Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

13 files changed, 315 insertions, 334 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 07d6c4853fe8..9e3b8c33c24b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -73,6 +73,7 @@
 #include <linux/signal.h>
 #include <linux/highmem.h>
 #include <linux/file.h>
+#include <linux/fdtable.h>
 #include <linux/times.h>
 #include <linux/cpuset.h>
 #include <linux/rcupdate.h>
@@ -297,6 +298,7 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
         render_cap_t(m, "CapInh:\t", &p->cap_inheritable);
         render_cap_t(m, "CapPrm:\t", &p->cap_permitted);
         render_cap_t(m, "CapEff:\t", &p->cap_effective);
+        render_cap_t(m, "CapBnd:\t", &p->cap_bset);
 }
 
 static inline void task_context_switch_counts(struct seq_file *m,
@@ -425,12 +427,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
         cutime = cstime = utime = stime = cputime_zero;
         cgtime = gtime = cputime_zero;
 
-        rcu_read_lock();
         if (lock_task_sighand(task, &flags)) {
                 struct signal_struct *sig = task->signal;
 
                 if (sig->tty) {
-                        tty_pgrp = pid_nr_ns(sig->tty->pgrp, ns);
+                        struct pid *pgrp = tty_get_pgrp(sig->tty);
+                        tty_pgrp = pid_nr_ns(pgrp, ns);
+                        put_pid(pgrp);
                         tty_nr = new_encode_dev(tty_devnum(sig->tty));
                 }
 
@@ -469,7 +472,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
                 unlock_task_sighand(task, &flags);
         }
-        rcu_read_unlock();
 
         if (!whole || num_threads < 2)
                 wchan = get_wchan(task);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c5e412a00b17..808cbdc193d3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -56,6 +56,7 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/file.h>
+#include <linux/fdtable.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
 #include <linux/namei.h>
@@ -195,12 +196,32 @@ static int proc_root_link(struct inode *inode, struct path *path)
         return result;
 }
 
-#define MAY_PTRACE(task) \
-        (task == current || \
-        (task->parent == current && \
-        (task->ptrace & PT_PTRACED) && \
-         (task_is_stopped_or_traced(task)) && \
-         security_ptrace(current,task) == 0))
+/*
+ * Return zero if current may access user memory in @task, -error if not.
+ */
+static int check_mem_permission(struct task_struct *task)
+{
+        /*
+         * A task can always look at itself, in case it chooses
+         * to use system calls instead of load instructions.
+         */
+        if (task == current)
+                return 0;
+
+        /*
+         * If current is actively ptrace'ing, and would also be
+         * permitted to freshly attach with ptrace now, permit it.
+         */
+        if (task->parent == current && (task->ptrace & PT_PTRACED) &&
+            task_is_stopped_or_traced(task) &&
+            ptrace_may_attach(task))
+                return 0;
+
+        /*
+         * Noone else is allowed.
+         */
+        return -EPERM;
+}
 
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
@@ -722,7 +743,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
         if (!task)
                 goto out_no_task;
 
-        if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+        if (check_mem_permission(task))
                 goto out;
 
         ret = -ENOMEM;
@@ -748,7 +769,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 
                 this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
                 retval = access_process_vm(task, src, page, this_len, 0);
-                if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) {
+                if (!retval || check_mem_permission(task)) {
                         if (!ret)
                                 ret = -EIO;
                         break;
@@ -792,7 +813,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
         if (!task)
                 goto out_no_task;
 
-        if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+        if (check_mem_permission(task))
                 goto out;
 
