Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...

1 files changed, 686 insertions, 0 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
new file mode 100644
index 0000000..f045bba
--- /dev/null
+++ b/fs/coredump.c
@@ -0,0 +1,686 @@
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <linux/swap.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/perf_event.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/key.h>
+#include <linux/personality.h>
+#include <linux/binfmts.h>
+#include <linux/utsname.h>
+#include <linux/pid_namespace.h>
+#include <linux/module.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/tsacct_kern.h>
+#include <linux/cn_proc.h>
+#include <linux/audit.h>
+#include <linux/tracehook.h>
+#include <linux/kmod.h>
+#include <linux/fsnotify.h>
+#include <linux/fs_struct.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/oom.h>
+#include <linux/compat.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/tlb.h>
+#include <asm/exec.h>
+
+#include <trace/events/task.h>
+#include "internal.h"
+
+#include <trace/events/sched.h>
+
+int core_uses_pid;
+char core_pattern[CORENAME_MAX_SIZE] = "core";
+unsigned int core_pipe_limit;
+
+struct core_name {
+	char *corename;
+	int used, size;
+};
+static atomic_t call_count = ATOMIC_INIT(1);
+
+/* The maximal length of core_pattern is also specified in sysctl.c */
+
+static int expand_corename(struct core_name *cn)
+{
+	char *old_corename = cn->corename;
+
+	cn->size = CORENAME_MAX_SIZE * atomic_inc_return(&call_count);
+	cn->corename = krealloc(old_corename, cn->size, GFP_KERNEL);
+
+	if (!cn->corename) {
+		kfree(old_corename);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int cn_printf(struct core_name *cn, const char *fmt, ...)
+{
+	char *cur;
+	int need;
+	int ret;
+	va_list arg;
+
+	va_start(arg, fmt);
+	need = vsnprintf(NULL, 0, fmt, arg);
+	va_end(arg);
+
+	if (likely(need < cn->size - cn->used - 1))
+		goto out_printf;
+
+	ret = expand_corename(cn);
+	if (ret)
+		goto expand_fail;
+
+out_printf:
+	cur = cn->corename + cn->used;
+	va_start(arg, fmt);
+	vsnprintf(cur, need + 1, fmt, arg);
+	va_end(arg);
+	cn->used += need;
+	return 0;
+
+expand_fail:
+	return ret;
+}
+
+static void cn_escape(char *str)
+{
+	for (; *str; str++)
+		if (*str == '/')
+			*str = '!';
+}
+
+static int cn_print_exe_file(struct core_name *cn)
+{
+	struct file *exe_file;
+	char *pathbuf, *path;
+	int ret;
+
+	exe_file = get_mm_exe_file(current->mm);
+	if (!exe_file) {
+		char *commstart = cn->corename + cn->used;
+		ret = cn_printf(cn, "%s (path unknown)", current->comm);
+		cn_escape(commstart);
+		return ret;
+	}
+
+	pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
+	if (!pathbuf) {
+		ret = -ENOMEM;
+		goto put_exe_file;
+	}
+
+	path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
+	if (IS_ERR(path)) {
+		ret = PTR_ERR(path);
+		goto free_buf;
+	}
+
+	cn_escape(path);
+
+	ret = cn_printf(cn, "%s", path);
+
+free_buf:
+	kfree(pathbuf);
+put_exe_file:
+	fput(exe_file);
+	return ret;
+}
+
+/* format_corename will inspect the pattern parameter, and output a
+ * name into corename, which must have space for at least
+ * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
+ */
+static int format_corename(struct core_name *cn, long signr)
+{
+	const struct cred *cred = current_cred();
+	const char *pat_ptr = core_pattern;
+	int ispipe = (*pat_ptr == '|');
+	int pid_in_pattern = 0;
+	int err = 0;
+
+	cn->size = CORENAME_MAX_SIZE * atomic_read(&call_count);
+	cn->corename = kmalloc(cn->size, GFP_KERNEL);
+	cn->used = 0;
+
+	if (!cn->corename)
+		return -ENOMEM;
+
+	/* Repeat as long as we have more pattern to process and more output
+	   space */
+	while (*pat_ptr) {
+		if (*pat_ptr != '%') {
+			if (*pat_ptr == 0)
+				goto out;
+			err = cn_printf(cn, "%c", *pat_ptr++);
+		} else {
+			switch (*++pat_ptr) {
+			/* single % at the end, drop that */
+			case 0:
+				goto out;
+			/* Double percent, output one percent */
+			case '%':
+				err = cn_printf(cn, "%c", '%');
+				break;
+			/* pid */
+			case 'p':
+				pid_in_pattern = 1;
+				err = cn_printf(cn, "%d",
+					      task_tgid_vnr(current));
+				break;
+			/* uid */
+			case 'u':
+				err = cn_printf(cn, "%d", cred->uid);
+				break;
+			/* gid */
+			case 'g':
+				err = cn_printf(cn, "%d", cred->gid);
+				break;
+			/* signal that caused the coredump */
+			case 's':
+				err = cn_printf(cn, "%ld", signr);
+				break;
+			/* UNIX time of coredump */
+			case 't': {
+				struct timeval tv;
