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
  ...

5 files changed, 107 insertions, 15 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
  *
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index b352d66b5d51..27bd9e4f927b 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -320,6 +320,7 @@ TRACE_EVENT(io_uring_complete,
  * io_uring_submit_sqe - called before submitting one SQE
  *
  * @ctx:		pointer to a ring context structure
+ * @opcode:		opcode of request
  * @user_data:		user data associated with the request
  * @force_nonblock:	whether a context blocking or not
  * @sq_thread:		true if sq_thread has submitted this SQE
@@ -329,12 +330,14 @@ TRACE_EVENT(io_uring_complete,
  */
 TRACE_EVENT(io_uring_submit_sqe,
 
-	TP_PROTO(void *ctx, u64 user_data, bool force_nonblock, bool sq_thread),
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock,
+		 bool sq_thread),
 
-	TP_ARGS(ctx, user_data, force_nonblock, sq_thread),
+	TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
 		__field(  u64,		user_data	)
 		__field(  bool,		force_nonblock	)
 		__field(  bool,		sq_thread	)
@@ -342,13 +345,15 @@ TRACE_EVENT(io_uring_submit_sqe,
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
 		__entry->user_data	= user_data;
 		__entry->force_nonblock	= force_nonblock;
 		__entry->sq_thread	= sq_thread;
 	),
 
-	TP_printk("ring %p, user data 0x%llx, non block %d, sq_thread %d",
-			  __entry->ctx, (unsigned long long) __entry->user_data,
+	TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
 			  __entry->force_nonblock, __entry->sq_thread)
 );
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 55cfcb71606d..3f7961c1c243 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -34,21 +34,43 @@ struct io_uring_sqe {
 		__u32		timeout_flags;
 		__u32		accept_flags;
 		__u32		cancel_flags;
+		__u32		open_flags;
+		__u32		statx_flags;
+		__u32		fadvise_advice;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
-		__u16	buf_index;	/* index into fixed buffers, if used */
+		struct {
+			/* index into fixed buffers, if used */
+			__u16	buf_index;
+			/* personality to use, if used */
+			__u16	personality;
+		};
 		__u64	__pad2[3];
 	};
 };
 
+enum {
+	IOSQE_FIXED_FILE_BIT,
+	IOSQE_IO_DRAIN_BIT,
+	IOSQE_IO_LINK_BIT,
+	IOSQE_IO_HARDLINK_BIT,
+	IOSQE_ASYNC_BIT,
+};
+
 /*
  * sqe->flags
  */
-#define IOSQE_FIXED_FILE	(1U << 0)	/* use fixed fileset */
-#define IOSQE_IO_DRAIN		(1U << 1)	/* issue after inflight IO */
-#define IOSQE_IO_LINK		(1U << 2)	/* links next sqe */
-#define IOSQE_IO_HARDLINK	(1U << 3)	/* like LINK, but stronger */
+/* use fixed fileset */
+#define IOSQE_FIXED_FILE	(1U << IOSQE_FIXED_FILE_BIT)
+/* issue after inflight IO */
+#define IOSQE_IO_DRAIN		(1U << IOSQE_IO_DRAIN_BIT)
+/* links next sqe */
+#define IOSQE_IO_LINK		(1U << IOSQE_IO_LINK_BIT)
+/* like LINK, but stronger */
+#define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
+/* always go async */
+#define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
 
 /*
  * io_uring_setup() flags
@@ -57,6 +79,8 @@ struct io_uring_sqe {
 #define IORING_SETUP_SQPOLL	(1U << 1)	/* SQ poll thread */
 #define IORING_SETUP_SQ_AFF	(1U << 2)	/* sq_thread_cpu is valid */
 #define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
+#define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
+#define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
 
 enum {
 	IORING_OP_NOP,
@@ -76,6 +100,19 @@ enum {
 	IORING_OP_ASYNC_CANCEL,
 	IORING_OP_LINK_TIMEOUT,
 	IORING_OP_CONNECT,
+	IORING_OP_FALLOCATE,
+	IORING_OP_OPENAT,
+	IORING_OP_CLOSE,
+	IORING_OP_FILES_UPDATE,
+	IORING_OP_STATX,
+	IORING_OP_READ,
+	IORING_OP_WRITE,
+	IORING_OP_FADVISE,
+	IORING_OP_MADVISE,
+	IORING_OP_SEND,
+	IORING_OP_RECV,
+	IORING_OP_OPENAT2,
+	IORING_OP_EPOLL_CTL,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -153,7 +190,8 @@ struct io_uring_params {
 	__u32 sq_thread_cpu;
 	__u32 sq_thread_idle;
 	__u32 features;
-	__u32 resv[4];
+	__u32 wq_fd;
+	__u32 resv[3];
 	struct io_sqring_offsets sq_off;
 	struct io_cqring_offsets cq_off;
 };
@@ -164,6 +202,8 @@ struct io_uring_params {
 #define IORING_FEAT_SINGLE_MMAP		(1U << 0)
 #define IORING_FEAT_NODROP		(1U << 1)
 #define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
+#define IORING_FEAT_RW_CUR_POS		(1U << 3)
+#define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -175,6 +215,10 @@ struct io_uring_params {
 #define IORING_REGISTER_EVENTFD		4
 #define IORING_UNREGISTER_EVENTFD	5
 #define IORING_REGISTER_FILES_UPDATE	6
+#define IORING_REGISTER_EVENTFD_ASYNC	7
+#define IORING_REGISTER_PROBE		8
+#define IORING_REGISTER_PERSONALITY	9
+#define IORING_UNREGISTER_PERSONALITY	10
 
 struct io_uring_files_update {
 	__u32 offset;
@@ -182,4 +226,21 @@ struct io_uring_files_update {
 	__aligned_u64 /* __s32 * */ fds;
 };
 
+#define IO_URING_OP_SUPPORTED	(1U << 0)
+
+struct io_uring_probe_op {
+	__u8 op;
+	__u8 resv;
+	__u16 flags;	/* IO_URING_OP_* flags */
+	__u32 resv2;
+};
+
+struct io_uring_probe {
+	__u8 last_op;	/* last opcode supported */
+	__u8 ops_len;	/* length of ops[] array below */
+	__u16 resv;
+	__u32 resv2[3];
+	struct io_uring_probe_op ops[0];
+};
+
 #endif