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
  ...

1 files changed, 1820 insertions, 380 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e54556b0fcc6..ac5340fdcdfe 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -46,6 +46,7 @@
 #include <linux/compat.h>
 #include <linux/refcount.h>
 #include <linux/uio.h>
+#include <linux/bits.h>
 
 #include <linux/sched/signal.h>
 #include <linux/fs.h>
@@ -70,6 +71,10 @@
 #include <linux/sizes.h>
 #include <linux/hugetlb.h>
 #include <linux/highmem.h>
+#include <linux/namei.h>
+#include <linux/fsnotify.h>
+#include <linux/fadvise.h>
+#include <linux/eventpoll.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -177,6 +182,21 @@ struct fixed_file_table {
 	struct file		**files;
 };
 
+enum {
+	FFD_F_ATOMIC,
+};
+
+struct fixed_file_data {
+	struct fixed_file_table		*table;
+	struct io_ring_ctx		*ctx;
+
+	struct percpu_ref		refs;
+	struct llist_head		put_llist;
+	unsigned long			state;
+	struct work_struct		ref_work;
+	struct completion		done;
+};
+
 struct io_ring_ctx {
 	struct {
 		struct percpu_ref	refs;
@@ -184,10 +204,11 @@ struct io_ring_ctx {
 
 	struct {
 		unsigned int		flags;
-		bool			compat;
-		bool			account_mem;
-		bool			cq_overflow_flushed;
-		bool			drain_next;
+		int			compat: 1;
+		int			account_mem: 1;
+		int			cq_overflow_flushed: 1;
+		int			drain_next: 1;
+		int			eventfd_async: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -207,13 +228,14 @@ struct io_ring_ctx {
 		unsigned		sq_thread_idle;
 		unsigned		cached_sq_dropped;
 		atomic_t		cached_cq_overflow;
-		struct io_uring_sqe	*sq_sqes;
+		unsigned long		sq_check_overflow;
 
 		struct list_head	defer_list;
 		struct list_head	timeout_list;
 		struct list_head	cq_overflow_list;
 
 		wait_queue_head_t	inflight_wait;
+		struct io_uring_sqe	*sq_sqes;
 	} ____cacheline_aligned_in_smp;
 
 	struct io_rings	*rings;
@@ -229,8 +251,10 @@ struct io_ring_ctx {
 	 * readers must ensure that ->refs is alive as long as the file* is
 	 * used. Only updated through io_uring_register(2).
 	 */
-	struct fixed_file_table	*file_table;
+	struct fixed_file_data	*file_data;
 	unsigned		nr_user_files;
+	int 			ring_fd;
+	struct file 		*ring_file;
 
 	/* if used, fixed mapped user buffers */
 	unsigned		nr_user_bufs;
@@ -250,11 +274,14 @@ struct io_ring_ctx {
 	struct socket		*ring_sock;
 #endif
 
+	struct idr		personality_idr;
+
 	struct {
 		unsigned		cached_cq_tail;
 		unsigned		cq_entries;
 		unsigned		cq_mask;
 		atomic_t		cq_timeouts;
+		unsigned long		cq_check_overflow;
 		struct wait_queue_head	cq_wait;
 		struct fasync_struct	*cq_fasync;
 		struct eventfd_ctx	*cq_ev_fd;
@@ -267,7 +294,8 @@ struct io_ring_ctx {
 
 	struct {
 		spinlock_t		completion_lock;
-		bool			poll_multi_file;
+		struct llist_head	poll_llist;
+
 		/*
 		 * ->poll_list is protected by the ctx->uring_lock for
 		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
@@ -277,6 +305,7 @@ struct io_ring_ctx {
 		struct list_head	poll_list;
 		struct hlist_head	*cancel_hash;
 		unsigned		cancel_hash_bits;
+		bool			poll_multi_file;
 
 		spinlock_t		inflight_lock;
 		struct list_head	inflight_list;
@@ -299,6 +328,12 @@ struct io_poll_iocb {
 	struct wait_queue_entry		wait;
 };
 
+struct io_close {
+	struct file			*file;
+	struct file			*put_file;
+	int				fd;
+};
+
 struct io_timeout_data {
 	struct io_kiocb			*req;
 	struct hrtimer			timer;
@@ -319,6 +354,7 @@ struct io_sync {
 	loff_t				len;
 	loff_t				off;
 	int				flags;
+	int				mode;
 };
 