+				do_gettimeofday(&tv);
+				err = cn_printf(cn, "%lu", tv.tv_sec);
+				break;
+			}
+			/* hostname */
+			case 'h': {
+				char *namestart = cn->corename + cn->used;
+				down_read(&uts_sem);
+				err = cn_printf(cn, "%s",
+					      utsname()->nodename);
+				up_read(&uts_sem);
+				cn_escape(namestart);
+				break;
+			}
+			/* executable */
+			case 'e': {
+				char *commstart = cn->corename + cn->used;
+				err = cn_printf(cn, "%s", current->comm);
+				cn_escape(commstart);
+				break;
+			}
+			case 'E':
+				err = cn_print_exe_file(cn);
+				break;
+			/* core limit size */
+			case 'c':
+				err = cn_printf(cn, "%lu",
+					      rlimit(RLIMIT_CORE));
+				break;
+			default:
+				break;
+			}
+			++pat_ptr;
+		}
+
+		if (err)
+			return err;
+	}
+
+	/* Backward compatibility with core_uses_pid:
+	 *
+	 * If core_pattern does not include a %p (as is the default)
+	 * and core_uses_pid is set, then .%pid will be appended to
+	 * the filename. Do not do this for piped commands. */
+	if (!ispipe && !pid_in_pattern && core_uses_pid) {
+		err = cn_printf(cn, ".%d", task_tgid_vnr(current));
+		if (err)
+			return err;
+	}
+out:
+	return ispipe;
+}
+
+static int zap_process(struct task_struct *start, int exit_code)
+{
+	struct task_struct *t;
+	int nr = 0;
+
+	start->signal->flags = SIGNAL_GROUP_EXIT;
+	start->signal->group_exit_code = exit_code;
+	start->signal->group_stop_count = 0;
+
+	t = start;
+	do {
+		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
+		if (t != current && t->mm) {
+			sigaddset(&t->pending.signal, SIGKILL);
+			signal_wake_up(t, 1);
+			nr++;
+		}
+	} while_each_thread(start, t);
+
+	return nr;
+}
+
+static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
+				struct core_state *core_state, int exit_code)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+	int nr = -EAGAIN;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	if (!signal_group_exit(tsk->signal)) {
+		mm->core_state = core_state;
+		nr = zap_process(tsk, exit_code);
+	}
+	spin_unlock_irq(&tsk->sighand->siglock);
+	if (unlikely(nr < 0))
+		return nr;
+
+	if (atomic_read(&mm->mm_users) == nr + 1)
+		goto done;
+	/*
+	 * We should find and kill all tasks which use this mm, and we should
+	 * count them correctly into ->nr_threads. We don't take tasklist
+	 * lock, but this is safe wrt:
+	 *
+	 * fork:
+	 *	None of sub-threads can fork after zap_process(leader). All
+	 *	processes which were created before this point should be
+	 *	visible to zap_threads() because copy_process() adds the new
+	 *	process to the tail of init_task.tasks list, and lock/unlock
+	 *	of ->siglock provides a memory barrier.
+	 *
+	 * do_exit:
+	 *	The caller holds mm->mmap_sem. This means that the task which
+	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
+	 *	its ->mm.
+	 *
+	 * de_thread:
+	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
+	 *	we must see either old or new leader, this does not matter.
+	 *	However, it can change p->sighand, so lock_task_sighand(p)
+	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
+	 *	it can't fail.
+	 *
+	 *	Note also that "g" can be the old leader with ->mm == NULL
+	 *	and already unhashed and thus removed from ->thread_group.
+	 *	This is OK, __unhash_process()->list_del_rcu() does not
+	 *	clear the ->next pointer, we will find the new leader via
+	 *	next_thread().
+	 */
+	rcu_read_lock();
+	for_each_process(g) {
+		if (g == tsk->group_leader)
+			continue;
+		if (g->flags & PF_KTHREAD)
+			continue;
+		p = g;
+		do {
+			if (p->mm) {
+				if (unlikely(p->mm == mm)) {
+					lock_task_sighand(p, &flags);
+					nr += zap_process(p, exit_code);
+					unlock_task_sighand(p, &flags);
+				}
+				break;
+			}
+		} while_each_thread(g, p);
+	}
+	rcu_read_unlock();
+done:
+	atomic_set(&core_state->nr_threads, nr);
+	return nr;
+}
+
+static int coredump_wait(int exit_code, struct core_state *core_state)
+{
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+	int core_waiters = -EBUSY;
+
+	init_completion(&core_state->startup);
+	core_state->dumper.task = tsk;
+	core_state->dumper.next = NULL;
+
+	down_write(&mm->mmap_sem);
+	if (!mm->core_state)
+		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
+	up_write(&mm->mmap_sem);
+
+	if (core_waiters > 0) {
+		struct core_thread *ptr;
+
+		wait_for_completion(&core_state->startup);
+		/*
+		 * Wait for all the threads to become inactive, so that
+		 * all the thread context (extended register state, like
+		 * fpu etc) gets copied to the memory.
