block *s, void *data, int silent)
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index f3bf016d5ee3..cff10ab1af63 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -91,6 +91,7 @@ static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos)
                         next = _rb;
                         break;
                 }
+                pos--;
         }
 
         return next;
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index 6fd57f154197..fb117b74809e 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -49,6 +49,39 @@ static int property_read_proc(char *page, char **start, off_t off,
  */
 
 /*
+ * Add a property to a node
+ */
+static struct proc_dir_entry *
+__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp)
+{
+        struct proc_dir_entry *ent;
+
+        /*
+         * Unfortunately proc_register puts each new entry
+         * at the beginning of the list.  So we rearrange them.
+         */
+        ent = create_proc_read_entry(pp->name,
+                                     strncmp(pp->name, "security-", 9)
+                                     ? S_IRUGO : S_IRUSR, de,
+                                     property_read_proc, pp);
+        if (ent == NULL)
+                return NULL;
+
+        if (!strncmp(pp->name, "security-", 9))
+                ent->size = 0; /* don't leak number of password chars */
+        else
+                ent->size = pp->length;
+
+        return ent;
+}
+
+
+void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop)
+{
+        __proc_device_tree_add_prop(pde, prop);
+}
+
+/*
  * Process a node, adding entries for its children and its properties.
  */
 void proc_device_tree_add_node(struct device_node *np,
@@ -57,11 +90,9 @@ void proc_device_tree_add_node(struct device_node *np,
         struct property *pp;
         struct proc_dir_entry *ent;
         struct device_node *child;
-        struct proc_dir_entry *list = NULL, **lastp;
         const char *p;
 
         set_node_proc_entry(np, de);
-        lastp = &list;
         for (child = NULL; (child = of_get_next_child(np, child));) {
                 p = strrchr(child->full_name, '/');
                 if (!p)
@@ -71,9 +102,6 @@ void proc_device_tree_add_node(struct device_node *np,
                 ent = proc_mkdir(p, de);
                 if (ent == 0)
                         break;
-                *lastp = ent;
-                ent->next = NULL;
-                lastp = &ent->next;
                 proc_device_tree_add_node(child, ent);
         }
         of_node_put(child);
@@ -84,7 +112,7 @@ void proc_device_tree_add_node(struct device_node *np,
                  * properties are quite unimportant for us though, thus we
                  * simply "skip" them here, but we do have to check.
                  */
-                for (ent = list; ent != NULL; ent = ent->next)
+                for (ent = de->subdir; ent != NULL; ent = ent->next)
                         if (!strcmp(ent->name, pp->name))
                                 break;
                 if (ent != NULL) {
@@ -94,25 +122,10 @@ void proc_device_tree_add_node(struct device_node *np,
                         continue;
                 }
 
-                /*
-                 * Unfortunately proc_register puts each new entry
-                 * at the beginning of the list.  So we rearrange them.
-                 */
-                ent = create_proc_read_entry(pp->name,
-                                             strncmp(pp->name, "security-", 9)
-                                             ? S_IRUGO : S_IRUSR, de,
-                                             property_read_proc, pp);
+                ent = __proc_device_tree_add_prop(de, pp);
                 if (ent == 0)
                         break;
-                if (!strncmp(pp->name, "security-", 9))
-                     ent->size = 0; /* don't leak number of password chars */
-                else
-                     ent->size = pp->length;
-                ent->next = NULL;
-                *lastp = ent;
-                lastp = &ent->next;
         }
-        de->subdir = list;
 }
 
 /*
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index a3453555a94e..5b6b0b6038a7 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -629,12 +629,4 @@ void __init proc_misc_init(void)
         if (entry)
                 entry->proc_fops = &proc_sysrq_trigger_operations;
 #endif
-#ifdef CONFIG_PPC32
-        {
-                extern struct file_operations ppc_htab_operations;
-                entry = create_proc_entry("ppc_htab", S_IRUGO|S_IWUSR, NULL);
-                if (entry)
-                        entry->proc_fops = &ppc_htab_operations;
-        }
-#endif
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c7ef3e48e35b..50bd5a8f0446 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,22 +14,41 @@
 char *task_mem(struct mm_struct *mm, char *buffer)
 {
         unsigned long data, text, lib;
+        unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
+
+        /*
+         * Note: to minimize their overhead, mm maintains hiwater_vm and
+         * hiwater_rss only when about to *lower* total_vm or rss.  Any
+         * collector of these hiwater stats must therefore get total_vm
+         * and rss too, which will usually be the higher.  Barriers? not
+         * worth the effort, such snapshots can always be inconsistent.
+         */
+        hiwater_vm = total_vm = mm->total_vm;
+        if (hiwater_vm < mm->hiwater_vm)
+                hiwater_vm = mm->hiwater_vm;
+        hiwater_rss = total_rss = get_mm_rss(mm);
+        if (hiwater_rss < mm->hiwater_rss)
+                hiwater_rss = mm->hiwater_rss;
 
