Merge tag 'for-5.6/io_uring-vfs-2020-01-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - Support for various new opcodes (fallocate, openat, close, statx,
   fadvise, madvise, openat2, non-vectored read/write, send/recv, and
   epoll_ctl)

 - Faster ring quiesce for fileset updates

 - Optimizations for overflow condition checking

 - Support for max-sized clamping

 - Support for probing what opcodes are supported

 - Support for io-wq backend sharing between "sibling" rings

 - Support for registering personalities

 - Lots of little fixes and improvements

* tag 'for-5.6/io_uring-vfs-2020-01-29' of git://git.kernel.dk/linux-block: (64 commits)
  io_uring: add support for epoll_ctl(2)
  eventpoll: support non-blocking do_epoll_ctl() calls
  eventpoll: abstract out epoll_ctl() handler
  io_uring: fix linked command file table usage
  io_uring: support using a registered personality for commands
  io_uring: allow registering credentials
  io_uring: add io-wq workqueue sharing
  io-wq: allow grabbing existing io-wq
  io_uring/io-wq: don't use static creds/mm assignments
  io-wq: make the io_wq ref counted
  io_uring: fix refcounting with batched allocations at OOM
  io_uring: add comment for drain_next
  io_uring: don't attempt to copy iovec for READ/WRITE
  io_uring: honor IOSQE_ASYNC for linked reqs
  io_uring: prep req when do IOSQE_ASYNC
  io_uring: use labeled array init in io_op_defs
  io_uring: optimise sqe-to-req flags translation
  io_uring: remove REQ_F_IO_DRAINED
  io_uring: file switch work needs to get flushed on exit
  io_uring: hide uring_fd in ctx
  ...

Author: torvalds

drivers/android/binder.c

@@ -2249,10 +2249,12 @@ static void binder_deferred_fd_close(int fd)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
 	__close_fd_get_file(fd, &twcb->file);
-	if (twcb->file)
+	if (twcb->file) {
+		filp_close(twcb->file, current->files);
 		task_work_add(current, &twcb->twork, true);
-	else
+	} else {
 		kfree(twcb);
+	}
 }
 
 static void binder_transaction_buffer_release(struct binder_proc *proc,

fs/eventpoll.c

@@ -354,12 +354,6 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p)
 	return container_of(p, struct ep_pqueue, pt)->epi;
 }
 
-/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
-static inline int ep_op_has_event(int op)
-{
-	return op != EPOLL_CTL_DEL;
-}
-
 /* Initialize the poll safe wake up structure */
 static void ep_nested_calls_init(struct nested_calls *ncalls)
 {
@@ -2074,27 +2068,28 @@ SYSCALL_DEFINE1(epoll_create, int, size)
 	return do_epoll_create(0);
 }
 
-/*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set.
- */
-SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
-		struct epoll_event __user *, event)
+static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
+				   bool nonblock)
+{
+	if (!nonblock) {
+		mutex_lock_nested(mutex, depth);
+		return 0;
+	}
+	if (mutex_trylock(mutex))
+		return 0;
+	return -EAGAIN;
+}
+
+int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
+		 bool nonblock)
 {
 	int error;
 	int full_check = 0;
 	struct fd f, tf;
 	struct eventpoll *ep;
 	struct epitem *epi;
-	struct epoll_event epds;
 	struct eventpoll *tep = NULL;
 
-	error = -EFAULT;
-	if (ep_op_has_event(op) &&
-	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
-		goto error_return;
-
 	error = -EBADF;
 	f = fdget(epfd);
 	if (!f.file)
@@ -2112,7 +2107,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 
 	/* Check if EPOLLWAKEUP is allowed */
 	if (ep_op_has_event(op))
-		ep_take_care_of_epollwakeup(&epds);
+		ep_take_care_of_epollwakeup(epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor
@@ -2128,11 +2123,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
 	 * Also, we do not currently supported nested exclusive wakeups.
 	 */
-	if (ep_op_has_event(op) && (epds.events & EPOLLEXCLUSIVE)) {
+	if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
 		if (op == EPOLL_CTL_MOD)
 			goto error_tgt_fput;
 		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
-				(epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+				(epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
 			goto error_tgt_fput;
 	}
 
