1 files changed, 200 insertions, 41 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index acb7ef80ea4f..f3d02ca461ec 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -63,6 +63,7 @@
 #include <linux/namei.h>
 #include <linux/mnt_namespace.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
 #include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
@@ -148,18 +149,13 @@ static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
         return count;
 }
 
-static int get_fs_path(struct task_struct *task, struct path *path, bool root)
+static int get_task_root(struct task_struct *task, struct path *root)
 {
-        struct fs_struct *fs;
         int result = -ENOENT;
 
         task_lock(task);
-        fs = task->fs;
-        if (fs) {
-                read_lock(&fs->lock);
-                *path = root ? fs->root : fs->pwd;
-                path_get(path);
-                read_unlock(&fs->lock);
+        if (task->fs) {
+                get_fs_root(task->fs, root);
                 result = 0;
         }
         task_unlock(task);
@@ -172,7 +168,12 @@ static int proc_cwd_link(struct inode *inode, struct path *path)
         int result = -ENOENT;
 
         if (task) {
-                result = get_fs_path(task, path, 0);
+                task_lock(task);
+                if (task->fs) {
+                        get_fs_pwd(task->fs, path);
+                        result = 0;
+                }
+                task_unlock(task);
                 put_task_struct(task);
         }
         return result;
@@ -184,7 +185,7 @@ static int proc_root_link(struct inode *inode, struct path *path)
         int result = -ENOENT;
 
         if (task) {
-                result = get_fs_path(task, path, 1);
+                result = get_task_root(task, path);
                 put_task_struct(task);
         }
         return result;
@@ -225,7 +226,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 {
         struct mm_struct *mm;
 
-        if (mutex_lock_killable(&task->cred_guard_mutex))
+        if (mutex_lock_killable(&task->signal->cred_guard_mutex))
                 return NULL;
 
         mm = get_task_mm(task);
@@ -234,7 +235,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
                 mmput(mm);
                 mm = NULL;
         }
-        mutex_unlock(&task->cred_guard_mutex);
+        mutex_unlock(&task->signal->cred_guard_mutex);
 
         return mm;
 }
@@ -427,17 +428,14 @@ static const struct file_operations proc_lstats_operations = {
 
 #endif
 
-/* The badness from the OOM killer */
-unsigned long badness(struct task_struct *p, unsigned long uptime);
 static int proc_oom_score(struct task_struct *task, char *buffer)
 {
         unsigned long points = 0;
-        struct timespec uptime;
 
-        do_posix_clock_monotonic_gettime(&uptime);
         read_lock(&tasklist_lock);
         if (pid_alive(task))
-                points = badness(task, uptime.tv_sec);
+                points = oom_badness(task, NULL, NULL,
+                                        totalram_pages + total_swap_pages);
         read_unlock(&tasklist_lock);
         return sprintf(buffer, "%lu\n", points);
 }
@@ -561,9 +559,19 @@ static int proc_setattr(struct dentry *dentry, struct iattr *attr)
                 return -EPERM;
 
         error = inode_change_ok(inode, attr);
-        if (!error)
-                error = inode_setattr(inode, attr);
-        return error;
+        if (error)
+                return error;
+
+        if ((attr->ia_valid & ATTR_SIZE) &&
+            attr->ia_size != i_size_read(inode)) {
+                error = vmtruncate(inode, attr->ia_size);
+                if (error)
+                        return error;
+        }
+
+        setattr_copy(inode, attr);
+        mark_inode_dirty(inode);
+        return 0;
 }
 
 static const struct inode_operations proc_def_inode_operations = {
@@ -589,7 +597,7 @@ static int mounts_open_common(struct inode *inode, struct file *file,
                                 get_mnt_ns(ns);
                 }
                 rcu_read_unlock();
-                if (ns && get_fs_path(task, &root, 1) == 0)
+                if (ns && get_task_root(task, &root) == 0)
                         ret = 0;
                 put_task_struct(task);
         }
@@ -763,6 +771,8 @@ static const struct file_operations proc_single_file_operations = {
 static int mem_open(struct inode* inode, struct file* file)
 {
         file->private_data = (void*)((long)current->self_exec_id);
+        /* OK to pass negative loff_t, we can catch out-of-range */
+        file->f_mode |= FMODE_UNSIGNED_OFFSET;
         return 0;
 }
 
