6 files changed, 318 insertions, 108 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 4cb81776a7ff..965625a0977d 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -289,6 +289,15 @@ static inline char *task_cap(struct task_struct *p, char *buffer)
                             cap_t(p->cap_effective));
 }
 
+static inline char *task_context_switch_counts(struct task_struct *p,
+                                                char *buffer)
+{
+        return buffer + sprintf(buffer, "voluntary_ctxt_switches:\t%lu\n"
+                            "nonvoluntary_ctxt_switches:\t%lu\n",
+                            p->nvcsw,
+                            p->nivcsw);
+}
+
 int proc_pid_status(struct task_struct *task, char *buffer)
 {
         char *orig = buffer;
@@ -307,6 +316,7 @@ int proc_pid_status(struct task_struct *task, char *buffer)
 #if defined(CONFIG_S390)
         buffer = task_show_regs(task, buffer);
 #endif
+        buffer = task_context_switch_counts(task, buffer);
         return buffer - orig;
 }
 
@@ -439,8 +449,9 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 
         /* Temporary variable needed for gcc-2.96 */
         /* convert timespec -> nsec*/
-        start_time = (unsigned long long)task->start_time.tv_sec * NSEC_PER_SEC
-                                + task->start_time.tv_nsec;
+        start_time =
+                (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC
+                                + task->real_start_time.tv_nsec;
         /* convert nsec -> ticks */
         start_time = nsec_to_clock_t(start_time);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 46ea5d56e1bb..ae3627337a92 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -67,7 +67,6 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
-#include <linux/seccomp.h>
 #include <linux/cpuset.h>
 #include <linux/audit.h>
 #include <linux/poll.h>
@@ -204,12 +203,17 @@ static int proc_pid_environ(struct task_struct *task, char * buffer)
         int res = 0;
         struct mm_struct *mm = get_task_mm(task);
         if (mm) {
-                unsigned int len = mm->env_end - mm->env_start;
+                unsigned int len;
+
+                res = -ESRCH;
+                if (!ptrace_may_attach(task))
+                        goto out;
+
+                len  = mm->env_end - mm->env_start;
                 if (len > PAGE_SIZE)
                         len = PAGE_SIZE;
                 res = access_process_vm(task, mm->env_start, buffer, len, 0);
-                if (!ptrace_may_attach(task))
-                        res = -ESRCH;
+out:
                 mmput(mm);
         }
         return res;
@@ -812,71 +816,6 @@ static const struct file_operations proc_loginuid_operations = {
 };
 #endif
 
-#ifdef CONFIG_SECCOMP
-static ssize_t seccomp_read(struct file *file, char __user *buf,
-                            size_t count, loff_t *ppos)
-{
-        struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode);
-        char __buf[20];
-        size_t len;
-
-        if (!tsk)
-                return -ESRCH;
-        /* no need to print the trailing zero, so use only len */
-        len = sprintf(__buf, "%u\n", tsk->seccomp.mode);
-        put_task_struct(tsk);
-
-        return simple_read_from_buffer(buf, count, ppos, __buf, len);
-}
-
-static ssize_t seccomp_write(struct file *file, const char __user *buf,
-                             size_t count, loff_t *ppos)
-{
-        struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode);
-        char __buf[20], *end;
-        unsigned int seccomp_mode;
-        ssize_t result;
-
-        result = -ESRCH;
-        if (!tsk)
-                goto out_no_task;
-
-        /* can set it only once to be even more secure */
-        result = -EPERM;
-        if (unlikely(tsk->seccomp.mode))
-                goto out;
-
-        result = -EFAULT;
-        memset(__buf, 0, sizeof(__buf));
-        count = min(count, sizeof(__buf) - 1);
-        if (copy_from_user(__buf, buf, count))
-                goto out;
-
-        seccomp_mode = simple_strtoul(__buf, &end, 0);
-        if (*end == '\n')
-                end++;
-        result = -EINVAL;
-        if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
-                tsk->seccomp.mode = seccomp_mode;
-                set_tsk_thread_flag(tsk, TIF_SECCOMP);
-        } else
-                goto out;
-        result = -EIO;
-        if (unlikely(!(end - __buf)))
-                goto out;
-        result = end - __buf;
-out:
-        put_task_struct(tsk);
-out_no_task:
-        return result;
-}
-
-static const struct file_operations proc_seccomp_operations = {
-        .read           = seccomp_read,
-        .write          = seccomp_write,
-};
-#endif /* CONFIG_SECCOMP */
-
 #ifdef CONFIG_FAULT_INJECTION
 static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
                                       size_t count, loff_t *ppos)
@@ -2037,9 +1976,6 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("numa_maps",  S_IRUGO, numa_maps),
 #endif
         REG("mem",        S_IRUSR|S_IWUSR, mem),
-#ifdef CONFIG_SECCOMP
-        REG("seccomp",    S_IRUSR|S_IWUSR, seccomp),
-#endif
         LNK("cwd",        cwd),
         LNK("root",       root),
         LNK("exe",        exe),
@@ -2324,9 +2260,6 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("numa_maps", S_IRUGO, numa_maps),
 #endif
         REG("mem",       S_IRUSR|S_IWUSR, mem),
-#ifdef CONFIG_SECCOMP
-        REG("seccomp",   S_IRUSR|S_IWUSR, seccomp),
-#endif
         LNK("cwd",       cwd),
         LNK("root",      root),
         LNK("exe",       exe),
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8a40e15f5ecb..b5e7155d30d8 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -20,6 +20,7 @@
 #include <linux/namei.h>
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
+#include <linux/completion.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -529,12 +530,6 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
                 return -EAGAIN;
         dp->low_ino = i;
 