@@ -2157,13 +2152,17 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * deep wakeup paths from forming in parallel through multiple
 	 * EPOLL_CTL_ADD operations.
 	 */
-	mutex_lock_nested(&ep->mtx, 0);
+	error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+	if (error)
+		goto error_tgt_fput;
 	if (op == EPOLL_CTL_ADD) {
 		if (!list_empty(&f.file->f_ep_links) ||
 						is_file_epoll(tf.file)) {
-			full_check = 1;
 			mutex_unlock(&ep->mtx);
-			mutex_lock(&epmutex);
+			error = epoll_mutex_lock(&epmutex, 0, nonblock);
+			if (error)
+				goto error_tgt_fput;
+			full_check = 1;
 			if (is_file_epoll(tf.file)) {
 				error = -ELOOP;
 				if (ep_loop_check(ep, tf.file) != 0) {
@@ -2173,10 +2172,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			} else
 				list_add(&tf.file->f_tfile_llink,
 							&tfile_check_list);
-			mutex_lock_nested(&ep->mtx, 0);
+			error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+			if (error) {
+out_del:
+				list_del(&tf.file->f_tfile_llink);
+				goto error_tgt_fput;
+			}
 			if (is_file_epoll(tf.file)) {
 				tep = tf.file->private_data;
-				mutex_lock_nested(&tep->mtx, 1);
+				error = epoll_mutex_lock(&tep->mtx, 1, nonblock);
+				if (error) {
+					mutex_unlock(&ep->mtx);
+					goto out_del;
+				}
 			}
 		}
 	}
@@ -2192,8 +2200,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	switch (op) {
 	case EPOLL_CTL_ADD:
 		if (!epi) {
-			epds.events |= EPOLLERR | EPOLLHUP;
-			error = ep_insert(ep, &epds, tf.file, fd, full_check);
+			epds->events |= EPOLLERR | EPOLLHUP;
+			error = ep_insert(ep, epds, tf.file, fd, full_check);
 		} else
 			error = -EEXIST;
 		if (full_check)
@@ -2208,8 +2216,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	case EPOLL_CTL_MOD:
 		if (epi) {
 			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
-				epds.events |= EPOLLERR | EPOLLHUP;
-				error = ep_modify(ep, epi, &epds);
+				epds->events |= EPOLLERR | EPOLLHUP;
+				error = ep_modify(ep, epi, epds);
 			}
 		} else
 			error = -ENOENT;
@@ -2231,6 +2239,23 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	return error;
 }
 
+/*
+ * The following function implements the controller interface for
+ * the eventpoll file that enables the insertion/removal/change of
+ * file descriptors inside the interest set.
+ */
+SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
+		struct epoll_event __user *, event)
+{
+	struct epoll_event epds;
+
+	if (ep_op_has_event(op) &&
+	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
+		return -EFAULT;
+
+	return do_epoll_ctl(epfd, op, fd, &epds, false);
+}
+
 /*
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_wait(2).

fs/file.c

@@ -642,7 +642,9 @@ int __close_fd(struct files_struct *files, unsigned fd)
 EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
 
 /*
- * variant of __close_fd that gets a ref on the file for later fput
+ * variant of __close_fd that gets a ref on the file for later fput.
+ * The caller must ensure that filp_close() called on the file, and then
+ * an fput().
  */
 int __close_fd_get_file(unsigned int fd, struct file **res)
 {
@@ -662,7 +664,7 @@ int __close_fd_get_file(unsigned int fd, struct file **res)
 	spin_unlock(&files->file_lock);
 	get_file(file);
 	*res = file;
-	return filp_close(file, files);
+	return 0;
 
 out_unlock:
 	spin_unlock(&files->file_lock);

fs/internal.h

@@ -124,6 +124,8 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname,
 		const struct open_flags *op);
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *);
+extern struct open_how build_open_how(int flags, umode_t mode);
+extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 long do_faccessat(int dfd, const char __user *filename, int mode);
@@ -182,3 +184,9 @@ extern const struct dentry_operations ns_dentry_operations;
 
 /* direct-io.c: */
 int sb_init_dio_done_wq(struct super_block *sb);
+
+/*
+ * fs/stat.c:
+ */
+unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags);
+int cp_statx(const struct kstat *stat, struct statx __user *buffer);