Merge branch 'master' into for-next

Sync with Linus' branch in order to be able to apply fixups
of more recent patches.

1 files changed, 133 insertions, 131 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index c7c64272b0fa..617db4e0faa0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -405,11 +405,11 @@ print0:
 
 static int lock_trace(struct task_struct *task)
 {
-	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	int err = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 		return -EPERM;
 	}
 	return 0;
@@ -417,7 +417,7 @@ static int lock_trace(struct task_struct *task)
 
 static void unlock_trace(struct task_struct *task)
 {
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -551,8 +551,17 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 {
 	unsigned long totalpages = totalram_pages() + total_swap_pages;
 	unsigned long points = 0;
+	long badness;
+
+	badness = oom_badness(task, totalpages);
+	/*
+	 * Special case OOM_SCORE_ADJ_MIN for all others scale the
+	 * badness value into [0, 2000] range which we have been
+	 * exporting for a long time so userspace might depend on it.
+	 */
+	if (badness != LONG_MIN)
+		points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3;
 
-	points = oom_badness(task, totalpages) * 1000 / totalpages;
 	seq_printf(m, "%lu\n", points);
 
 	return 0;
@@ -697,13 +706,21 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr)
  * May current process learn task's sched/cmdline info (for hide_pid_min=1)
  * or euid/egid (for hide_pid_min=2)?
  */
-static bool has_pid_permissions(struct pid_namespace *pid,
+static bool has_pid_permissions(struct proc_fs_info *fs_info,
 				 struct task_struct *task,
-				 int hide_pid_min)
+				 enum proc_hidepid hide_pid_min)
 {
-	if (pid->hide_pid < hide_pid_min)
+	/*
+	 * If 'hidpid' mount option is set force a ptrace check,
+	 * we indicate that we are using a filesystem syscall
+	 * by passing PTRACE_MODE_READ_FSCREDS
+	 */
+	if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE)
+		return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+
+	if (fs_info->hide_pid < hide_pid_min)
 		return true;
-	if (in_group_p(pid->pid_gid))
+	if (in_group_p(fs_info->pid_gid))
 		return true;
 	return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
@@ -711,18 +728,18 @@ static bool has_pid_permissions(struct pid_namespace *pid,
 
 static int proc_pid_permission(struct inode *inode, int mask)
 {
-	struct pid_namespace *pid = proc_pid_ns(inode);
+	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
 	struct task_struct *task;
 	bool has_perms;
 
 	task = get_proc_task(inode);
 	if (!task)
 		return -ESRCH;
-	has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
+	has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS);
 	put_task_struct(task);
 
 	if (!has_perms) {
-		if (pid->hide_pid == HIDEPID_INVISIBLE) {
+		if (fs_info->hide_pid == HIDEPID_INVISIBLE) {
 			/*
 			 * Let's make getdents(), stat(), and open()
 			 * consistent with each other.  If a process
@@ -746,7 +763,7 @@ static const struct inode_operations proc_def_inode_operations = {
 static int proc_single_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns = proc_pid_ns(inode);
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
 	struct pid *pid = proc_pid(inode);
 	struct task_struct *task;
 	int ret;
@@ -1415,7 +1432,7 @@ static const struct file_operations proc_fail_nth_operations = {
 static int sched_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns = proc_pid_ns(inode);
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
 	struct task_struct *p;
 
 	p = get_proc_task(inode);
@@ -1573,6 +1590,7 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 	noffsets = 0;
 	for (pos = kbuf; pos; pos = next_line) {
 		struct proc_timens_offset *off = &offsets[noffsets];
+		char clock[10];
 		int err;
 
 		/* Find the end of line and ensure we don't look past it */
@@ -1584,10 +1602,21 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 				next_line = NULL;
 		}
 
-		err = sscanf(pos, "%u %lld %lu", &off->clockid,
+		err = sscanf(pos, "%9s %lld %lu", clock,
 				&off->val.tv_sec, &off->val.tv_nsec);
 		if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC)
 			goto out;
+
+		clock[sizeof(clock) - 1] = 0;
+		if (strcmp(clock, "monotonic") == 0 ||
+		    strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0)
+			off->clockid = CLOCK_MONOTONIC;
+		else if (strcmp(clock, "boottime") == 0 ||
+			 strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0)
+			off->clockid = CLOCK_BOOTTIME;
+		else
+			goto out;
+
 		noffsets++;
 		if (noffsets == ARRAY_SIZE(offsets)) {
 			if (next_line)
@@ -1834,11 +1863,25 @@ void task_dump_owner(struct task_struct *task, umode_t mode,
 	*rgid = gid;
 }
 
