11 files changed, 211 insertions, 121 deletions

diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 712f24db9600..ab30716584f5 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -5,7 +5,7 @@
 obj-y   += proc.o
 
 proc-y                  := nommu.o task_nommu.o
-proc-$(CONFIG_MMU)      := mmu.o task_mmu.o
+proc-$(CONFIG_MMU)      := task_mmu.o
 
 proc-y       += inode.o root.o base.o generic.o array.o \
                 fd.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f7ed9ee46eb9..cbd0f1b324b9 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -143,6 +143,7 @@ static const char * const task_state_array[] = {
         "x (dead)",             /*  64 */
         "K (wakekill)",         /* 128 */
         "W (waking)",           /* 256 */
+        "P (parked)",           /* 512 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 69078c7cef1f..a19308604145 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -86,6 +86,7 @@
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
 #include <linux/flex_array.h>
+#include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
@@ -2013,6 +2014,102 @@ static const struct file_operations proc_map_files_operations = {
         .llseek         = default_llseek,
 };
 
+struct timers_private {
+        struct pid *pid;
+        struct task_struct *task;
+        struct sighand_struct *sighand;
+        struct pid_namespace *ns;
+        unsigned long flags;
+};
+
+static void *timers_start(struct seq_file *m, loff_t *pos)
+{
+        struct timers_private *tp = m->private;
+
+        tp->task = get_pid_task(tp->pid, PIDTYPE_PID);
+        if (!tp->task)
+                return ERR_PTR(-ESRCH);
+
+        tp->sighand = lock_task_sighand(tp->task, &tp->flags);
+        if (!tp->sighand)
+                return ERR_PTR(-ESRCH);
+
+        return seq_list_start(&tp->task->signal->posix_timers, *pos);
+}
+
+static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct timers_private *tp = m->private;
+        return seq_list_next(v, &tp->task->signal->posix_timers, pos);
+}
+
+static void timers_stop(struct seq_file *m, void *v)
+{
+        struct timers_private *tp = m->private;
+
+        if (tp->sighand) {
+                unlock_task_sighand(tp->task, &tp->flags);
+                tp->sighand = NULL;
+        }
+
+        if (tp->task) {
+                put_task_struct(tp->task);
+                tp->task = NULL;
+        }
+}
+
+static int show_timer(struct seq_file *m, void *v)
+{
+        struct k_itimer *timer;
+        struct timers_private *tp = m->private;
+        int notify;
+        static char *nstr[] = {
+                [SIGEV_SIGNAL] = "signal",
+                [SIGEV_NONE] = "none",
+                [SIGEV_THREAD] = "thread",
+        };
+
+        timer = list_entry((struct list_head *)v, struct k_itimer, list);
+        notify = timer->it_sigev_notify;
+
+        seq_printf(m, "ID: %d\n", timer->it_id);
+        seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo,
+                        timer->sigq->info.si_value.sival_ptr);
+        seq_printf(m, "notify: %s/%s.%d\n",
+                nstr[notify & ~SIGEV_THREAD_ID],
+                (notify & SIGEV_THREAD_ID) ? "tid" : "pid",
+                pid_nr_ns(timer->it_pid, tp->ns));
+
+        return 0;
+}
+
+static const struct seq_operations proc_timers_seq_ops = {
+        .start  = timers_start,
+        .next   = timers_next,
+        .stop   = timers_stop,
+        .show   = show_timer,
+};
+
+static int proc_timers_open(struct inode *inode, struct file *file)
+{
+        struct timers_private *tp;
+
+        tp = __seq_open_private(file, &proc_timers_seq_ops,
+                        sizeof(struct timers_private));
+        if (!tp)
+                return -ENOMEM;
+
+        tp->pid = proc_pid(inode);
+        tp->ns = inode->i_sb->s_fs_info;
+        return 0;
+}
+
+static const struct file_operations proc_timers_operations = {
+        .open           = proc_timers_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release_private,
+};
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 
 static struct dentry *proc_pident_instantiate(struct inode *dir,
@@ -2583,6 +2680,9 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
         REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
 #endif
+#ifdef CONFIG_CHECKPOINT_RESTORE
+        REG("timers",     S_IRUGO, proc_timers_operations),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 4b3b3ffb52f1..21e1a8f1659d 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde)
                 free_proc_entry(pde);
 }
 