@@ -1015,36 +1025,74 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
         memset(buffer, 0, sizeof(buffer));
         if (count > sizeof(buffer) - 1)
                 count = sizeof(buffer) - 1;
-        if (copy_from_user(buffer, buf, count))
-                return -EFAULT;
+        if (copy_from_user(buffer, buf, count)) {
+                err = -EFAULT;
+                goto out;
+        }
 
         err = strict_strtol(strstrip(buffer), 0, &oom_adjust);
         if (err)
-                return -EINVAL;
+                goto out;
         if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
-             oom_adjust != OOM_DISABLE)
-                return -EINVAL;
+             oom_adjust != OOM_DISABLE) {
+                err = -EINVAL;
+                goto out;
+        }
 
         task = get_proc_task(file->f_path.dentry->d_inode);
-        if (!task)
-                return -ESRCH;
+        if (!task) {
+                err = -ESRCH;
+                goto out;
+        }
+
+        task_lock(task);
+        if (!task->mm) {
+                err = -EINVAL;
+                goto err_task_lock;
+        }
+
         if (!lock_task_sighand(task, &flags)) {
-                put_task_struct(task);
-                return -ESRCH;
+                err = -ESRCH;
+                goto err_task_lock;
         }
 
         if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) {
-                unlock_task_sighand(task, &flags);
-                put_task_struct(task);
-                return -EACCES;
+                err = -EACCES;
+                goto err_sighand;
         }
 
-        task->signal->oom_adj = oom_adjust;
+        if (oom_adjust != task->signal->oom_adj) {
+                if (oom_adjust == OOM_DISABLE)
+                        atomic_inc(&task->mm->oom_disable_count);
+                if (task->signal->oom_adj == OOM_DISABLE)
+                        atomic_dec(&task->mm->oom_disable_count);
+        }
 
+        /*
+         * Warn that /proc/pid/oom_adj is deprecated, see
+         * Documentation/feature-removal-schedule.txt.
+         */
+        printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, "
+                        "please use /proc/%d/oom_score_adj instead.\n",
+                        current->comm, task_pid_nr(current),
+                        task_pid_nr(task), task_pid_nr(task));
+        task->signal->oom_adj = oom_adjust;
+        /*
+         * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+         * value is always attainable.
+         */
+        if (task->signal->oom_adj == OOM_ADJUST_MAX)
+                task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX;
+        else
+                task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
+                                                                -OOM_DISABLE;
+err_sighand:
         unlock_task_sighand(task, &flags);
+err_task_lock:
+        task_unlock(task);
         put_task_struct(task);
-
-        return count;
+out:
+        return err < 0 ? err : count;
 }
 
 static const struct file_operations proc_oom_adjust_operations = {
@@ -1053,6 +1101,106 @@ static const struct file_operations proc_oom_adjust_operations = {
         .llseek         = generic_file_llseek,
 };
 
+static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
+                                        size_t count, loff_t *ppos)
+{
+        struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+        char buffer[PROC_NUMBUF];
+        int oom_score_adj = OOM_SCORE_ADJ_MIN;
+        unsigned long flags;
+        size_t len;
+
+        if (!task)
+                return -ESRCH;
+        if (lock_task_sighand(task, &flags)) {
+                oom_score_adj = task->signal->oom_score_adj;
+                unlock_task_sighand(task, &flags);
+        }
+        put_task_struct(task);
+        len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+        return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
+                                        size_t count, loff_t *ppos)
+{
+        struct task_struct *task;
+        char buffer[PROC_NUMBUF];
+        unsigned long flags;
+        long oom_score_adj;
+        int err;
+
+        memset(buffer, 0, sizeof(buffer));
+        if (count > sizeof(buffer) - 1)
+                count = sizeof(buffer) - 1;
+        if (copy_from_user(buffer, buf, count)) {
+                err = -EFAULT;
+                goto out;
+        }
+
+        err = strict_strtol(strstrip(buffer), 0, &oom_score_adj);
+        if (err)
+                goto out;
+        if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
+                        oom_score_adj > OOM_SCORE_ADJ_MAX) {
+                err = -EINVAL;
+                goto out;
+        }
+
+        task = get_proc_task(file->f_path.dentry->d_inode);
+        if (!task) {
+                err = -ESRCH;
+                goto out;
+        }
+
+        task_lock(task);
+        if (!task->mm) {
+                err = -EINVAL;
+                goto err_task_lock;
+        }
+
+        if (!lock_task_sighand(task, &flags)) {
+                err = -ESRCH;
+                goto err_task_lock;
+        }
+
+        if (oom_score_adj < task->signal->oom_score_adj &&
+                        !capable(CAP_SYS_RESOURCE)) {
+                err = -EACCES;
+                goto err_sighand;
+        }
+
+        if (oom_score_adj != task->signal->oom_score_adj) {
+                if (oom_score_adj == OOM_SCORE_ADJ_MIN)
+                        atomic_inc(&task->mm->oom_disable_count);
+                if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+                        atomic_dec(&task->mm->oom_disable_count);
+        }
+        task->signal->oom_score_adj = oom_score_adj;
+        /*
+         * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
+         * always attainable.
+         */
+        if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+                task->signal->oom_adj = OOM_DISABLE;
+        else
+                task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
+                                                        OOM_SCORE_ADJ_MAX;
+err_sighand:
+        unlock_task_sighand(task, &flags);
+err_task_lock:
+        task_unlock(task);
+        put_task_struct(task);
+out:
+        return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_score_adj_operations = {
+        .read           = oom_score_adj_read,
+        .write          = oom_score_adj_write,
+        .llseek         = default_llseek,
+};
+
 #ifdef CONFIG_AUDITSYSCALL
 #define TMPBUFLEN 21
 static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
@@ -1426,7 +1574,7 @@ static int do_proc_readlink(struct path *path, char __user *buffer, int buflen)
         if (!tmp)
                 return -ENOMEM;
 