+void proc_pid_evict_inode(struct proc_inode *ei)
+{
+	struct pid *pid = ei->pid;
+
+	if (S_ISDIR(ei->vfs_inode.i_mode)) {
+		spin_lock(&pid->lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(&pid->lock);
+	}
+
+	put_pid(pid);
+}
+
 struct inode *proc_pid_make_inode(struct super_block * sb,
 				  struct task_struct *task, umode_t mode)
 {
 	struct inode * inode;
 	struct proc_inode *ei;
+	struct pid *pid;
 
 	/* We need a new inode */
 
@@ -1856,10 +1899,18 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 	/*
 	 * grab the reference to task.
 	 */
-	ei->pid = get_task_pid(task, PIDTYPE_PID);
-	if (!ei->pid)
+	pid = get_task_pid(task, PIDTYPE_PID);
+	if (!pid)
 		goto out_unlock;
 
+	/* Let the pid remember us for quick removal */
+	ei->pid = pid;
+	if (S_ISDIR(mode)) {
+		spin_lock(&pid->lock);
+		hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes);
+		spin_unlock(&pid->lock);
+	}
+
 	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 	security_task_to_inode(task, inode);
 
@@ -1875,7 +1926,7 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	struct pid_namespace *pid = proc_pid_ns(inode);
+	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
 	struct task_struct *task;
 
 	generic_fillattr(inode, stat);
@@ -1885,7 +1936,7 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 	rcu_read_lock();
 	task = pid_task(proc_pid(inode), PIDTYPE_PID);
 	if (task) {
-		if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
+		if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) {
 			rcu_read_unlock();
 			/*
 			 * This doesn't prevent learning whether PID exists,
@@ -2070,11 +2121,11 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out;
 
 	if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
-		status = down_read_killable(&mm->mmap_sem);
+		status = mmap_read_lock_killable(mm);
 		if (!status) {
 			exact_vma_exists = !!find_exact_vma(mm, vm_start,
 							    vm_end);
-			up_read(&mm->mmap_sem);
+			mmap_read_unlock(mm);
 		}
 	}
 
@@ -2121,7 +2172,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
 	if (rc)
 		goto out_mmput;
 
-	rc = down_read_killable(&mm->mmap_sem);
+	rc = mmap_read_lock_killable(mm);
 	if (rc)
 		goto out_mmput;
 
@@ -2132,7 +2183,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
 		path_get(path);
 		rc = 0;
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 out_mmput:
 	mmput(mm);
@@ -2147,16 +2198,16 @@ struct map_files_info {
 };
 
 /*
- * Only allow CAP_SYS_ADMIN to follow the links, due to concerns about how the
- * symlinks may be used to bypass permissions on ancestor directories in the
- * path to the file in question.
+ * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due
+ * to concerns about how the symlinks may be used to bypass permissions on
+ * ancestor directories in the path to the file in question.
  */
 static const char *
 proc_map_files_get_link(struct dentry *dentry,
 			struct inode *inode,
 		        struct delayed_call *done)
 {
-	if (!capable(CAP_SYS_ADMIN))
+	if (!checkpoint_restore_ns_capable(&init_user_ns))
 		return ERR_PTR(-EPERM);
 
 	return proc_pid_get_link(dentry, inode, done);
@@ -2222,7 +2273,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 		goto out_put_task;
 
 	result = ERR_PTR(-EINTR);
-	if (down_read_killable(&mm->mmap_sem))
+	if (mmap_read_lock_killable(mm))
 		goto out_put_mm;
 
 	result = ERR_PTR(-ENOENT);
@@ -2235,7 +2286,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 				(void *)(unsigned long)vma->vm_file->f_mode);
 
 out_no_vma:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 out_put_mm:
 	mmput(mm);
 out_put_task:
@@ -2280,7 +2331,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	if (!mm)
 		goto out_put_task;
 
-	ret = down_read_killable(&mm->mmap_sem);
+	ret = mmap_read_lock_killable(mm);
 	if (ret) {
 		mmput(mm);
 		goto out_put_task;
@@ -2291,11 +2342,11 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	/*
 	 * We need two passes here:
 	 *
-	 *  1) Collect vmas of mapped files with mmap_sem taken
-	 *  2) Release mmap_sem and instantiate entries
+	 *  1) Collect vmas of mapped files with mmap_lock taken
+	 *  2) Release mmap_lock and instantiate entries
 	 *
 	 * otherwise we get lockdep complained, since filldir()
-	 * routine might require mmap_sem taken in might_fault().
+	 * routine might require mmap_lock taken in might_fault().
 	 */
 