-/*
- * Remove a /proc entry and free it if it's not currently in use.
- */
-void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+static void entry_rundown(struct proc_dir_entry *de)
 {
-        struct proc_dir_entry **p;
-        struct proc_dir_entry *de = NULL;
-        const char *fn = name;
-        unsigned int len;
-
-        spin_lock(&proc_subdir_lock);
-        if (__xlate_proc_name(name, &parent, &fn) != 0) {
-                spin_unlock(&proc_subdir_lock);
-                return;
-        }
-        len = strlen(fn);
-
-        for (p = &parent->subdir; *p; p=&(*p)->next ) {
-                if (proc_match(len, fn, *p)) {
-                        de = *p;
-                        *p = de->next;
-                        de->next = NULL;
-                        break;
-                }
-        }
-        spin_unlock(&proc_subdir_lock);
-        if (!de) {
-                WARN(1, "name '%s'\n", name);
-                return;
-        }
-
         spin_lock(&de->pde_unload_lock);
         /*
          * Stop accepting new callers into module. If you're
@@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
                 spin_lock(&de->pde_unload_lock);
         }
         spin_unlock(&de->pde_unload_lock);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+        struct proc_dir_entry **p;
+        struct proc_dir_entry *de = NULL;
+        const char *fn = name;
+        unsigned int len;
+
+        spin_lock(&proc_subdir_lock);
+        if (__xlate_proc_name(name, &parent, &fn) != 0) {
+                spin_unlock(&proc_subdir_lock);
+                return;
+        }
+        len = strlen(fn);
+
+        for (p = &parent->subdir; *p; p=&(*p)->next ) {
+                if (proc_match(len, fn, *p)) {
+                        de = *p;
+                        *p = de->next;
+                        de->next = NULL;
+                        break;
+                }
+        }
+        spin_unlock(&proc_subdir_lock);
+        if (!de) {
+                WARN(1, "name '%s'\n", name);
+                return;
+        }
+
+        entry_rundown(de);
 
         if (S_ISDIR(de->mode))
                 parent->nlink--;
@@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
         pde_put(de);
 }
 EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+        struct proc_dir_entry **p;
+        struct proc_dir_entry *root = NULL, *de, *next;
+        const char *fn = name;
+        unsigned int len;
+
+        spin_lock(&proc_subdir_lock);
+        if (__xlate_proc_name(name, &parent, &fn) != 0) {
+                spin_unlock(&proc_subdir_lock);
+                return -ENOENT;
+        }
+        len = strlen(fn);
+
+        for (p = &parent->subdir; *p; p=&(*p)->next ) {
+                if (proc_match(len, fn, *p)) {
+                        root = *p;
+                        *p = root->next;
+                        root->next = NULL;
+                        break;
+                }
+        }
+        if (!root) {
+                spin_unlock(&proc_subdir_lock);
+                return -ENOENT;
+        }
+        de = root;
+        while (1) {
+                next = de->subdir;
+                if (next) {
+                        de->subdir = next->next;
+                        next->next = NULL;
+                        de = next;
+                        continue;
+                }
+                spin_unlock(&proc_subdir_lock);
+
+                entry_rundown(de);
+                next = de->parent;
+                if (S_ISDIR(de->mode))
+                        next->nlink--;
+                de->nlink = 0;
+                if (de == root)
+                        break;
+                pde_put(de);
+
+                spin_lock(&proc_subdir_lock);
+                de = next;
+        }
+        pde_put(root);
+        return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a86aebc9ba7c..869116c2afbe 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -446,9 +446,10 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
-        struct inode *inode = iget_locked(sb, de->low_ino);
+        struct inode *inode = new_inode_pseudo(sb);
 
-        if (inode && (inode->i_state & I_NEW)) {
+        if (inode) {
+                inode->i_ino = de->low_ino;
                 inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
                 PROC_I(inode)->pde = de;
 
@@ -476,7 +477,6 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
                                 inode->i_fop = de->proc_fops;
                         }
                 }
-                unlock_new_inode(inode);
         } else
                pde_put(de);
         return inode;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 85ff3a4598b3..75710357a517 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -30,24 +30,6 @@ extern int proc_net_init(void);
 static inline int proc_net_init(void) { return 0; }
 #endif
 
