Merge tag 'pull-fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull 'struct fd' class updates from Al Viro:
 "The bulk of struct fd memory safety stuff

  Making sure that struct fd instances are destroyed in the same scope
  where they'd been created, getting rid of reassignments and passing
  them by reference, converting to CLASS(fd{,_pos,_raw}).

  We are getting very close to having the memory safety of that stuff
  trivial to verify"

* tag 'pull-fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (28 commits)
  deal with the last remaing boolean uses of fd_file()
  css_set_fork(): switch to CLASS(fd_raw, ...)
  memcg_write_event_control(): switch to CLASS(fd)
  assorted variants of irqfd setup: convert to CLASS(fd)
  do_pollfd(): convert to CLASS(fd)
  convert do_select()
  convert vfs_dedupe_file_range().
  convert cifs_ioctl_copychunk()
  convert media_request_get_by_fd()
  convert spu_run(2)
  switch spufs_calls_{get,put}() to CLASS() use
  convert cachestat(2)
  convert do_preadv()/do_pwritev()
  fdget(), more trivial conversions
  fdget(), trivial conversions
  privcmd_ioeventfd_assign(): don't open-code eventfd_ctx_fdget()
  o2hb_region_dev_store(): avoid goto around fdget()/fdput()
  introduce "fd_pos" class, convert fdget_pos() users to it.
  fdget_raw() users: switch to CLASS(fd_raw)
  convert vmsplice() to CLASS(fd)
  ...

9 files changed, 65 insertions, 127 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 044c7ba1cc48..9bc4a84bd309 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6476,7 +6476,6 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	struct cgroup *dst_cgrp = NULL;
 	struct css_set *cset;
 	struct super_block *sb;
-	struct file *f;
 
 	if (kargs->flags & CLONE_INTO_CGROUP)
 		cgroup_lock();
@@ -6493,14 +6492,14 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 		return 0;
 	}
 
-	f = fget_raw(kargs->cgroup);
-	if (!f) {
+	CLASS(fd_raw, f)(kargs->cgroup);
+	if (fd_empty(f)) {
 		ret = -EBADF;
 		goto err;
 	}
-	sb = f->f_path.dentry->d_sb;
+	sb = fd_file(f)->f_path.dentry->d_sb;
 
-	dst_cgrp = cgroup_get_from_file(f);
+	dst_cgrp = cgroup_get_from_file(fd_file(f));
 	if (IS_ERR(dst_cgrp)) {
 		ret = PTR_ERR(dst_cgrp);
 		dst_cgrp = NULL;
@@ -6548,15 +6547,12 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	}
 
 	put_css_set(cset);
-	fput(f);
 	kargs->cgrp = dst_cgrp;
 	return ret;
 
 err:
 	cgroup_threadgroup_change_end(current);
 	cgroup_unlock();
-	if (f)
-		fput(f);
 	if (dst_cgrp)
 		cgroup_put(dst_cgrp);
 	put_css_set(cset);
@@ -6966,14 +6962,11 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path);
  */
 struct cgroup *cgroup_v1v2_get_from_fd(int fd)
 {
-	struct cgroup *cgrp;
-	struct fd f = fdget_raw(fd);
-	if (!fd_file(f))
+	CLASS(fd_raw, f)(fd);
+	if (fd_empty(f))
 		return ERR_PTR(-EBADF);
 
-	cgrp = cgroup_v1v2_get_from_file(fd_file(f));
-	fdput(f);
-	return cgrp;
+	return cgroup_v1v2_get_from_file(fd_file(f));
 }
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index df27d08a7232..b65446be00a7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -966,22 +966,20 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 {
 	struct perf_cgroup *cgrp;
 	struct cgroup_subsys_state *css;
-	struct fd f = fdget(fd);
+	CLASS(fd, f)(fd);
 	int ret = 0;
 