         copied = -ENOMEM;
@@ -1181,6 +1202,81 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+/*
+ * We added or removed a vma mapping the executable. The vmas are only mapped
+ * during exec and are not mapped with the mmap system call.
+ * Callers must hold down_write() on the mm's mmap_sem for these
+ */
+void added_exe_file_vma(struct mm_struct *mm)
+{
+        mm->num_exe_file_vmas++;
+}
+
+void removed_exe_file_vma(struct mm_struct *mm)
+{
+        mm->num_exe_file_vmas--;
+        if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+                fput(mm->exe_file);
+                mm->exe_file = NULL;
+        }
+
+}
+
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+        if (new_exe_file)
+                get_file(new_exe_file);
+        if (mm->exe_file)
+                fput(mm->exe_file);
+        mm->exe_file = new_exe_file;
+        mm->num_exe_file_vmas = 0;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+        struct file *exe_file;
+
+        /* We need mmap_sem to protect against races with removal of
+         * VM_EXECUTABLE vmas */
+        down_read(&mm->mmap_sem);
+        exe_file = mm->exe_file;
+        if (exe_file)
+                get_file(exe_file);
+        up_read(&mm->mmap_sem);
+        return exe_file;
+}
+
+void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+        /* It's safe to write the exe_file pointer without exe_file_lock because
+         * this is called during fork when the task is not yet in /proc */
+        newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
+static int proc_exe_link(struct inode *inode, struct path *exe_path)
+{
+        struct task_struct *task;
+        struct mm_struct *mm;
+        struct file *exe_file;
+
+        task = get_proc_task(inode);
+        if (!task)
+                return -ENOENT;
+        mm = get_task_mm(task);
+        put_task_struct(task);
+        if (!mm)
+                return -ENOENT;
+        exe_file = get_mm_exe_file(mm);
+        mmput(mm);
+        if (exe_file) {
+                *exe_path = exe_file->f_path;
+                path_get(&exe_file->f_path);
+                fput(exe_file);
+                return 0;
+        } else
+                return -ENOENT;
+}
+
 static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
         struct inode *inode = dentry->d_inode;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a36ad3c75cf4..43e54e86cefd 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -69,12 +69,7 @@ proc_file_read(struct file *file, char __user *buf, size_t nbytes,
                 count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
 
                 start = NULL;
-                if (dp->get_info) {
-                        /* Handle old net routines */
-                        n = dp->get_info(page, &start, *ppos, count);
-                        if (n < count)
-                                eof = 1;
-                } else if (dp->read_proc) {
+                if (dp->read_proc) {
                         /*
                          * How to be a proc read function
                          * ------------------------------
@@ -277,8 +272,11 @@ static int xlate_proc_name(const char *name,
         int                     len;
         int                     rtn = 0;
 
+        de = *ret;
+        if (!de)
+                de = &proc_root;
+
         spin_lock(&proc_subdir_lock);
-        de = &proc_root;
         while (1) {
                 next = strchr(cp, '/');
                 if (!next)
@@ -385,20 +383,18 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 
         lock_kernel();
         spin_lock(&proc_subdir_lock);
-        if (de) {
-                for (de = de->subdir; de ; de = de->next) {
-                        if (de->namelen != dentry->d_name.len)
-                                continue;
-                        if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-                                unsigned int ino;
+        for (de = de->subdir; de ; de = de->next) {
+                if (de->namelen != dentry->d_name.len)
+                        continue;
+                if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
+                        unsigned int ino;
 
-                                ino = de->low_ino;
-                                de_get(de);
-                                spin_unlock(&proc_subdir_lock);
-                                error = -EINVAL;
-                                inode = proc_get_inode(dir->i_sb, ino, de);
-                                goto out_unlock;
-                        }
+                        ino = de->low_ino;
+                        de_get(de);
+                        spin_unlock(&proc_subdir_lock);
+                        error = -EINVAL;
+                        inode = proc_get_inode(dir->i_sb, ino, de);
+                        goto out_unlock;
                 }
         }
         spin_unlock(&proc_subdir_lock);
@@ -410,7 +406,8 @@ out_unlock:
                 d_add(dentry, inode);
                 return NULL;
         }
-        de_put(de);
+        if (de)
+                de_put(de);
         return ERR_PTR(error);
 }
 
@@ -440,10 +437,6 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
         lock_kernel();
 
         ino = inode->i_ino;
-        if (!de) {
-                ret = -EINVAL;
-                goto out;
-        }
         i = filp->f_pos;
         switch (i) {
                 case 0:
@@ -582,7 +575,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
         /* make sure name is valid */
         if (!name || !strlen(name)) goto out;
 
-        if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0)
+        if (xlate_proc_name(name, parent, &fn) != 0)
                 goto out;
 
