for-5.8/io_uring-2020-06-01

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl7VP+kQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpuK4D/0XsSG/Yirbba1rrbqw/qpw9xcAs9oyN0tS
 8SmmGN27ghrkVSsGBXNcG+PSTu3pkkLjYZ6TQtKamrya9G+lRAsKRsQ+Yq+7Qv4e
 N6lCUlLJ99KqTMtwvIoxSpA1tz3ENHucOw2cJrw3kd9G0kil7GvDkIOBasd+kmwn
 ak+mnMJZzRhqSM7M5lKQOk8l92gKBHGbPy4xKb0st3dQkYptDvit0KcNSAuevtOp
 sRZpdbXaT3FA6xa5iEgggI6vZQGVmK1EaGoQqZ8vgVo75aovkjZyQWWiFVVOlEqr
 QjUCCQuixcbMRbZjgpojqva5nmLhFVhLCfoSH2XgttEQZhmTwypdRwM2/IlxV5q2
 xCofrDkhYOfIgHkuP6p68ukIPIfQ+4jotvsmXZ/HeD/xbx3TRyJRZadISr6wiuLm
 7zRXWaGCYomUIPJOOrpBQ9FsCglkaN63oB6VGuGKTg3g7kE2QrZ2/aGuexP+FAdh
 OrA8BlzxZzpqMKhjQVKOl9r6FU928MZn8nIAkMdQ/Ia1mOpb4rrPo4qCdf+tbhPO
 pmKtQPQjbszQ3UfTgShvfvDk43BeRim1DxZPFTauSu1FMpqWBCwQgXMynPFrf5TR
 HXF61G+jw5swDW6uJgW7bXdm7hHr15vRqQr54MgGS+T0OOa1df9MR0dJB5CGklfI
 ycLU6AAT+A==
 =A/qA
 -----END PGP SIGNATURE-----

Merge tag 'for-5.8/io_uring-2020-06-01' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "A relatively quiet round, mostly just fixes and code improvements. In
particular:

   - Make statx just use the generic statx handler, instead of open
     coding it. We don't need that anymore, as we always call it async
     safe (Bijan)

   - Enable closing of the ring itself. Also fixes O_PATH closure (me)

   - Properly name completion members (me)

   - Batch reap of dead file registrations (me)

   - Allow IORING_OP_POLL with double waitqueues (me)

   - Add tee(2) support (Pavel)

   - Remove double off read (Pavel)

   - Fix overflow cancellations (Pavel)

   - Improve CQ timeouts (Pavel)

   - Async defer drain fixes (Pavel)

   - Add support for enabling/disabling notifications on a registered
     eventfd (Stefano)

   - Remove dead state parameter (Xiaoguang)

   - Disable SQPOLL submit on dying ctx (Xiaoguang)

   - Various code cleanups"

* tag 'for-5.8/io_uring-2020-06-01' of git://git.kernel.dk/linux-block: (29 commits)
  io_uring: fix overflowed reqs cancellation
  io_uring: off timeouts based only on completions
  io_uring: move timeouts flushing to a helper
  statx: hide interfaces no longer used by io_uring
  io_uring: call statx directly
  statx: allow system call to be invoked from io_uring
  io_uring: add io_statx structure
  io_uring: get rid of manual punting in io_close
  io_uring: separate DRAIN flushing into a cold path
  io_uring: don't re-read sqe->off in timeout_prep()
  io_uring: simplify io_timeout locking
  io_uring: fix flush req->refs underflow
  io_uring: don't submit sqes when ctx->refs is dying
  io_uring: async task poll trigger cleanup
  io_uring: add tee(2) support
  splice: export do_tee()
  io_uring: don't repeat valid flag list
  io_uring: rename io_file_put()
  io_uring: remove req->needs_fixed_files
  io_uring: cleanup io_poll_remove_one() logic
  ...

fs/internal.h

@@ -185,5 +185,5 @@ 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 do_statx(int dfd, const char __user *filename, unsigned flags,
-int cp_statx(const struct kstat *stat, struct statx __user *buffer);
+	     unsigned int mask, struct statx __user *buffer);

fs/splice.c

@@ -1754,8 +1754,7 @@ static int link_pipe(struct pipe_inode_info *ipipe,
  * The 'flags' used are the SPLICE_F_* variants, currently the only
  * applicable one is SPLICE_F_NONBLOCK.
  */
-static long do_tee(struct file *in, struct file *out, size_t len,
+long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
-		   unsigned int flags)
 {
 	struct pipe_inode_info *ipipe = get_pipe_info(in);
 	struct pipe_inode_info *opipe = get_pipe_info(out);

fs/stat.c

@@ -153,7 +153,8 @@ int vfs_statx_fd(unsigned int fd, struct kstat *stat,
 }
 EXPORT_SYMBOL(vfs_statx_fd);
 
-inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags)
+static inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags,
+						 int flags)
 {
 	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
 		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
@@ -539,7 +540,7 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
-noinline_for_stack int
+static noinline_for_stack int
 cp_statx(const struct kstat *stat, struct statx __user *buffer)
 {
 	struct statx tmp;
@@ -574,6 +575,24 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
+int do_statx(int dfd, const char __user *filename, unsigned flags,
+	     unsigned int mask, struct statx __user *buffer)
+{
+	struct kstat stat;
+	int error;
+
+	if (mask & STATX__RESERVED)
+		return -EINVAL;
+	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+		return -EINVAL;
+
+	error = vfs_statx(dfd, filename, flags, &stat, mask);
+	if (error)
+		return error;
+
+	return cp_statx(&stat, buffer);
+}
+
 /**
  * sys_statx - System call to get enhanced stats
  * @dfd: Base directory to pathwalk from *or* fd to stat.
@@ -590,19 +609,7 @@ SYSCALL_DEFINE5(statx,
 		unsigned int, mask,
 		struct statx __user *, buffer)
 {
-	struct kstat stat;
+	return do_statx(dfd, filename, flags, mask, buffer);
-	int error;
-
-	if (mask & STATX__RESERVED)
-		return -EINVAL;
-	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
-		return -EINVAL;
-
-	error = vfs_statx(dfd, filename, flags, &stat, mask);
-	if (error)
-		return error;
-
-	return cp_statx(&stat, buffer);
 }
 
 #ifdef CONFIG_COMPAT

include/linux/splice.h

@@ -82,6 +82,9 @@ extern long do_splice(struct file *in, loff_t __user *off_in,
 		      struct file *out, loff_t __user *off_out,
 		      size_t len, unsigned int flags);
 
+extern long do_tee(struct file *in, struct file *out, size_t len,
+		   unsigned int flags);
+
 /*
  * for dynamic pipe sizing
  */

include/uapi/linux/io_uring.h

@@ -129,6 +129,7 @@ enum {
 	IORING_OP_SPLICE,
 	IORING_OP_PROVIDE_BUFFERS,
 	IORING_OP_REMOVE_BUFFERS,
+	IORING_OP_TEE,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -204,9 +205,18 @@ struct io_cqring_offsets {
 	__u32 ring_entries;
 	__u32 overflow;
 	__u32 cqes;
-	__u64 resv[2];
+	__u32 flags;
+	__u32 resv1;
+	__u64 resv2;
 };
 
+/*
+ * cq_ring->flags
+ */
+
+/* disable eventfd notifications */
+#define IORING_CQ_EVENTFD_DISABLED	(1U << 0)
+
 /*
  * io_uring_enter(2) flags
  */