-	if (!fd_file(f))
+	if (fd_empty(f))
 		return -EBADF;
 
 	css = css_tryget_online_from_dir(fd_file(f)->f_path.dentry,
 					 &perf_event_cgrp_subsys);
-	if (IS_ERR(css)) {
-		ret = PTR_ERR(css);
-		goto out;
-	}
+	if (IS_ERR(css))
+		return PTR_ERR(css);
 
 	ret = perf_cgroup_ensure_storage(event, css);
 	if (ret)
-		goto out;
+		return ret;
 
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
@@ -995,8 +993,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		perf_detach_cgroup(event);
 		ret = -EINVAL;
 	}
-out:
-	fdput(f);
 	return ret;
 }
 
@@ -5998,18 +5994,9 @@ EXPORT_SYMBOL_GPL(perf_event_period);
 
 static const struct file_operations perf_fops;
 
-static inline int perf_fget_light(int fd, struct fd *p)
+static inline bool is_perf_file(struct fd f)
 {
-	struct fd f = fdget(fd);
-	if (!fd_file(f))
-		return -EBADF;
-
-	if (fd_file(f)->f_op != &perf_fops) {
-		fdput(f);
-		return -EBADF;
-	}
-	*p = f;
-	return 0;
+	return !fd_empty(f) && fd_file(f)->f_op == &perf_fops;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -6057,20 +6044,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
-		int ret;
+		CLASS(fd, output)(arg);	     // arg == -1 => empty
+		struct perf_event *output_event = NULL;
 		if (arg != -1) {
-			struct perf_event *output_event;
-			struct fd output;
-			ret = perf_fget_light(arg, &output);
-			if (ret)
-				return ret;
+			if (!is_perf_file(output))
+				return -EBADF;
 			output_event = fd_file(output)->private_data;
-			ret = perf_event_set_output(event, output_event);
-			fdput(output);
-		} else {
-			ret = perf_event_set_output(event, NULL);
 		}
-		return ret;
+		return perf_event_set_output(event, output_event);
 	}
 
 	case PERF_EVENT_IOC_SET_FILTER:
@@ -12664,7 +12645,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
-	struct fd group = EMPTY_FD;
 	struct task_struct *task = NULL;
 	struct pmu *pmu;
 	int event_fd;
@@ -12735,10 +12715,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (event_fd < 0)
 		return event_fd;
 
+	CLASS(fd, group)(group_fd);     // group_fd == -1 => empty
 	if (group_fd != -1) {
-		err = perf_fget_light(group_fd, &group);
-		if (err)
+		if (!is_perf_file(group)) {
+			err = -EBADF;
 			goto err_fd;
+		}
 		group_leader = fd_file(group)->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
@@ -12750,7 +12732,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
 			err = PTR_ERR(task);
-			goto err_group_fd;
+			goto err_fd;
 		}
 	}
 
@@ -13017,12 +12999,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Drop the reference on the group_event after placing the
-	 * new event on the sibling_list. This ensures destruction
-	 * of the group leader will find the pointer to itself in
-	 * perf_group_detach().
+	 * File reference in group guarantees that group_leader has been
+	 * kept alive until we place the new event on the sibling_list.
+	 * This ensures destruction of the group leader will find
+	 * the pointer to itself in perf_group_detach().
 	 */
-	fdput(group);
 	fd_install(event_fd, event_file);
 	return event_fd;
 
@@ -13041,8 +13022,6 @@ err_alloc:
 err_task:
 	if (task)
 		put_task_struct(task);
-err_group_fd:
-	fdput(group);
 err_fd:
 	put_unused_fd(event_fd);
 	return err;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 49b9bca9de12..4490924fe24e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3202,7 +3202,7 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int
 {
 	struct idempotent idem;
 
-	if (!f || !(f->f_mode & FMODE_READ))
+	if (!(f->f_mode & FMODE_READ))
 		return -EBADF;
 
 	/* Are we the winners of the race and get to do this? */
@@ -3219,10 +3219,7 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int
 
 SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
-	int err;
-	struct fd f;
-
-	err = may_init_module();
+	int err = may_init_module();
 	if (err)
 		return err;
 
@@ -3233,10 +3230,10 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_COMPRESSED_FILE))
 		return -EINVAL;
 
-	f = fdget(fd);
-	err = idempotent_init_module(fd_file(f), uargs, flags);
-	fdput(f);
-	return err;
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EBADF;
+	return idempotent_init_module(fd_file(f), uargs, flags);
 }
 
 /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index dc952c3b05af..c9d97ed20122 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -545,12 +545,12 @@ static void commit_nsset(struct nsset *nsset)
 
 SYSCALL_DEFINE2(setns, int, fd, int, flags)
 {
-	struct fd f = fdget(fd);
+	CLASS(fd, f)(fd);
 	struct ns_common *ns = NULL;
 	struct nsset nsset = {};
 	int err = 0;
 
-	if (!fd_file(f))
+	if (fd_empty(f))
 		return -EBADF;
 
 	if (proc_ns_file(fd_file(f))) {
@@ -580,7 +580,6 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
 	}
 	put_nsset(&nsset);
 out:
-	fdput(f);
 	return err;
 }
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 2715afb77eab..115448e89c3e 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -536,11 +536,10 @@ EXPORT_SYMBOL_GPL(find_ge_pid);
 
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
 {
-	struct fd f;
+	CLASS(fd, f)(fd);
 	struct pid *pid;
 
-	f = fdget(fd);
-	if (!fd_file(f))
+	if (fd_empty(f))
 		return ERR_PTR(-EBADF);
 
 	pid = pidfd_pid(fd_file(f));
@@ -548,8 +547,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
 		get_pid(pid);
 		*flags = fd_file(f)->f_flags;
 	}
-
-	fdput(f);
 	return pid;
 }
 
@@ -747,23 +744,18 @@ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
 		unsigned int, flags)
 {
 	struct pid *pid;
-	struct fd f;
-	int ret;
 
 	/* flags is currently unused - make sure it's unset */
 	if (flags)
 		return -EINVAL;
 
-	f = fdget(pidfd);
-	if (!fd_file(f))
+	CLASS(fd, f)(pidfd);
+	if (fd_empty(f))
 		return -EBADF;
 
 	pid = pidfd_pid(fd_file(f));
 	if (IS_ERR(pid))
-		ret = PTR_ERR(pid);
-	else
-		ret = pidfd_getfd(pid, fd);
+		return PTR_ERR(pid);
 
-	fdput(f);
-	return ret;
+	return pidfd_getfd(pid, fd);
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index cbabb2d05e0a..65fd233f6f23 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3909,7 +3909,6 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 		siginfo_t __user *, info, unsigned int, flags)
 {
 	int ret;
-	struct fd f;
 	struct pid *pid;
 	kernel_siginfo_t kinfo;
 	enum pid_type type;
@@ -3922,20 +3921,17 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1)
 		return -EINVAL;
 
-	f = fdget(pidfd);
-	if (!fd_file(f))
+	CLASS(fd, f)(pidfd);
+	if (fd_empty(f))
 		return -EBADF;
 
 	/* Is this a pidfd? */
 	pid = pidfd_to_pid(fd_file(f));
-	if (IS_ERR(pid)) {
-		ret = PTR_ERR(pid);
-		goto err;
-	}
+	if (IS_ERR(pid))
+		return PTR_ERR(pid);
 
-	ret = -EINVAL;
 	if (!access_pidfd_pidns(pid))
-		goto err;
+		return -EINVAL;
 
 	switch (flags) {
 	case 0:
@@ -3959,28 +3955,23 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	if (info) {
 		ret = copy_siginfo_from_user_any(&kinfo, info);
 		if (unlikely(ret))
-			goto err;
+			return ret;
 
-		ret = -EINVAL;
 		if (unlikely(sig != kinfo.si_signo))
-			goto err;
+			return -EINVAL;
 