-struct vmalloc_info {
-        unsigned long   used;
-        unsigned long   largest_chunk;
-};
-
-#ifdef CONFIG_MMU
-#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
-extern void get_vmalloc_info(struct vmalloc_info *vmi);
-#else
-
-#define VMALLOC_TOTAL 0UL
-#define get_vmalloc_info(vmi)                   \
-do {                                            \
-        (vmi)->used = 0;                        \
-        (vmi)->largest_chunk = 0;               \
-} while(0)
-#endif
-
 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/kcore.c b/fs/proc/kcore.c
index eda6f017f272..f6a13f489e30 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -15,6 +15,7 @@
 #include <linux/capability.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
+#include <linux/notifier.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/printk.h>
@@ -564,7 +565,6 @@ static const struct file_operations proc_kcore_operations = {
         .llseek         = default_llseek,
 };
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /* just remember that we have to update kcore */
 static int __meminit kcore_callback(struct notifier_block *self,
                                     unsigned long action, void *arg)
@@ -578,8 +578,11 @@ static int __meminit kcore_callback(struct notifier_block *self,
         }
         return NOTIFY_OK;
 }
-#endif
 
+static struct notifier_block kcore_callback_nb __meminitdata = {
+        .notifier_call = kcore_callback,
+        .priority = 0,
+};
 
 static struct kcore_list kcore_vmalloc;
 
@@ -631,7 +634,7 @@ static int __init proc_kcore_init(void)
         add_modules_range();
         /* Store direct-map area from physical memory map */
         kcore_update_ram();
-        hotplug_memory_notifier(kcore_callback, 0);
+        register_hotmemory_notifier(&kcore_callback_nb);
 
         return 0;
 }
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 1efaaa19c4f3..5aa847a603c0 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -11,6 +11,7 @@
 #include <linux/swap.h>
 #include <linux/vmstat.h>
 #include <linux/atomic.h>
+#include <linux/vmalloc.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include "internal.h"
diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c
deleted file mode 100644
index 8ae221dfd010..000000000000
--- a/fs/proc/mmu.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/* mmu.c: mmu memory info files
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/spinlock.h>
-#include <linux/vmalloc.h>
-#include <linux/highmem.h>
-#include <asm/pgtable.h>
-#include "internal.h"
-
-void get_vmalloc_info(struct vmalloc_info *vmi)
-{
-        struct vm_struct *vma;
-        unsigned long free_area_size;
-        unsigned long prev_end;
-
-        vmi->used = 0;
-
-        if (!vmlist) {
-                vmi->largest_chunk = VMALLOC_TOTAL;
-        }
-        else {
-                vmi->largest_chunk = 0;
-
-                prev_end = VMALLOC_START;
-
-                read_lock(&vmlist_lock);
-
-                for (vma = vmlist; vma; vma = vma->next) {
-                        unsigned long addr = (unsigned long) vma->addr;
-
-                        /*
-                         * Some archs keep another range for modules in vmlist
-                         */
-                        if (addr < VMALLOC_START)
-                                continue;
-                        if (addr >= VMALLOC_END)
-                                break;
-
-                        vmi->used += vma->size;
-
-                        free_area_size = addr - prev_end;
-                        if (vmi->largest_chunk < free_area_size)
-                                vmi->largest_chunk = free_area_size;
-
-                        prev_end = vma->size + addr;
-                }
-
-                if (VMALLOC_END - prev_end > vmi->largest_chunk)
-                        vmi->largest_chunk = VMALLOC_END - prev_end;
-
-                read_unlock(&vmlist_lock);
-        }
-}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index b7a47196c8c3..66b51c0383da 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -118,7 +118,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
         struct super_block *sb = inode->i_sb;
         struct proc_inode *ei = PROC_I(inode);
         struct task_struct *task;
-        struct dentry *ns_dentry;
+        struct path ns_path;
         void *error = ERR_PTR(-EACCES);
 
         task = get_proc_task(inode);
@@ -128,14 +128,14 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
         if (!ptrace_may_access(task, PTRACE_MODE_READ))
                 goto out_put_task;
 
-        ns_dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
-        if (IS_ERR(ns_dentry)) {
-                error = ERR_CAST(ns_dentry);
+        ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
+        if (IS_ERR(ns_path.dentry)) {
+                error = ERR_CAST(ns_path.dentry);
                 goto out_put_task;
         }
 
-        dput(nd->path.dentry);
-        nd->path.dentry = ns_dentry;
+        ns_path.mnt = mntget(nd->path.mnt);
+        nd_jump_link(nd, &ns_path);
         error = NULL;
 
 out_put_task:
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac26bac..9c7fab1d23f0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
+#include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
@@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
         } else {
                 ns = task_active_pid_ns(current);
                 options = data;
+
+                if (!current_user_ns()->may_mount_proc)
+                        return ERR_PTR(-EPERM);
         }
 
         sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);