         /* At this point there must not be any '/' characters beyond *fn */
@@ -648,6 +641,23 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
         return ent;
 }
 
+struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
+                struct proc_dir_entry *parent)
+{
+        struct proc_dir_entry *ent;
+
+        ent = __proc_create(&parent, name, S_IFDIR | S_IRUGO | S_IXUGO, 2);
+        if (ent) {
+                ent->data = net;
+                if (proc_register(parent, ent) < 0) {
+                        kfree(ent);
+                        ent = NULL;
+                }
+        }
+        return ent;
+}
+EXPORT_SYMBOL_GPL(proc_net_mkdir);
+
 struct proc_dir_entry *proc_mkdir(const char *name,
                 struct proc_dir_entry *parent)
 {
@@ -682,9 +692,10 @@ struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
         return ent;
 }
 
-struct proc_dir_entry *proc_create(const char *name, mode_t mode,
-                                   struct proc_dir_entry *parent,
-                                   const struct file_operations *proc_fops)
+struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
+                                        struct proc_dir_entry *parent,
+                                        const struct file_operations *proc_fops,
+                                        void *data)
 {
         struct proc_dir_entry *pde;
         nlink_t nlink;
@@ -705,6 +716,7 @@ struct proc_dir_entry *proc_create(const char *name, mode_t mode,
         if (!pde)
                 goto out;
         pde->proc_fops = proc_fops;
+        pde->data = data;
         if (proc_register(parent, pde) < 0)
                 goto out_free;
         return pde;
@@ -734,55 +746,58 @@ void free_proc_entry(struct proc_dir_entry *de)
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
         struct proc_dir_entry **p;
-        struct proc_dir_entry *de;
+        struct proc_dir_entry *de = NULL;
         const char *fn = name;
         int len;
 
-        if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
-                goto out;
+        if (xlate_proc_name(name, &parent, &fn) != 0)
+                return;
         len = strlen(fn);
 
         spin_lock(&proc_subdir_lock);
         for (p = &parent->subdir; *p; p=&(*p)->next ) {
-                if (!proc_match(len, fn, *p))
-                        continue;
-                de = *p;
-                *p = de->next;
-                de->next = NULL;
-
-                spin_lock(&de->pde_unload_lock);
-                /*
-                 * Stop accepting new callers into module. If you're
-                 * dynamically allocating ->proc_fops, save a pointer somewhere.
-                 */
-                de->proc_fops = NULL;
-                /* Wait until all existing callers into module are done. */
-                if (de->pde_users > 0) {
-                        DECLARE_COMPLETION_ONSTACK(c);
-
-                        if (!de->pde_unload_completion)
-                                de->pde_unload_completion = &c;
-
-                        spin_unlock(&de->pde_unload_lock);
-                        spin_unlock(&proc_subdir_lock);
+                if (proc_match(len, fn, *p)) {
+                        de = *p;
+                        *p = de->next;
+                        de->next = NULL;
+                        break;
+                }
+        }
+        spin_unlock(&proc_subdir_lock);
+        if (!de)
+                return;
 
-                        wait_for_completion(de->pde_unload_completion);
+        spin_lock(&de->pde_unload_lock);
+        /*
+         * Stop accepting new callers into module. If you're
+         * dynamically allocating ->proc_fops, save a pointer somewhere.
+         */
+        de->proc_fops = NULL;
+        /* Wait until all existing callers into module are done. */
+        if (de->pde_users > 0) {
+                DECLARE_COMPLETION_ONSTACK(c);
+
+                if (!de->pde_unload_completion)
+                        de->pde_unload_completion = &c;
 
-                        spin_lock(&proc_subdir_lock);
-                        goto continue_removing;
-                }
                 spin_unlock(&de->pde_unload_lock);
 