 	for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
@@ -2307,7 +2358,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL);
 		if (!p) {
 			ret = -ENOMEM;
-			up_read(&mm->mmap_sem);
+			mmap_read_unlock(mm);
 			mmput(mm);
 			goto out_put_task;
 		}
@@ -2316,7 +2367,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		p->end = vma->vm_end;
 		p->mode = vma->vm_file->f_mode;
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	mmput(mm);
 
 	for (i = 0; i < nr_files; i++) {
@@ -2436,7 +2487,7 @@ static int proc_timers_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	tp->pid = proc_pid(inode);
-	tp->ns = proc_pid_ns(inode);
+	tp->ns = proc_pid_ns(inode->i_sb);
 	return 0;
 }
 
@@ -2736,6 +2787,15 @@ static const struct pid_entry smack_attr_dir_stuff[] = {
 LSM_DIR_OPS(smack);
 #endif
 
+#ifdef CONFIG_SECURITY_APPARMOR
+static const struct pid_entry apparmor_attr_dir_stuff[] = {
+	ATTR("apparmor", "current",	0666),
+	ATTR("apparmor", "prev",	0444),
+	ATTR("apparmor", "exec",	0666),
+};
+LSM_DIR_OPS(apparmor);
+#endif
+
 static const struct pid_entry attr_dir_stuff[] = {
 	ATTR(NULL, "current",		0666),
 	ATTR(NULL, "prev",		0444),
@@ -2747,6 +2807,10 @@ static const struct pid_entry attr_dir_stuff[] = {
 	DIR("smack",			0555,
 	    proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
 #endif
+#ifdef CONFIG_SECURITY_APPARMOR
+	DIR("apparmor",			0555,
+	    proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops),
+#endif
 };
 
 static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
@@ -2861,7 +2925,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	unsigned long flags;
 	int result;
 
-	result = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	result = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (result)
 		return result;
 
@@ -2897,7 +2961,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	result = 0;
 
 out_unlock:
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 	return result;
 }
 
@@ -3230,90 +3294,28 @@ static const struct inode_operations proc_tgid_base_inode_operations = {
 	.permission	= proc_pid_permission,
 };
 
-static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
-{
-	struct dentry *dentry, *leader, *dir;
-	char buf[10 + 1];
-	struct qstr name;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", pid);
-	/* no ->d_hash() rejects on procfs */
-	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
-	if (dentry) {
-		d_invalidate(dentry);
-		dput(dentry);
-	}
-
-	if (pid == tgid)
-		return;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", tgid);
-	leader = d_hash_and_lookup(mnt->mnt_root, &name);
-	if (!leader)
-		goto out;
-
-	name.name = "task";
-	name.len = strlen(name.name);
-	dir = d_hash_and_lookup(leader, &name);
-	if (!dir)
-		goto out_put_leader;
-
-	name.name = buf;
-	name.len = snprintf(buf, sizeof(buf), "%u", pid);
-	dentry = d_hash_and_lookup(dir, &name);
-	if (dentry) {
-		d_invalidate(dentry);
-		dput(dentry);
-	}
-
-	dput(dir);
-out_put_leader:
-	dput(leader);
-out:
-	return;
-}
-
 /**
- * proc_flush_task -  Remove dcache entries for @task from the /proc dcache.
- * @task: task that should be flushed.
- *
- * When flushing dentries from proc, one needs to flush them from global
- * proc (proc_mnt) and from all the namespaces' procs this task was seen
- * in. This call is supposed to do all of this job.
+ * proc_flush_pid -  Remove dcache entries for @pid from the /proc dcache.
+ * @pid: pid that should be flushed.
  *
- * Looks in the dcache for
- * /proc/@pid
- * /proc/@tgid/task/@pid
- * if either directory is present flushes it and all of it'ts children
- * from the dcache.
+ * This function walks a list of inodes (that belong to any proc
+ * filesystem) that are attached to the pid and flushes them from
+ * the dentry cache.
  *
  * It is safe and reasonable to cache /proc entries for a task until
  * that task exits.  After that they just clog up the dcache with
  * useless entries, possibly causing useful dcache entries to be
- * flushed instead.  This routine is proved to flush those useless
- * dcache entries at process exit time.
+ * flushed instead.  This routine is provided to flush those useless
+ * dcache entries when a process is reaped.
  *
  * NOTE: This routine is just an optimization so it does not guarantee
- *       that no dcache entries will exist at process exit time it
- *       just makes it very unlikely that any will persist.
+ *       that no dcache entries will exist after a process is reaped
+ *       it just makes it very unlikely that any will persist.
  */
 