 		/* Only allow sending arbitrary signals to yourself. */
-		ret = -EPERM;
 		if ((task_pid(current) != pid || type > PIDTYPE_TGID) &&
 		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
-			goto err;
+			return -EPERM;
 	} else {
 		prepare_kill_siginfo(sig, &kinfo, type);
 	}
 
 	if (type == PIDTYPE_PGID)
-		ret = kill_pgrp_info(sig, &kinfo, pid);
+		return kill_pgrp_info(sig, &kinfo, pid);
 	else
-		ret = kill_pid_info_type(sig, &kinfo, pid, type);
-err:
-	fdput(f);
-	return ret;
+		return kill_pid_info_type(sig, &kinfo, pid, type);
 }
 
 static int
diff --git a/kernel/sys.c b/kernel/sys.c
index 4da31f28fda8..ebe10c27a9f4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1911,12 +1911,11 @@ SYSCALL_DEFINE1(umask, int, mask)
 
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
-	struct fd exe;
+	CLASS(fd, exe)(fd);
 	struct inode *inode;
 	int err;
 
-	exe = fdget(fd);
-	if (!fd_file(exe))
+	if (fd_empty(exe))
 		return -EBADF;
 
 	inode = file_inode(fd_file(exe));
@@ -1926,18 +1925,14 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	 * sure that this one is executable as well, to avoid breaking an
 	 * overall picture.
 	 */
-	err = -EACCES;
 	if (!S_ISREG(inode->i_mode) || path_noexec(&fd_file(exe)->f_path))
-		goto exit;
+		return -EACCES;
 
 	err = file_permission(fd_file(exe), MAY_EXEC);
 	if (err)
-		goto exit;
+		return err;
 
-	err = replace_mm_exe_file(mm, fd_file(exe));
-exit:
-	fdput(exe);
-	return err;
+	return replace_mm_exe_file(mm, fd_file(exe));
 }
 
 /*
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 0700f40c53ac..0cd680ccc7e5 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -411,15 +411,14 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *na;
 	size_t size;
 	u32 fd;
-	struct fd f;
 
 	na = info->attrs[CGROUPSTATS_CMD_ATTR_FD];
 	if (!na)
 		return -EINVAL;
 
 	fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]);
-	f = fdget(fd);
-	if (!fd_file(f))
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
 		return 0;
 
 	size = nla_total_size(sizeof(struct cgroupstats));
@@ -427,14 +426,13 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb,
 				size);
 	if (rc < 0)
-		goto err;
+		return rc;
 
 	na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
 				sizeof(struct cgroupstats));
 	if (na == NULL) {
 		nlmsg_free(rep_skb);
-		rc = -EMSGSIZE;
-		goto err;
+		return -EMSGSIZE;
 	}
 
 	stats = nla_data(na);
@@ -443,14 +441,10 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	rc = cgroupstats_build(stats, fd_file(f)->f_path.dentry);
 	if (rc < 0) {
 		nlmsg_free(rep_skb);
-		goto err;
+		return rc;
 	}
 
-	rc = send_reply(rep_skb, info);
-
-err:
-	fdput(f);
-	return rc;
+	return send_reply(rep_skb, info);
 }
 
 static int cmd_attr_register_cpumask(struct genl_info *info)
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index d36242fd4936..1895fbc32bcb 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -663,16 +663,14 @@ struct watch_queue *get_watch_queue(int fd)
 {
 	struct pipe_inode_info *pipe;
 	struct watch_queue *wqueue = ERR_PTR(-EINVAL);
-	struct fd f;
+	CLASS(fd, f)(fd);
 
-	f = fdget(fd);
-	if (fd_file(f)) {
+	if (!fd_empty(f)) {
 		pipe = get_pipe_info(fd_file(f), false);
 		if (pipe && pipe->watch_queue) {
 			wqueue = pipe->watch_queue;
 			kref_get(&wqueue->usage);
 		}
-		fdput(f);
 	}
 
 	return wqueue;