+                wait_for_completion(de->pde_unload_completion);
+
+                goto continue_removing;
+        }
+        spin_unlock(&de->pde_unload_lock);
+
 continue_removing:
-                if (S_ISDIR(de->mode))
-                        parent->nlink--;
-                de->nlink = 0;
-                WARN_ON(de->subdir);
-                if (atomic_dec_and_test(&de->count))
-                        free_proc_entry(de);
-                break;
+        if (S_ISDIR(de->mode))
+                parent->nlink--;
+        de->nlink = 0;
+        if (de->subdir) {
+                printk(KERN_WARNING "%s: removing non-empty directory "
+                        "'%s/%s', leaking at least '%s'\n", __func__,
+                        de->parent->name, de->name, de->subdir->name);
+                WARN_ON(1);
         }
-        spin_unlock(&proc_subdir_lock);
-out:
-        return;
+        if (atomic_dec_and_test(&de->count))
+                free_proc_entry(de);
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 82b3a1b5a70b..6f4e8dc97da1 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -25,8 +25,7 @@
 
 struct proc_dir_entry *de_get(struct proc_dir_entry *de)
 {
-        if (de)
-                atomic_inc(&de->count);
+        atomic_inc(&de->count);
         return de;
 }
 
@@ -35,18 +34,16 @@ struct proc_dir_entry *de_get(struct proc_dir_entry *de)
  */
 void de_put(struct proc_dir_entry *de)
 {
-        if (de) {       
-                lock_kernel();          
-                if (!atomic_read(&de->count)) {
-                        printk("de_put: entry %s already free!\n", de->name);
-                        unlock_kernel();
-                        return;
-                }
-
-                if (atomic_dec_and_test(&de->count))
-                        free_proc_entry(de);
+        lock_kernel();
+        if (!atomic_read(&de->count)) {
+                printk("de_put: entry %s already free!\n", de->name);
                 unlock_kernel();
+                return;
         }
+
+        if (atomic_dec_and_test(&de->count))
+                free_proc_entry(de);
+        unlock_kernel();
 }
 
 /*
@@ -392,7 +389,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 {
         struct inode * inode;
 
-        if (de != NULL && !try_module_get(de->owner))
+        if (!try_module_get(de->owner))
                 goto out_mod;
 
         inode = iget_locked(sb, ino);
@@ -402,30 +399,29 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
                 inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
                 PROC_I(inode)->fd = 0;
                 PROC_I(inode)->pde = de;
-                if (de) {
-                        if (de->mode) {
-                                inode->i_mode = de->mode;
-                                inode->i_uid = de->uid;
-                                inode->i_gid = de->gid;
-                        }
-                        if (de->size)
-                                inode->i_size = de->size;
-                        if (de->nlink)
-                                inode->i_nlink = de->nlink;
-                        if (de->proc_iops)
-                                inode->i_op = de->proc_iops;
-                        if (de->proc_fops) {
-                                if (S_ISREG(inode->i_mode)) {
+
+                if (de->mode) {
+                        inode->i_mode = de->mode;
+                        inode->i_uid = de->uid;
+                        inode->i_gid = de->gid;
+                }
+                if (de->size)
+                        inode->i_size = de->size;
+                if (de->nlink)
+                        inode->i_nlink = de->nlink;
+                if (de->proc_iops)
+                        inode->i_op = de->proc_iops;
+                if (de->proc_fops) {
+                        if (S_ISREG(inode->i_mode)) {
 #ifdef CONFIG_COMPAT
-                                        if (!de->proc_fops->compat_ioctl)
-                                                inode->i_fop =
-                                                        &proc_reg_file_ops_no_compat;
-                                        else
+                                if (!de->proc_fops->compat_ioctl)
+                                        inode->i_fop =
+                                                &proc_reg_file_ops_no_compat;
+                                else
 #endif
-                                                inode->i_fop = &proc_reg_file_ops;
-                                } else {
-                                        inode->i_fop = de->proc_fops;
-                                }
+                                        inode->i_fop = &proc_reg_file_ops;
+                        } else {
+                                inode->i_fop = de->proc_fops;
                         }
                 }
                 unlock_new_inode(inode);
@@ -433,8 +429,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
         return inode;
 
 out_ino:
-        if (de != NULL)
-                module_put(de->owner);
+        module_put(de->owner);
 out_mod:
         return NULL;
 }                       
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index bc72f5c8c47d..28cbca805905 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -11,6 +11,7 @@
 