+		 */
+		ptr = core_state->dumper.next;
+		while (ptr != NULL) {
+			wait_task_inactive(ptr->task, 0);
+			ptr = ptr->next;
+		}
+	}
+
+	return core_waiters;
+}
+
+static void coredump_finish(struct mm_struct *mm)
+{
+	struct core_thread *curr, *next;
+	struct task_struct *task;
+
+	next = mm->core_state->dumper.next;
+	while ((curr = next) != NULL) {
+		next = curr->next;
+		task = curr->task;
+		/*
+		 * see exit_mm(), curr->task must not see
+		 * ->task == NULL before we read ->next.
+		 */
+		smp_mb();
+		curr->task = NULL;
+		wake_up_process(task);
+	}
+
+	mm->core_state = NULL;
+}
+
+static void wait_for_dump_helpers(struct file *file)
+{
+	struct pipe_inode_info *pipe;
+
+	pipe = file->f_path.dentry->d_inode->i_pipe;
+
+	pipe_lock(pipe);
+	pipe->readers++;
+	pipe->writers--;
+
+	while ((pipe->readers > 1) && (!signal_pending(current))) {
+		wake_up_interruptible_sync(&pipe->wait);
+		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+		pipe_wait(pipe);
+	}
+
+	pipe->readers--;
+	pipe->writers++;
+	pipe_unlock(pipe);
+
+}
+
+/*
+ * umh_pipe_setup
+ * helper function to customize the process used
+ * to collect the core in userspace.  Specifically
+ * it sets up a pipe and installs it as fd 0 (stdin)
+ * for the process.  Returns 0 on success, or
+ * PTR_ERR on failure.
+ * Note that it also sets the core limit to 1.  This
+ * is a special value that we use to trap recursive
+ * core dumps
+ */
+static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
+{
+	struct file *files[2];
+	struct coredump_params *cp = (struct coredump_params *)info->data;
+	int err = create_pipe_files(files, 0);
+	if (err)
+		return err;
+
+	cp->file = files[1];
+
+	replace_fd(0, files[0], 0);
+	/* and disallow core files too */
+	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
+
+	return 0;
+}
+
+void do_coredump(long signr, int exit_code, struct pt_regs *regs)
+{
+	struct core_state core_state;
+	struct core_name cn;
+	struct mm_struct *mm = current->mm;
+	struct linux_binfmt * binfmt;
+	const struct cred *old_cred;
+	struct cred *cred;
+	int retval = 0;
+	int flag = 0;
+	int ispipe;
+	struct files_struct *displaced;
+	bool need_nonrelative = false;
+	static atomic_t core_dump_count = ATOMIC_INIT(0);
+	struct coredump_params cprm = {
+		.signr = signr,
+		.regs = regs,
+		.limit = rlimit(RLIMIT_CORE),
+		/*
+		 * We must use the same mm->flags while dumping core to avoid
+		 * inconsistency of bit flags, since this flag is not protected
+		 * by any locks.
+		 */
+		.mm_flags = mm->flags,
+	};
+
+	audit_core_dumps(signr);
+
+	binfmt = mm->binfmt;
+	if (!binfmt || !binfmt->core_dump)
+		goto fail;
+	if (!__get_dumpable(cprm.mm_flags))
+		goto fail;
+
+	cred = prepare_creds();
+	if (!cred)
+		goto fail;
+	/*
+	 * We cannot trust fsuid as being the "true" uid of the process
+	 * nor do we know its entire history. We only know it was tainted
+	 * so we dump it as root in mode 2, and only into a controlled
+	 * environment (pipe handler or fully qualified path).
+	 */
+	if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
+		/* Setuid core dump mode */
+		flag = O_EXCL;		/* Stop rewrite attacks */
+		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
+		need_nonrelative = true;
+	}
+
+	retval = coredump_wait(exit_code, &core_state);
+	if (retval < 0)
+		goto fail_creds;
+
+	old_cred = override_creds(cred);
+
+	/*
+	 * Clear any false indication of pending signals that might
+	 * be seen by the filesystem code called to write the core file.