 struct io_cancel {
@@ -348,8 +384,52 @@ struct io_connect {
 
 struct io_sr_msg {
 	struct file			*file;
-	struct user_msghdr __user	*msg;
+	union {
+		struct user_msghdr __user *msg;
+		void __user		*buf;
+	};
 	int				msg_flags;
+	size_t				len;
+};
+
+struct io_open {
+	struct file			*file;
+	int				dfd;
+	union {
+		unsigned		mask;
+	};
+	struct filename			*filename;
+	struct statx __user		*buffer;
+	struct open_how			how;
+};
+
+struct io_files_update {
+	struct file			*file;
+	u64				arg;
+	u32				nr_args;
+	u32				offset;
+};
+
+struct io_fadvise {
+	struct file			*file;
+	u64				offset;
+	u32				len;
+	u32				advice;
+};
+
+struct io_madvise {
+	struct file			*file;
+	u64				addr;
+	u32				len;
+	u32				advice;
+};
+
+struct io_epoll {
+	struct file			*file;
+	int				epfd;
+	int				op;
+	int				fd;
+	struct epoll_event		event;
 };
 
 struct io_async_connect {
@@ -370,15 +450,79 @@ struct io_async_rw {
 	ssize_t				size;
 };
 
+struct io_async_open {
+	struct filename			*filename;
+};
+
 struct io_async_ctx {
 	union {
 		struct io_async_rw	rw;
 		struct io_async_msghdr	msg;
 		struct io_async_connect	connect;
 		struct io_timeout_data	timeout;
+		struct io_async_open	open;
 	};
 };
 
+enum {
+	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
+	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
+	REQ_F_LINK_BIT		= IOSQE_IO_LINK_BIT,
+	REQ_F_HARDLINK_BIT	= IOSQE_IO_HARDLINK_BIT,
+	REQ_F_FORCE_ASYNC_BIT	= IOSQE_ASYNC_BIT,
+
+	REQ_F_LINK_NEXT_BIT,
+	REQ_F_FAIL_LINK_BIT,
+	REQ_F_INFLIGHT_BIT,
+	REQ_F_CUR_POS_BIT,
+	REQ_F_NOWAIT_BIT,
+	REQ_F_IOPOLL_COMPLETED_BIT,
+	REQ_F_LINK_TIMEOUT_BIT,
+	REQ_F_TIMEOUT_BIT,
+	REQ_F_ISREG_BIT,
+	REQ_F_MUST_PUNT_BIT,
+	REQ_F_TIMEOUT_NOSEQ_BIT,
+	REQ_F_COMP_LOCKED_BIT,
+};
+
+enum {
+	/* ctx owns file */
+	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	/* drain existing IO first */
+	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	/* linked sqes */
+	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	/* doesn't sever on completion < 0 */
+	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	/* IOSQE_ASYNC */
+	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+
+	/* already grabbed next link */
+	REQ_F_LINK_NEXT		= BIT(REQ_F_LINK_NEXT_BIT),
+	/* fail rest of links */
+	REQ_F_FAIL_LINK		= BIT(REQ_F_FAIL_LINK_BIT),
+	/* on inflight list */
+	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	/* read/write uses file position */
+	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	/* must not punt to workers */
+	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	/* polled IO has completed */
+	REQ_F_IOPOLL_COMPLETED	= BIT(REQ_F_IOPOLL_COMPLETED_BIT),
+	/* has linked timeout */
+	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	/* timeout request */
+	REQ_F_TIMEOUT		= BIT(REQ_F_TIMEOUT_BIT),
+	/* regular file */
+	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	/* must be punted even for NONBLOCK */
+	REQ_F_MUST_PUNT		= BIT(REQ_F_MUST_PUNT_BIT),
+	/* no timeout sequence */
+	REQ_F_TIMEOUT_NOSEQ	= BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
+	/* completion under lock */
+	REQ_F_COMP_LOCKED	= BIT(REQ_F_COMP_LOCKED_BIT),
+};
+
 /*
  * NOTE! Each of the iocb union members has the file pointer
  * as the first entry in their struct definition. So you can
@@ -396,11 +540,19 @@ struct io_kiocb {
 		struct io_timeout	timeout;
 		struct io_connect	connect;
 		struct io_sr_msg	sr_msg;
+		struct io_open		open;
+		struct io_close		close;
+		struct io_files_update	files_update;
+		struct io_fadvise	fadvise;
+		struct io_madvise	madvise;
+		struct io_epoll		epoll;
 	};
 