 #include <linux/proc_fs.h>
 
+extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
 extern int proc_sys_init(void);
 #else
@@ -46,9 +47,6 @@ extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
 
 extern int maps_protect;
 
-extern void create_seq_entry(char *name, mode_t mode,
-                                const struct file_operations *f);
-extern int proc_exe_link(struct inode *, struct path *);
 extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
                                 struct pid *pid, struct task_struct *task);
 extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 941e95114b5a..79ecd281d2cb 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -137,7 +137,7 @@ static const struct file_operations proc_nommu_vma_list_operations = {
 
 static int __init proc_nommu_init(void)
 {
-        create_seq_entry("maps", S_IRUGO, &proc_nommu_vma_list_operations);
+        proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations);
         return 0;
 }
 
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 441a32f0e5f2..74a323d2b850 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -179,6 +179,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
                 "PageTables:   %8lu kB\n"
                 "NFS_Unstable: %8lu kB\n"
                 "Bounce:       %8lu kB\n"
+                "WritebackTmp: %8lu kB\n"
                 "CommitLimit:  %8lu kB\n"
                 "Committed_AS: %8lu kB\n"
                 "VmallocTotal: %8lu kB\n"
@@ -210,6 +211,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
                 K(global_page_state(NR_PAGETABLE)),
                 K(global_page_state(NR_UNSTABLE_NFS)),
                 K(global_page_state(NR_BOUNCE)),
+                K(global_page_state(NR_WRITEBACK_TEMP)),
                 K(allowed),
                 K(committed),
                 (unsigned long)VMALLOC_TOTAL >> 10,
@@ -826,14 +828,6 @@ static struct file_operations proc_kpageflags_operations = {
 
 struct proc_dir_entry *proc_root_kcore;
 
-void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
-{
-        struct proc_dir_entry *entry;
-        entry = create_proc_entry(name, mode, NULL);
-        if (entry)
-                entry->proc_fops = f;
-}
-
 void __init proc_misc_init(void)
 {
         static struct {
@@ -862,66 +856,52 @@ void __init proc_misc_init(void)
 
         /* And now for trickier ones */
 #ifdef CONFIG_PRINTK
-        {
-                struct proc_dir_entry *entry;
-                entry = create_proc_entry("kmsg", S_IRUSR, &proc_root);
-                if (entry)
-                        entry->proc_fops = &proc_kmsg_operations;
-        }
+        proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
 #endif
-        create_seq_entry("locks", 0, &proc_locks_operations);
-        create_seq_entry("devices", 0, &proc_devinfo_operations);
-        create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations);
+        proc_create("locks", 0, NULL, &proc_locks_operations);
+        proc_create("devices", 0, NULL, &proc_devinfo_operations);
+        proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
 #ifdef CONFIG_BLOCK
-        create_seq_entry("partitions", 0, &proc_partitions_operations);
+        proc_create("partitions", 0, NULL, &proc_partitions_operations);
 #endif
-        create_seq_entry("stat", 0, &proc_stat_operations);
-        create_seq_entry("interrupts", 0, &proc_interrupts_operations);
+        proc_create("stat", 0, NULL, &proc_stat_operations);
+        proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
 #ifdef CONFIG_SLABINFO
-        create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations);
+        proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
 #ifdef CONFIG_DEBUG_SLAB_LEAK
-        create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations);
+        proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
 #endif
 #endif
 #ifdef CONFIG_MMU
         proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
 #endif
-        create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
-        create_seq_entry("pagetypeinfo", S_IRUGO, &pagetypeinfo_file_ops);
-        create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
-        create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations);
+        proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
+        proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
+        proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
+        proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #ifdef CONFIG_BLOCK
-        create_seq_entry("diskstats", 0, &proc_diskstats_operations);
+        proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
 #endif
 #ifdef CONFIG_MODULES
-        create_seq_entry("modules", 0, &proc_modules_operations);
+        proc_create("modules", 0, NULL, &proc_modules_operations);
 #endif
 #ifdef CONFIG_SCHEDSTATS
-        create_seq_entry("schedstat", 0, &proc_schedstat_operations);
+        proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
 #endif
 #ifdef CONFIG_PROC_KCORE
-        proc_root_kcore = create_proc_entry("kcore", S_IRUSR, NULL);
-        if (proc_root_kcore) {
-                proc_root_kcore->proc_fops = &proc_kcore_operations;
+        proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations);
+        if (proc_root_kcore)
                 proc_root_kcore->size =
                                 (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
-        }
 #endif
 #ifdef CONFIG_PROC_PAGE_MONITOR
-        create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
-        create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
+        proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
+        proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
 #endif
 #ifdef CONFIG_PROC_VMCORE
-        proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
-        if (proc_vmcore)
-                proc_vmcore->proc_fops = &proc_vmcore_operations;
+        proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
 #endif
 #ifdef CONFIG_MAGIC_SYSRQ
-        {
-                struct proc_dir_entry *entry;
-                entry = create_proc_entry("sysrq-trigger", S_IWUSR, NULL);
-                if (entry)
-                        entry->proc_fops = &proc_sysrq_trigger_operations;
-        }
+        proc_create("sysrq-trigger", S_IWUSR, NULL, &proc_sysrq_trigger_operations);
 #endif
 }
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 13cd7835d0df..83f357b30d71 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -159,17 +159,6 @@ struct net *get_proc_net(const struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(get_proc_net);
 
-struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
-                struct proc_dir_entry *parent)
-{
-        struct proc_dir_entry *pde;
-        pde = proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
-        if (pde != NULL)
-                pde->data = net;
-        return pde;
-}
-EXPORT_SYMBOL_GPL(proc_net_mkdir);
-
 static __net_init int proc_net_ns_init(struct net *net)
 {
         struct proc_dir_entry *netd, *net_statd;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 614c34b6d1c2..5acc001d49f6 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -165,8 +165,8 @@ out:
         return err;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-                                size_t count, loff_t *ppos)
+static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
+                size_t count, loff_t *ppos, int write)
 {
         struct dentry *dentry = filp->f_dentry;
         struct ctl_table_header *head;
@@ -190,12 +190,12 @@ static ssize_t proc_sys_read(struct file *filp, char __user *buf,
          * and won't be until we finish.
          */
         error = -EPERM;
-        if (sysctl_perm(table, MAY_READ))
+        if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
                 goto out;
 
         /* careful: calling conventions are nasty here */
         res = count;
-        error = table->proc_handler(table, 0, filp, buf, &res, ppos);
+        error = table->proc_handler(table, write, filp, buf, &res, ppos);
         if (!error)
                 error = res;
 out:
@@ -204,44 +204,16 @@ out:
         return error;
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+static ssize_t proc_sys_read(struct file *filp, char __user *buf,
                                 size_t count, loff_t *ppos)
 {
-        struct dentry *dentry = filp->f_dentry;
-        struct ctl_table_header *head;
-        struct ctl_table *table;
-        ssize_t error;
-        size_t res;
-
-        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-        /* Has the sysctl entry disappeared on us? */
-        error = -ENOENT;
-        if (!table)
-                goto out;
-
-        /* Has the sysctl entry been replaced by a directory? */
-        error = -EISDIR;
-        if (!table->proc_handler)
-                goto out;
-
-        /*
-         * At this point we know that the sysctl was not unregistered
-         * and won't be until we finish.
-         */
-        error = -EPERM;
-        if (sysctl_perm(table, MAY_WRITE))
-                goto out;
-
-        /* careful: calling conventions are nasty here */
-        res = count;
-        error = table->proc_handler(table, 1, filp, (char __user *)buf,
-                                    &res, ppos);
-        if (!error)
-                error = res;
-out:
-        sysctl_head_finish(head);
+        return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+}
 
-        return error;
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+                                size_t count, loff_t *ppos)
+{
+        return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
 }
 
 
@@ -416,7 +388,7 @@ static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *
                 goto out;
 
         /* Use the permissions on the sysctl table entry */
-        error = sysctl_perm(table, mask);
+        error = sysctl_perm(head->root, table, mask);
 out:
         sysctl_head_finish(head);
         return error;
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index 49816e00b51a..21f490f5d65c 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -5,7 +5,7 @@
  */
 