-        spin_lock(&proc_subdir_lock);
-        dp->next = dir->subdir;
-        dp->parent = dir;
-        dir->subdir = dp;
-        spin_unlock(&proc_subdir_lock);
-
         if (S_ISDIR(dp->mode)) {
                 if (dp->proc_iops == NULL) {
                         dp->proc_fops = &proc_dir_operations;
@@ -550,6 +545,13 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
                 if (dp->proc_iops == NULL)
                         dp->proc_iops = &proc_file_inode_operations;
         }
+
+        spin_lock(&proc_subdir_lock);
+        dp->next = dir->subdir;
+        dp->parent = dir;
+        dir->subdir = dp;
+        spin_unlock(&proc_subdir_lock);
+
         return 0;
 }
 
@@ -613,6 +615,9 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent,
         ent->namelen = len;
         ent->mode = mode;
         ent->nlink = nlink;
+        ent->pde_users = 0;
+        spin_lock_init(&ent->pde_unload_lock);
+        ent->pde_unload_completion = NULL;
  out:
         return ent;
 }
@@ -649,9 +654,6 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
 
         ent = proc_create(&parent, name, S_IFDIR | mode, 2);
         if (ent) {
-                ent->proc_fops = &proc_dir_operations;
-                ent->proc_iops = &proc_dir_inode_operations;
-
                 if (proc_register(parent, ent) < 0) {
                         kfree(ent);
                         ent = NULL;
@@ -686,10 +688,6 @@ struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
 
         ent = proc_create(&parent,name,mode,nlink);
         if (ent) {
-                if (S_ISDIR(mode)) {
-                        ent->proc_fops = &proc_dir_operations;
-                        ent->proc_iops = &proc_dir_inode_operations;
-                }
                 if (proc_register(parent, ent) < 0) {
                         kfree(ent);
                         ent = NULL;
@@ -734,9 +732,35 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
                 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);
+
+                        wait_for_completion(de->pde_unload_completion);
+
+                        spin_lock(&proc_subdir_lock);
+                        goto continue_removing;
+                }
+                spin_unlock(&de->pde_unload_lock);
+
+continue_removing:
                 if (S_ISDIR(de->mode))
                         parent->nlink--;
-                proc_kill_inodes(de);
+                if (!S_ISREG(de->mode))
+                        proc_kill_inodes(de);
                 de->nlink = 0;
                 WARN_ON(de->subdir);
                 if (!atomic_read(&de->count))
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d5ce65c68d7b..dd28e86ab422 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/stat.h>
+#include <linux/completion.h>
 #include <linux/file.h>
 #include <linux/limits.h>
 #include <linux/init.h>
@@ -140,6 +141,251 @@ static const struct super_operations proc_sops = {
         .remount_fs     = proc_remount,
 };
 