         data = mm->total_vm - mm->shared_vm - mm->stack_vm;
         text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
         lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
         buffer += sprintf(buffer,
+                "VmPeak:\t%8lu kB\n"
                 "VmSize:\t%8lu kB\n"
                 "VmLck:\t%8lu kB\n"
+                "VmHWM:\t%8lu kB\n"
                 "VmRSS:\t%8lu kB\n"
                 "VmData:\t%8lu kB\n"
                 "VmStk:\t%8lu kB\n"
                 "VmExe:\t%8lu kB\n"
                 "VmLib:\t%8lu kB\n"
                 "VmPTE:\t%8lu kB\n",
-                (mm->total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
+                hiwater_vm << (PAGE_SHIFT-10),
+                (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
                 mm->locked_vm << (PAGE_SHIFT-10),
-                get_mm_counter(mm, rss) << (PAGE_SHIFT-10),
+                hiwater_rss << (PAGE_SHIFT-10),
+                total_rss << (PAGE_SHIFT-10),
                 data << (PAGE_SHIFT-10),
                 mm->stack_vm << (PAGE_SHIFT-10), text, lib,
                 (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
@@ -44,13 +63,11 @@ unsigned long task_vsize(struct mm_struct *mm)
 int task_statm(struct mm_struct *mm, int *shared, int *text,
                int *data, int *resident)
 {
-        int rss = get_mm_counter(mm, rss);
-
-        *shared = rss - get_mm_counter(mm, anon_rss);
+        *shared = get_mm_counter(mm, file_rss);
         *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
                                                                 >> PAGE_SHIFT;
         *data = mm->total_vm - mm->shared_vm;
-        *resident = rss;
+        *resident = *shared + get_mm_counter(mm, anon_rss);
         return mm->total_vm;
 }
 
@@ -178,7 +195,7 @@ static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats
 
 static int show_map(struct seq_file *m, void *v)
 {
-        return show_map_internal(m, v, 0);
+        return show_map_internal(m, v, NULL);
 }
 
 static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
@@ -186,13 +203,14 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                 struct mem_size_stats *mss)
 {
         pte_t *pte, ptent;
+        spinlock_t *ptl;
         unsigned long pfn;
         struct page *page;
 
-        pte = pte_offset_map(pmd, addr);
+        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
         do {
                 ptent = *pte;
-                if (pte_none(ptent) || !pte_present(ptent))
+                if (!pte_present(ptent))
                         continue;
 
                 mss->resident += PAGE_SIZE;
@@ -213,8 +231,8 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                 mss->private_clean += PAGE_SIZE;
                 }
         } while (pte++, addr += PAGE_SIZE, addr != end);
-        pte_unmap(pte - 1);
-        cond_resched_lock(&vma->vm_mm->page_table_lock);
+        pte_unmap_unlock(pte - 1, ptl);
+        cond_resched();
 }
 
 static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -268,17 +286,11 @@ static inline void smaps_pgd_range(struct vm_area_struct *vma,
 static int show_smap(struct seq_file *m, void *v)
 {
         struct vm_area_struct *vma = v;
-        struct mm_struct *mm = vma->vm_mm;
         struct mem_size_stats mss;
 
         memset(&mss, 0, sizeof mss);
-
-        if (mm) {
-                spin_lock(&mm->page_table_lock);
+        if (vma->vm_mm)
                 smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
-                spin_unlock(&mm->page_table_lock);
-        }
-
         return show_map_internal(m, v, &mss);
 }
 
@@ -390,12 +402,11 @@ struct numa_maps {
 /*
  * Calculate numa node maps for a vma
  */
-static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
+static struct numa_maps *get_numa_maps(struct vm_area_struct *vma)
 {
+        int i;
         struct page *page;
         unsigned long vaddr;
-        struct mm_struct *mm = vma->vm_mm;
-        int i;
         struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL);
 
         if (!md)
@@ -407,9 +418,8 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
         for_each_node(i)
                 md->node[i] =0;
 
-        spin_lock(&mm->page_table_lock);
         for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
-                page = follow_page(mm, vaddr, 0);
+                page = follow_page(vma, vaddr, 0);
                 if (page) {
                         int count = page_mapcount(page);
 
@@ -422,8 +432,8 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
                                 md->anon++;
                         md->node[page_to_nid(page)]++;
                 }
+                cond_resched();
         }
-        spin_unlock(&mm->page_table_lock);
         return md;
 }
 
@@ -469,7 +479,7 @@ static int show_numa_map(struct seq_file *m, void *v)
                 seq_printf(m, " interleave={");
                 first = 1;
                 for_each_node(n) {
-                        if (test_bit(n, pol->v.nodes)) {
+                        if (node_isset(n, pol->v.nodes)) {
                                 if (!first)
                                         seq_putc(m,',');
                                 else