 #include <asm/uaccess.h>
-
+#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/time.h>
@@ -136,39 +136,54 @@ static const struct file_operations proc_tty_drivers_operations = {
         .release        = seq_release,
 };
 
-/*
- * This is the handler for /proc/tty/ldiscs
- */
-static int tty_ldiscs_read_proc(char *page, char **start, off_t off,
-                                int count, int *eof, void *data)
+static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
 {
-        int     i;
-        int     len = 0;
-        off_t   begin = 0;
+        return (*pos < NR_LDISCS) ? pos : NULL;
+}
+
+static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        (*pos)++;
+        return (*pos < NR_LDISCS) ? pos : NULL;
+}
+
+static void tty_ldiscs_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
+{
+        int i = *(loff_t *)v;
         struct tty_ldisc *ld;
         
-        for (i=0; i < NR_LDISCS; i++) {
-                ld = tty_ldisc_get(i);
-                if (ld == NULL)
-                        continue;
-                len += sprintf(page+len, "%-10s %2d\n",
-                               ld->name ? ld->name : "???", i);
-                tty_ldisc_put(i);
-                if (len+begin > off+count)
-                        break;
-                if (len+begin < off) {
-                        begin += len;
-                        len = 0;
-                }
-        }
-        if (i >= NR_LDISCS)
-                *eof = 1;
-        if (off >= len+begin)
+        ld = tty_ldisc_get(i);
+        if (ld == NULL)
                 return 0;
-        *start = page + (off-begin);
-        return ((count < begin+len-off) ? count : begin+len-off);
+        seq_printf(m, "%-10s %2d\n", ld->name ? ld->name : "???", i);
+        tty_ldisc_put(i);
+        return 0;
+}
+
+static const struct seq_operations tty_ldiscs_seq_ops = {
+        .start  = tty_ldiscs_seq_start,
+        .next   = tty_ldiscs_seq_next,
+        .stop   = tty_ldiscs_seq_stop,
+        .show   = tty_ldiscs_seq_show,
+};
+
+static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &tty_ldiscs_seq_ops);
 }
 
+static const struct file_operations tty_ldiscs_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = proc_tty_ldiscs_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
 /*
  * This function is called by tty_register_driver() to handle
  * registering the driver's /proc handler into /proc/tty/driver/<foo>
@@ -177,16 +192,14 @@ void proc_tty_register_driver(struct tty_driver *driver)
 {
         struct proc_dir_entry *ent;
                 
-        if ((!driver->read_proc && !driver->write_proc) ||
-            !driver->driver_name ||
+        if (!driver->ops->read_proc || !driver->driver_name ||
             driver->proc_entry)
                 return;
 
         ent = create_proc_entry(driver->driver_name, 0, proc_tty_driver);
         if (!ent)
                 return;
-        ent->read_proc = driver->read_proc;
-        ent->write_proc = driver->write_proc;
+        ent->read_proc = driver->ops->read_proc;
         ent->owner = driver->owner;
         ent->data = driver;
 
@@ -214,7 +227,6 @@ void proc_tty_unregister_driver(struct tty_driver *driver)
  */
 void __init proc_tty_init(void)
 {
-        struct proc_dir_entry *entry;
         if (!proc_mkdir("tty", NULL))
                 return;
         proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL);
@@ -224,10 +236,7 @@ void __init proc_tty_init(void)
          * password lengths and inter-keystroke timings during password
          * entry.
          */
-        proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR | S_IXUSR, NULL);
-
-        create_proc_read_entry("tty/ldiscs", 0, NULL, tty_ldiscs_read_proc, NULL);
-        entry = create_proc_entry("tty/drivers", 0, NULL);
-        if (entry)
-                entry->proc_fops = &proc_tty_drivers_operations;
+        proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
+        proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops);
+        proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations);
 }
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ef0fb57fc9ef..95117538a4f6 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -22,8 +22,6 @@
 
 #include "internal.h"
 
-struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver;
-
 static int proc_test_super(struct super_block *sb, void *data)
 {
         return sb->s_fs_info == data;
@@ -126,8 +124,8 @@ void __init proc_root_init(void)
 #ifdef CONFIG_SYSVIPC
         proc_mkdir("sysvipc", NULL);
 #endif
-        proc_root_fs = proc_mkdir("fs", NULL);
-        proc_root_driver = proc_mkdir("driver", NULL);
+        proc_mkdir("fs", NULL);
+        proc_mkdir("driver", NULL);
         proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
 #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
         /* just give it a mountpoint */
@@ -137,7 +135,7 @@ void __init proc_root_init(void)
 #ifdef CONFIG_PROC_DEVICETREE
         proc_device_tree_init();
 #endif
-        proc_bus = proc_mkdir("bus", NULL);
+        proc_mkdir("bus", NULL);
         proc_sys_init();
 }
 
@@ -232,9 +230,5 @@ void pid_ns_release_proc(struct pid_namespace *ns)
 EXPORT_SYMBOL(proc_symlink);
 EXPORT_SYMBOL(proc_mkdir);
 EXPORT_SYMBOL(create_proc_entry);
-EXPORT_SYMBOL(proc_create);
+EXPORT_SYMBOL(proc_create_data);
 EXPORT_SYMBOL(remove_proc_entry);
-EXPORT_SYMBOL(proc_root);
-EXPORT_SYMBOL(proc_root_fs);
-EXPORT_SYMBOL(proc_bus);
-EXPORT_SYMBOL(proc_root_driver);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7415eeb7cc3a..88717c0f941b 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -5,11 +5,9 @@
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
 #include <linux/pagemap.h>
-#include <linux/ptrace.h>
 #include <linux/mempolicy.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
-#include <linux/seq_file.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -75,40 +73,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
         return mm->total_vm;
 }
 
-int proc_exe_link(struct inode *inode, struct path *path)
-{
-        struct vm_area_struct * vma;
-        int result = -ENOENT;
-        struct task_struct *task = get_proc_task(inode);
-        struct mm_struct * mm = NULL;
-
-        if (task) {
-                mm = get_task_mm(task);
-                put_task_struct(task);
-        }
-        if (!mm)
-                goto out;
-        down_read(&mm->mmap_sem);
-
-        vma = mm->mmap;
-        while (vma) {
-                if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
-                        break;
-                vma = vma->vm_next;
-        }
-
-        if (vma) {
-                *path = vma->vm_file->f_path;
-                path_get(&vma->vm_file->f_path);
-                result = 0;
-        }
-
-        up_read(&mm->mmap_sem);
-        mmput(mm);
-out:
-        return result;
-}
-
 static void pad_len_spaces(struct seq_file *m, int len)
 {
         len = 25 + sizeof(void*) * 6 - len;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 8011528518bd..4b4f9cc2f186 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -1,6 +1,7 @@
 
 #include <linux/mm.h>
 #include <linux/file.h>
+#include <linux/fdtable.h>
 #include <linux/mount.h>
 #include <linux/ptrace.h>
 #include <linux/seq_file.h>
@@ -103,40 +104,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
         return size;
 }
 
-int proc_exe_link(struct inode *inode, struct path *path)
-{
-        struct vm_list_struct *vml;
-        struct vm_area_struct *vma;
-        struct task_struct *task = get_proc_task(inode);
-        struct mm_struct *mm = get_task_mm(task);
-        int result = -ENOENT;
-
-        if (!mm)
-                goto out;
-        down_read(&mm->mmap_sem);
-
-        vml = mm->context.vmlist;
-        vma = NULL;
-        while (vml) {
-                if ((vml->vma->vm_flags & VM_EXECUTABLE) && vml->vma->vm_file) {
-                        vma = vml->vma;
-                        break;
-                }
-                vml = vml->next;
-        }
-
-        if (vma) {
-                *path = vma->vm_file->f_path;
-                path_get(&vma->vm_file->f_path);
-                result = 0;
-        }
-
-        up_read(&mm->mmap_sem);
-        mmput(mm);
-out:
-        return result;
-}
-
 /*
  * display mapping lines for a particular process's /proc/pid/maps
  */