 	struct io_async_ctx		*io;
-	struct file			*ring_file;
-	int				ring_fd;
+	/*
+	 * llist_node is only used for poll deferred completions
+	 */
+	struct llist_node		llist_node;
 	bool				has_user;
 	bool				in_async;
 	bool				needs_fixed_file;
@@ -414,23 +566,6 @@ struct io_kiocb {
 	struct list_head	link_list;
 	unsigned int		flags;
 	refcount_t		refs;
-#define REQ_F_NOWAIT		1	/* must not punt to workers */
-#define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
-#define REQ_F_FIXED_FILE	4	/* ctx owns file */
-#define REQ_F_LINK_NEXT		8	/* already grabbed next link */
-#define REQ_F_IO_DRAIN		16	/* drain existing IO first */
-#define REQ_F_IO_DRAINED	32	/* drain done */
-#define REQ_F_LINK		64	/* linked sqes */
-#define REQ_F_LINK_TIMEOUT	128	/* has linked timeout */
-#define REQ_F_FAIL_LINK		256	/* fail rest of links */
-#define REQ_F_DRAIN_LINK	512	/* link should be fully drained */
-#define REQ_F_TIMEOUT		1024	/* timeout request */
-#define REQ_F_ISREG		2048	/* regular file */
-#define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
-#define REQ_F_TIMEOUT_NOSEQ	8192	/* no timeout sequence */
-#define REQ_F_INFLIGHT		16384	/* on inflight list */
-#define REQ_F_COMP_LOCKED	32768	/* completion under lock */
-#define REQ_F_HARDLINK		65536	/* doesn't sever on completion < 0 */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -463,14 +598,162 @@ struct io_submit_state {
 	unsigned int		ios_left;
 };
 
+struct io_op_def {
+	/* needs req->io allocated for deferral/async */
+	unsigned		async_ctx : 1;
+	/* needs current->mm setup, does mm access */
+	unsigned		needs_mm : 1;
+	/* needs req->file assigned */
+	unsigned		needs_file : 1;
+	/* needs req->file assigned IFF fd is >= 0 */
+	unsigned		fd_non_neg : 1;
+	/* hash wq insertion if file is a regular file */
+	unsigned		hash_reg_file : 1;
+	/* unbound wq insertion if file is a non-regular file */
+	unsigned		unbound_nonreg_file : 1;
+	/* opcode is not supported by this kernel */
+	unsigned		not_supported : 1;
+	/* needs file table */
+	unsigned		file_table : 1;
+};
+
+static const struct io_op_def io_op_defs[] = {
+	[IORING_OP_NOP] = {},
+	[IORING_OP_READV] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITEV] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FSYNC] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_READ_FIXED] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITE_FIXED] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_POLL_ADD] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_POLL_REMOVE] = {},
+	[IORING_OP_SYNC_FILE_RANGE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_SENDMSG] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_RECVMSG] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_TIMEOUT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+	},
+	[IORING_OP_TIMEOUT_REMOVE] = {},
+	[IORING_OP_ACCEPT] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_ASYNC_CANCEL] = {},
+	[IORING_OP_LINK_TIMEOUT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+	},
+	[IORING_OP_CONNECT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FALLOCATE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_OPENAT] = {
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_CLOSE] = {
+		.needs_file		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_FILES_UPDATE] = {
+		.needs_mm		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_STATX] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+	},
+	[IORING_OP_READ] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITE] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FADVISE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_MADVISE] = {
+		.needs_mm		= 1,
+	},
+	[IORING_OP_SEND] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_RECV] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_OPENAT2] = {
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_EPOLL_CTL] = {
+		.unbound_nonreg_file	= 1,
+		.file_table		= 1,
+	},
+};
+
 static void io_wq_submit_work(struct io_wq_work **workptr);
 static void io_cqring_fill_event(struct io_kiocb *req, long res);
-static void __io_free_req(struct io_kiocb *req);
 static void io_put_req(struct io_kiocb *req);
-static void io_double_put_req(struct io_kiocb *req);
 static void __io_double_put_req(struct io_kiocb *req);
 static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
 static void io_queue_linked_timeout(struct io_kiocb *req);
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+				 struct io_uring_files_update *ip,
+				 unsigned nr_args);
+static int io_grab_files(struct io_kiocb *req);
 
 static struct kmem_cache *req_cachep;
 
@@ -537,9 +820,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->completions[0]);
 	init_completion(&ctx->completions[1]);
+	idr_init(&ctx->personality_idr);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
 	spin_lock_init(&ctx->completion_lock);
+	init_llist_head(&ctx->poll_llist);
 	INIT_LIST_HEAD(&ctx->poll_list);
 	INIT_LIST_HEAD(&ctx->defer_list);
 	INIT_LIST_HEAD(&ctx->timeout_list);
@@ -566,7 +851,7 @@ static inline bool __req_need_defer(struct io_kiocb *req)
 
 static inline bool req_need_defer(struct io_kiocb *req)
 {
-	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN)
+	if (unlikely(req->flags & REQ_F_IO_DRAIN))
 		return __req_need_defer(req);
 
 	return false;
@@ -606,53 +891,53 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
 
-	if (ctx->cached_cq_tail != READ_ONCE(rings->cq.tail)) {
-		/* order cqe stores with ring update */
-		smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
+	/* order cqe stores with ring update */
+	smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
 