-void proc_flush_task(struct task_struct *task)
+void proc_flush_pid(struct pid *pid)
 {
-	int i;
-	struct pid *pid, *tgid;
-	struct upid *upid;
-
-	pid = task_pid(task);
-	tgid = task_tgid(task);
-
-	for (i = 0; i <= pid->level; i++) {
-		upid = &pid->numbers[i];
-		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
-					tgid->numbers[i].nr);
-	}
+	proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock);
 }
 
 static struct dentry *proc_pid_instantiate(struct dentry * dentry,
@@ -3340,6 +3342,7 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 {
 	struct task_struct *task;
 	unsigned tgid;
+	struct proc_fs_info *fs_info;
 	struct pid_namespace *ns;
 	struct dentry *result = ERR_PTR(-ENOENT);
 
@@ -3347,7 +3350,8 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 	if (tgid == ~0U)
 		goto out;
 
-	ns = dentry->d_sb->s_fs_info;
+	fs_info = proc_sb_info(dentry->d_sb);
+	ns = fs_info->pid_ns;
 	rcu_read_lock();
 	task = find_task_by_pid_ns(tgid, ns);
 	if (task)
@@ -3356,7 +3360,14 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 	if (!task)
 		goto out;
 
+	/* Limit procfs to only ptraceable tasks */
+	if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) {
+		if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS))
+			goto out_put_task;
+	}
+
 	result = proc_pid_instantiate(dentry, task, NULL);
+out_put_task:
 	put_task_struct(task);
 out:
 	return result;
@@ -3382,20 +3393,8 @@ retry:
 	pid = find_ge_pid(iter.tgid, ns);
 	if (pid) {
 		iter.tgid = pid_nr_ns(pid, ns);
-		iter.task = pid_task(pid, PIDTYPE_PID);
-		/* What we to know is if the pid we have find is the
-		 * pid of a thread_group_leader.  Testing for task
-		 * being a thread_group_leader is the obvious thing
-		 * todo but there is a window when it fails, due to
-		 * the pid transfer logic in de_thread.
-		 *
-		 * So we perform the straight forward test of seeing
-		 * if the pid we have found is the pid of a thread
-		 * group leader, and don't worry if the task we have
-		 * found doesn't happen to be a thread group leader.
-		 * As we don't care in the case of readdir.
-		 */
-		if (!iter.task || !has_group_leader_pid(iter.task)) {
+		iter.task = pid_task(pid, PIDTYPE_TGID);
+		if (!iter.task) {
 			iter.tgid += 1;
 			goto retry;
 		}
@@ -3411,20 +3410,21 @@ retry:
 int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct tgid_iter iter;
-	struct pid_namespace *ns = proc_pid_ns(file_inode(file));
+	struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb);
+	struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb);
 	loff_t pos = ctx->pos;
 
 	if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
 		return 0;
 
 	if (pos == TGID_OFFSET - 2) {
-		struct inode *inode = d_inode(ns->proc_self);
+		struct inode *inode = d_inode(fs_info->proc_self);
 		if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
 			return 0;
 		ctx->pos = pos = pos + 1;
 	}
 	if (pos == TGID_OFFSET - 1) {
-		struct inode *inode = d_inode(ns->proc_thread_self);
+		struct inode *inode = d_inode(fs_info->proc_thread_self);
 		if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
 			return 0;
 		ctx->pos = pos = pos + 1;
@@ -3438,7 +3438,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 		unsigned int len;
 
 		cond_resched();
-		if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
+		if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE))
 			continue;
 
 		len = snprintf(name, sizeof(name), "%u", iter.tgid);
@@ -3638,6 +3638,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	struct task_struct *task;
 	struct task_struct *leader = get_proc_task(dir);
 	unsigned tid;
+	struct proc_fs_info *fs_info;
 	struct pid_namespace *ns;
 	struct dentry *result = ERR_PTR(-ENOENT);
 
@@ -3648,7 +3649,8 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	if (tid == ~0U)
 		goto out;
 
-	ns = dentry->d_sb->s_fs_info;
+	fs_info = proc_sb_info(dentry->d_sb);
+	ns = fs_info->pid_ns;
 	rcu_read_lock();
 	task = find_task_by_pid_ns(tid, ns);
 	if (task)
@@ -3762,7 +3764,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	/* f_version caches the tgid value that the last readdir call couldn't
 	 * return. lseek aka telldir automagically resets f_version to 0.
 	 */
-	ns = proc_pid_ns(inode);
+	ns = proc_pid_ns(inode->i_sb);
 	tid = (int)file->f_version;
 	file->f_version = 0;
 	for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);