+	 */
+	clear_thread_flag(TIF_SIGPENDING);
+
+	ispipe = format_corename(&cn, signr);
+
+ 	if (ispipe) {
+		int dump_count;
+		char **helper_argv;
+
+		if (ispipe < 0) {
+			printk(KERN_WARNING "format_corename failed\n");
+			printk(KERN_WARNING "Aborting core\n");
+			goto fail_corename;
+		}
+
+		if (cprm.limit == 1) {
+			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
+			 *
+			 * Normally core limits are irrelevant to pipes, since
+			 * we're not writing to the file system, but we use
+			 * cprm.limit of 1 here as a speacial value, this is a
+			 * consistent way to catch recursive crashes.
+			 * We can still crash if the core_pattern binary sets
+			 * RLIM_CORE = !1, but it runs as root, and can do
+			 * lots of stupid things.
+			 *
+			 * Note that we use task_tgid_vnr here to grab the pid
+			 * of the process group leader.  That way we get the
+			 * right pid if a thread in a multi-threaded
+			 * core_pattern process dies.
+			 */
+			printk(KERN_WARNING
+				"Process %d(%s) has RLIMIT_CORE set to 1\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Aborting core\n");
+			goto fail_unlock;
+		}
+		cprm.limit = RLIM_INFINITY;
+
+		dump_count = atomic_inc_return(&core_dump_count);
+		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
+			printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
+			       task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_dropcount;
+		}
+
+		helper_argv = argv_split(GFP_KERNEL, cn.corename+1, NULL);
+		if (!helper_argv) {
+			printk(KERN_WARNING "%s failed to allocate memory\n",
+			       __func__);
+			goto fail_dropcount;
+		}
+
+		retval = call_usermodehelper_fns(helper_argv[0], helper_argv,
+					NULL, UMH_WAIT_EXEC, umh_pipe_setup,
+					NULL, &cprm);
+		argv_free(helper_argv);
+		if (retval) {
+ 			printk(KERN_INFO "Core dump to %s pipe failed\n",
+			       cn.corename);
+			goto close_fail;
+ 		}
+	} else {
+		struct inode *inode;
+
+		if (cprm.limit < binfmt->min_coredump)
+			goto fail_unlock;
+
+		if (need_nonrelative && cn.corename[0] != '/') {
+			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
+				"to fully qualified path!\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_unlock;
+		}
+
+		cprm.file = filp_open(cn.corename,
+				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
+				 0600);
+		if (IS_ERR(cprm.file))
+			goto fail_unlock;
+
+		inode = cprm.file->f_path.dentry->d_inode;
+		if (inode->i_nlink > 1)
+			goto close_fail;
+		if (d_unhashed(cprm.file->f_path.dentry))
+			goto close_fail;
+		/*
+		 * AK: actually i see no reason to not allow this for named
+		 * pipes etc, but keep the previous behaviour for now.
+		 */
+		if (!S_ISREG(inode->i_mode))
+			goto close_fail;
+		/*
+		 * Dont allow local users get cute and trick others to coredump
+		 * into their pre-created files.
+		 */
+		if (!uid_eq(inode->i_uid, current_fsuid()))
+			goto close_fail;
+		if (!cprm.file->f_op || !cprm.file->f_op->write)
+			goto close_fail;
+		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
+			goto close_fail;
+	}
+
+	/* get us an unshared descriptor table; almost always a no-op */
+	retval = unshare_files(&displaced);
+	if (retval)
+		goto close_fail;
+	if (displaced)
+		put_files_struct(displaced);
+	retval = binfmt->core_dump(&cprm);
+	if (retval)
+		current->signal->group_exit_code |= 0x80;
+
+	if (ispipe && core_pipe_limit)
+		wait_for_dump_helpers(cprm.file);
+close_fail:
+	if (cprm.file)
+		filp_close(cprm.file, NULL);
+fail_dropcount:
+	if (ispipe)
+		atomic_dec(&core_dump_count);
+fail_unlock:
+	kfree(cn.corename);
+fail_corename:
+	coredump_finish(mm);
+	revert_creds(old_cred);
+fail_creds:
+	put_cred(cred);
+fail:
+	return;
+}
+
+/*
+ * Core dumping helper functions.  These are the only things you should
+ * do on a core-file: use only these functions to write out all the
+ * necessary info.
+ */
+int dump_write(struct file *file, const void *addr, int nr)
+{
+	return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+}
+EXPORT_SYMBOL(dump_write);
+
+int dump_seek(struct file *file, loff_t off)
+{
+	int ret = 1;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
+			return 0;
+	} else {
+		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
+
+		if (!buf)
+			return 0;
+		while (off > 0) {
+			unsigned long n = off;
+
+			if (n > PAGE_SIZE)
+				n = PAGE_SIZE;
+			if (!dump_write(file, buf, n)) {
+				ret = 0;
+				break;
+			}
+			off -= n;
+		}
+		free_page((unsigned long)buf);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(dump_seek);