-        pathname = d_path(path, tmp, PAGE_SIZE);
+        pathname = d_path_with_unreachable(path, tmp, PAGE_SIZE);
         len = PTR_ERR(pathname);
         if (IS_ERR(pathname))
                 goto out;
@@ -1500,6 +1648,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st
 
         /* Common stuff */
         ei = PROC_I(inode);
+        inode->i_ino = get_next_ino();
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
         inode->i_op = &proc_def_inode_operations;
 
@@ -1939,11 +2088,13 @@ static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
 static const struct file_operations proc_fdinfo_file_operations = {
         .open           = nonseekable_open,
         .read           = proc_fdinfo_read,
+        .llseek         = no_llseek,
 };
 
 static const struct file_operations proc_fd_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_readfd,
+        .llseek         = default_llseek,
 };
 
 /*
@@ -2012,6 +2163,7 @@ static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
 static const struct file_operations proc_fdinfo_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_readfdinfo,
+        .llseek         = default_llseek,
 };
 
 /*
@@ -2202,14 +2354,14 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
                 goto out_free;
 
         /* Guard against adverse ptrace interaction */
-        length = mutex_lock_interruptible(&task->cred_guard_mutex);
+        length = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
         if (length < 0)
                 goto out_free;
 
         length = security_setprocattr(task,
                                       (char*)file->f_path.dentry->d_name.name,
                                       (void*)page, count);
-        mutex_unlock(&task->cred_guard_mutex);
+        mutex_unlock(&task->signal->cred_guard_mutex);
 out_free:
         free_page((unsigned long) page);
 out:
@@ -2243,6 +2395,7 @@ static int proc_attr_dir_readdir(struct file * filp,
 static const struct file_operations proc_attr_dir_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_attr_dir_readdir,
+        .llseek         = default_llseek,
 };
 
 static struct dentry *proc_attr_dir_lookup(struct inode *dir,
@@ -2442,6 +2595,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
 
         /* Initialize the inode */
         ei = PROC_I(inode);
+        inode->i_ino = get_next_ino();
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 
         /*
@@ -2575,7 +2729,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         INF("auxv",       S_IRUSR, proc_pid_auxv),
         ONE("status",     S_IRUGO, proc_pid_status),
         ONE("personality", S_IRUSR, proc_pid_personality),
-        INF("limits",     S_IRUSR, proc_pid_limits),
+        INF("limits",     S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
@@ -2625,6 +2779,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
         INF("oom_score",  S_IRUGO, proc_oom_score),
         REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+        REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
         REG("sessionid",  S_IRUGO, proc_sessionid_operations),
@@ -2650,6 +2805,7 @@ static int proc_tgid_base_readdir(struct file * filp,
 static const struct file_operations proc_tgid_base_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_tgid_base_readdir,
+        .llseek         = default_llseek,
 };
 
 static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
@@ -2910,7 +3066,7 @@ static const struct pid_entry tid_base_stuff[] = {
         INF("auxv",      S_IRUSR, proc_pid_auxv),
         ONE("status",    S_IRUGO, proc_pid_status),
         ONE("personality", S_IRUSR, proc_pid_personality),
-        INF("limits",    S_IRUSR, proc_pid_limits),
+        INF("limits",    S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
@@ -2959,6 +3115,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
         INF("oom_score", S_IRUGO, proc_oom_score),
         REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+        REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
         REG("sessionid",  S_IRUSR, proc_sessionid_operations),
@@ -2986,6 +3143,7 @@ static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *den
 static const struct file_operations proc_tid_base_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_tid_base_readdir,
+        .llseek         = default_llseek,
 };
 
 static const struct inode_operations proc_tid_base_inode_operations = {
@@ -3222,4 +3380,5 @@ static const struct inode_operations proc_task_inode_operations = {
 static const struct file_operations proc_task_operations = {
         .read           = generic_read_dir,
         .readdir        = proc_task_readdir,
+        .llseek         = default_llseek,
 };