+static void pde_users_dec(struct proc_dir_entry *pde)
+{
+        spin_lock(&pde->pde_unload_lock);
+        pde->pde_users--;
+        if (pde->pde_unload_completion && pde->pde_users == 0)
+                complete(pde->pde_unload_completion);
+        spin_unlock(&pde->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        loff_t rv = -EINVAL;
+        loff_t (*llseek)(struct file *, loff_t, int);
+
+        spin_lock(&pde->pde_unload_lock);
+        /*
+         * remove_proc_entry() is going to delete PDE (as part of module
+         * cleanup sequence). No new callers into module allowed.
+         */
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        /*
+         * Bump refcount so that remove_proc_entry will wail for ->llseek to
+         * complete.
+         */
+        pde->pde_users++;
+        /*
+         * Save function pointer under lock, to protect against ->proc_fops
+         * NULL'ifying right after ->pde_unload_lock is dropped.
+         */
+        llseek = pde->proc_fops->llseek;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (!llseek)
+                llseek = default_llseek;
+        rv = llseek(file, offset, whence);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        ssize_t rv = -EIO;
+        ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        read = pde->proc_fops->read;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (read)
+                rv = read(file, buf, count, ppos);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        ssize_t rv = -EIO;
+        ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        write = pde->proc_fops->write;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (write)
+                rv = write(file, buf, count, ppos);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        unsigned int rv = 0;
+        unsigned int (*poll)(struct file *, struct poll_table_struct *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        poll = pde->proc_fops->poll;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (poll)
+                rv = poll(file, pts);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        long rv = -ENOTTY;
+        long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long);
+        int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        unlocked_ioctl = pde->proc_fops->unlocked_ioctl;
+        ioctl = pde->proc_fops->ioctl;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (unlocked_ioctl) {
+                rv = unlocked_ioctl(file, cmd, arg);
+                if (rv == -ENOIOCTLCMD)
+                        rv = -EINVAL;
+        } else if (ioctl) {
+                lock_kernel();
+                rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
+                unlock_kernel();
+        }
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        long rv = -ENOTTY;
+        long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        compat_ioctl = pde->proc_fops->compat_ioctl;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (compat_ioctl)
+                rv = compat_ioctl(file, cmd, arg);
+
+        pde_users_dec(pde);
+        return rv;
+}
+#endif
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+        struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+        int rv = -EIO;
+        int (*mmap)(struct file *, struct vm_area_struct *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        mmap = pde->proc_fops->mmap;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (mmap)
+                rv = mmap(file, vma);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+        struct proc_dir_entry *pde = PDE(inode);
+        int rv = 0;
+        int (*open)(struct inode *, struct file *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        open = pde->proc_fops->open;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (open)
+                rv = open(inode, file);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+        struct proc_dir_entry *pde = PDE(inode);
+        int rv = 0;
+        int (*release)(struct inode *, struct file *);
+
+        spin_lock(&pde->pde_unload_lock);
+        if (!pde->proc_fops) {
+                spin_unlock(&pde->pde_unload_lock);
+                return rv;
+        }
+        pde->pde_users++;
+        release = pde->proc_fops->release;
+        spin_unlock(&pde->pde_unload_lock);
+
+        if (release)
+                rv = release(inode, file);
+
+        pde_users_dec(pde);
+        return rv;
+}
+
+static const struct file_operations proc_reg_file_ops = {
+        .llseek         = proc_reg_llseek,
+        .read           = proc_reg_read,
+        .write          = proc_reg_write,
+        .poll           = proc_reg_poll,
+        .unlocked_ioctl = proc_reg_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+        .compat_ioctl   = proc_reg_compat_ioctl,
+#endif
+        .mmap           = proc_reg_mmap,
+        .open           = proc_reg_open,
+        .release        = proc_reg_release,
+};
+
 struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
                                 struct proc_dir_entry *de)
 {
@@ -166,8 +412,12 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
                         inode->i_nlink = de->nlink;
                 if (de->proc_iops)
                         inode->i_op = de->proc_iops;
-                if (de->proc_fops)
-                        inode->i_fop = de->proc_fops;
+                if (de->proc_fops) {
+                        if (S_ISREG(inode->i_mode))
+                                inode->i_fop = &proc_reg_file_ops;
+                        else
+                                inode->i_fop = de->proc_fops;
+                }
         }
 
         return inode;
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 5fd49e47f83a..d24b8d46059a 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -105,6 +105,7 @@ static int uptime_read_proc(char *page, char **start, off_t off,
         cputime_t idletime = cputime_add(init_task.utime, init_task.stime);
 
         do_posix_clock_monotonic_gettime(&uptime);
+        monotonic_to_bootbased(&uptime);
         cputime_to_timespec(idletime, &idle);
         len = sprintf(page,"%lu.%02lu %lu.%02lu\n",
                         (unsigned long) uptime.tv_sec,
@@ -443,12 +444,12 @@ static int show_stat(struct seq_file *p, void *v)
         unsigned long jif;
         cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
         u64 sum = 0;
+        struct timespec boottime;
 
         user = nice = system = idle = iowait =
                 irq = softirq = steal = cputime64_zero;
-        jif = - wall_to_monotonic.tv_sec;
-        if (wall_to_monotonic.tv_nsec)
-                --jif;
+        getboottime(&boottime);
+        jif = boottime.tv_sec;
 
         for_each_possible_cpu(i) {
                 int j;
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index b3a473b0a191..22846225acfa 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -69,7 +69,7 @@ static void show_tty_range(struct seq_file *m, struct tty_driver *p,
 
 static int show_tty_driver(struct seq_file *m, void *v)
 {
-        struct tty_driver *p = v;
+        struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers);
         dev_t from = MKDEV(p->major, p->minor_start);
         dev_t to = from + p->num;
 
@@ -106,22 +106,13 @@ static int show_tty_driver(struct seq_file *m, void *v)
 /* iterator */
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-        struct list_head *p;
-        loff_t l = *pos;
-
         mutex_lock(&tty_mutex);
-        list_for_each(p, &tty_drivers)
-                if (!l--)
-                        return list_entry(p, struct tty_driver, tty_drivers);
-        return NULL;
+        return seq_list_start(&tty_drivers, *pos);
 }
 
 static void *t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-        struct list_head *p = ((struct tty_driver *)v)->tty_drivers.next;
-        (*pos)++;
-        return p==&tty_drivers ? NULL :
-                        list_entry(p, struct tty_driver, tty_drivers);
+        return seq_list_next(v, &tty_drivers, pos);
 }
 
 static void t_stop(struct seq_file *m, void *v)