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
  ...

3 files changed, 31 insertions, 5 deletions

diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index bc6d79b00c4e..8f000fada5a4 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -61,6 +61,15 @@ static inline void eventpoll_release(struct file *file)
 	eventpoll_release_file(file);
 }
 
+int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
+		 bool nonblock);
+
+/* 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;
+}
+
 #else
 
 static inline void eventpoll_init_file(struct file *file) {}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 67f8451b9a12..1233bf45164d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2323,6 +2323,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
+extern int do_madvise(unsigned long start, size_t len_in, int behavior);
 
 static inline unsigned long
 do_mmap_pgoff(struct file *file, unsigned long addr,
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 390031e816dc..22d9d183950d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -210,15 +210,17 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_tryget - try to increment a percpu refcount
+ * percpu_ref_tryget_many - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
+ * @nr: number of references to get
  *
- * Increment a percpu refcount unless its count already reached zero.
+ * Increment a percpu refcount  by @nr unless its count already reached zero.
  * Returns %true on success; %false on failure.
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+static inline bool percpu_ref_tryget_many(struct percpu_ref *ref,
+					  unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 	bool ret;
@@ -226,10 +228,10 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count)) {
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 		ret = true;
 	} else {
-		ret = atomic_long_inc_not_zero(&ref->count);
+		ret = atomic_long_add_unless(&ref->count, nr, 0);
 	}
 
 	rcu_read_unlock();
@@ -238,6 +240,20 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 }
 
 /**
+ * percpu_ref_tryget - try to increment a percpu refcount
+ * @ref: percpu_ref to try-get
+ *
+ * Increment a percpu refcount unless its count already reached zero.
+ * Returns %true on success; %false on failure.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+{
+	return percpu_ref_tryget_many(ref, 1);
+}
+
+/**
  * percpu_ref_tryget_live - try to increment a live percpu refcount
  * @ref: percpu_ref to try-get
  *