Merge tag 'io_uring-2019-03-06' of git://git.kernel.dk/linux-block

Pull io_uring IO interface from Jens Axboe:
 "Second attempt at adding the io_uring interface.

  Since the first one, we've added basic unit testing of the three
  system calls, that resides in liburing like the other unit tests that
  we have so far. It'll take a while to get full coverage of it, but
  we're working towards it. I've also added two basic test programs to
  tools/io_uring. One uses the raw interface and has support for all the
  various features that io_uring supports outside of standard IO, like
  fixed files, fixed IO buffers, and polled IO. The other uses the
  liburing API, and is a simplified version of cp(1).

  This adds support for a new IO interface, io_uring.

  io_uring allows an application to communicate with the kernel through
  two rings, the submission queue (SQ) and completion queue (CQ) ring.
  This allows for very efficient handling of IOs, see the v5 posting for
  some basic numbers:

    https://lore.kernel.org/linux-block/20190116175003.17880-1-axboe@kernel.dk/

  Outside of just efficiency, the interface is also flexible and
  extendable, and allows for future use cases like the upcoming NVMe
  key-value store API, networked IO, and so on. It also supports async
  buffered IO, something that we've always failed to support in the
  kernel.

  Outside of basic IO features, it supports async polled IO as well.
  This particular feature has already been tested at Facebook months ago
  for flash storage boxes, with 25-33% improvements. It makes polled IO
  actually useful for real world use cases, where even basic flash sees
  a nice win in terms of efficiency, latency, and performance. These
  boxes were IOPS bound before, now they are not.

  This series adds three new system calls. One for setting up an
  io_uring instance (io_uring_setup(2)), one for submitting/completing
  IO (io_uring_enter(2)), and one for aux functions like registrating
  file sets, buffers, etc (io_uring_register(2)). Through the help of
  Arnd, I've coordinated the syscall numbers so merge on that front
  should be painless.

  Jon did a writeup of the interface a while back, which (except for
  minor details that have been tweaked) is still accurate. Find that
  here:

    https://lwn.net/Articles/776703/

  Huge thanks to Al Viro for helping getting the reference cycle code
  correct, and to Jann Horn for his extensive reviews focused on both
  security and bugs in general.

  There's a userspace library that provides basic functionality for
  applications that don't need or want to care about how to fiddle with
  the rings directly. It has helpers to allow applications to easily set
  up an io_uring instance, and submit/complete IO through it without
  knowing about the intricacies of the rings. It also includes man pages
  (thanks to Jeff Moyer), and will continue to grow support helper
  functions and features as time progresses. Find it here:

    git://git.kernel.dk/liburing

  Fio has full support for the raw interface, both in the form of an IO
  engine (io_uring), but also with a small test application (t/io_uring)
  that can exercise and benchmark the interface"

* tag 'io_uring-2019-03-06' of git://git.kernel.dk/linux-block:
  io_uring: add a few test tools
  io_uring: allow workqueue item to handle multiple buffered requests
  io_uring: add support for IORING_OP_POLL
  io_uring: add io_kiocb ref count
  io_uring: add submission polling
  io_uring: add file set registration
  net: split out functions related to registering inflight socket files
  io_uring: add support for pre-mapped user IO buffers
  block: implement bio helper to add iter bvec pages to bio
  io_uring: batch io_kiocb allocation
  io_uring: use fget/fput_many() for file references
  fs: add fget_many() and fput_many()
  io_uring: support for IO polling
  io_uring: add fsync support
  Add io_uring IO interface

1 files changed, 151 insertions, 0 deletions

diff --git a/net/unix/scm.c b/net/unix/scm.c
new file mode 100644
index 000000000000..8c40f2b32392
--- /dev/null
+++ b/net/unix/scm.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/fs.h>
+#include <net/af_unix.h>
+#include <net/scm.h>
+#include <linux/init.h>
+
+#include "scm.h"
+
+unsigned int unix_tot_inflight;
+EXPORT_SYMBOL(unix_tot_inflight);
+
+LIST_HEAD(gc_inflight_list);
+EXPORT_SYMBOL(gc_inflight_list);
+
+DEFINE_SPINLOCK(unix_gc_lock);
+EXPORT_SYMBOL(unix_gc_lock);
+
+struct sock *unix_get_socket(struct file *filp)
+{
+	struct sock *u_sock = NULL;
+	struct inode *inode = file_inode(filp);
+
+	/* Socket ? */
+	if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
+		struct socket *sock = SOCKET_I(inode);
+		struct sock *s = sock->sk;
+
+		/* PF_UNIX ? */
+		if (s && sock->ops && sock->ops->family == PF_UNIX)
+			u_sock = s;
+	} else {
+		/* Could be an io_uring instance */
+		u_sock = io_uring_get_socket(filp);
+	}
+	return u_sock;
+}
+EXPORT_SYMBOL(unix_get_socket);
+
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
+ */
+void unix_inflight(struct user_struct *user, struct file *fp)
+{
+	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
+	if (s) {
+		struct unix_sock *u = unix_sk(s);
+
+		if (atomic_long_inc_return(&u->inflight) == 1) {
+			BUG_ON(!list_empty(&u->link));
+			list_add_tail(&u->link, &gc_inflight_list);
+		} else {
+			BUG_ON(list_empty(&u->link));
+		}
+		unix_tot_inflight++;
+	}
+	user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
+}
+
+void unix_notinflight(struct user_struct *user, struct file *fp)
+{
+	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
+	if (s) {
+		struct unix_sock *u = unix_sk(s);
+
+		BUG_ON(!atomic_long_read(&u->inflight));
+		BUG_ON(list_empty(&u->link));
+
+		if (atomic_long_dec_and_test(&u->inflight))
+			list_del_init(&u->link);
+		unix_tot_inflight--;
+	}
+	user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
+}
+
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
+int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	int i;
+
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
+	/*
+	 * Need to duplicate file references for the sake of garbage
+	 * collection.  Otherwise a socket in the fps might become a
+	 * candidate for GC while the skb is not yet queued.
+	 */
+	UNIXCB(skb).fp = scm_fp_dup(scm->fp);
+	if (!UNIXCB(skb).fp)
+		return -ENOMEM;
+
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
+	return 0;
+}
+EXPORT_SYMBOL(unix_attach_fds);
+
+void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	int i;
+
+	scm->fp = UNIXCB(skb).fp;
+	UNIXCB(skb).fp = NULL;
+
+	for (i = scm->fp->count-1; i >= 0; i--)
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
+}
+EXPORT_SYMBOL(unix_detach_fds);
+
+void unix_destruct_scm(struct sk_buff *skb)
+{
+	struct scm_cookie scm;
+
+	memset(&scm, 0, sizeof(scm));
+	scm.pid  = UNIXCB(skb).pid;
+	if (UNIXCB(skb).fp)
+		unix_detach_fds(&scm, skb);
+
+	/* Alas, it calls VFS */
+	/* So fscking what? fput() had been SMP-safe since the last Summer */
+	scm_destroy(&scm);
+	sock_wfree(skb);
+}
+EXPORT_SYMBOL(unix_destruct_scm);