-		if (wq_has_sleeper(&ctx->cq_wait)) {
-			wake_up_interruptible(&ctx->cq_wait);
-			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
-		}
+	if (wq_has_sleeper(&ctx->cq_wait)) {
+		wake_up_interruptible(&ctx->cq_wait);
+		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+	}
+}
+
+static inline void io_req_work_grab_env(struct io_kiocb *req,
+					const struct io_op_def *def)
+{
+	if (!req->work.mm && def->needs_mm) {
+		mmgrab(current->mm);
+		req->work.mm = current->mm;
 	}
+	if (!req->work.creds)
+		req->work.creds = get_current_cred();
 }
 
-static inline bool io_req_needs_user(struct io_kiocb *req)
+static inline void io_req_work_drop_env(struct io_kiocb *req)
 {
-	return !(req->opcode == IORING_OP_READ_FIXED ||
-		 req->opcode == IORING_OP_WRITE_FIXED);
+	if (req->work.mm) {
+		mmdrop(req->work.mm);
+		req->work.mm = NULL;
+	}
+	if (req->work.creds) {
+		put_cred(req->work.creds);
+		req->work.creds = NULL;
+	}
 }
 
 static inline bool io_prep_async_work(struct io_kiocb *req,
 				      struct io_kiocb **link)
 {
+	const struct io_op_def *def = &io_op_defs[req->opcode];
 	bool do_hashed = false;
 
-	switch (req->opcode) {
-	case IORING_OP_WRITEV:
-	case IORING_OP_WRITE_FIXED:
-		/* only regular files should be hashed for writes */
-		if (req->flags & REQ_F_ISREG)
+	if (req->flags & REQ_F_ISREG) {
+		if (def->hash_reg_file)
 			do_hashed = true;
-		/* fall-through */
-	case IORING_OP_READV:
-	case IORING_OP_READ_FIXED:
-	case IORING_OP_SENDMSG:
-	case IORING_OP_RECVMSG:
-	case IORING_OP_ACCEPT:
-	case IORING_OP_POLL_ADD:
-	case IORING_OP_CONNECT:
-		/*
-		 * We know REQ_F_ISREG is not set on some of these
-		 * opcodes, but this enables us to keep the check in
-		 * just one place.
-		 */
-		if (!(req->flags & REQ_F_ISREG))
+	} else {
+		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
-		break;
 	}
-	if (io_req_needs_user(req))
-		req->work.flags |= IO_WQ_WORK_NEEDS_USER;
+
+	io_req_work_grab_env(req, def);
 
 	*link = io_prep_linked_timeout(req);
 	return do_hashed;
@@ -711,10 +996,8 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 
 	__io_commit_cqring(ctx);
 
-	while ((req = io_get_deferred_req(ctx)) != NULL) {
-		req->flags |= REQ_F_IO_DRAINED;
+	while ((req = io_get_deferred_req(ctx)) != NULL)
 		io_queue_async_work(req);
-	}
 }
 
 static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
@@ -735,13 +1018,20 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	return &rings->cqes[tail & ctx->cq_mask];
 }
 
+static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
+{
+	if (!ctx->eventfd_async)
+		return true;
+	return io_wq_current_is_worker() || in_interrupt();
+}
+
 static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 {
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
 	if (waitqueue_active(&ctx->sqo_wait))
 		wake_up(&ctx->sqo_wait);
-	if (ctx->cq_ev_fd)
+	if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx))
 		eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
@@ -766,7 +1056,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 
 	/* if force is set, the ring is going away. always drop after that */
 	if (force)
-		ctx->cq_overflow_flushed = true;
+		ctx->cq_overflow_flushed = 1;
 
 	cqe = NULL;
 	while (!list_empty(&ctx->cq_overflow_list)) {
@@ -788,6 +1078,10 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	}
 
 	io_commit_cqring(ctx);
+	if (cqe) {
+		clear_bit(0, &ctx->sq_check_overflow);
+		clear_bit(0, &ctx->cq_check_overflow);
+	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
 
@@ -821,6 +1115,10 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
 	} else {
+		if (list_empty(&ctx->cq_overflow_list)) {
+			set_bit(0, &ctx->sq_check_overflow);
+			set_bit(0, &ctx->cq_check_overflow);
+		}
 		refcount_inc(&req->refs);
 		req->result = res;
 		list_add_tail(&req->list, &ctx->cq_overflow_list);
@@ -863,9 +1161,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct io_kiocb *req;
 
-	if (!percpu_ref_tryget(&ctx->refs))
-		return NULL;
-
 	if (!state) {
 		req = kmem_cache_alloc(req_cachep, gfp);
 		if (unlikely(!req))
@@ -898,7 +1193,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 
 got_it:
 	req->io = NULL;
-	req->ring_file = NULL;
 	req->file = NULL;
 	req->ctx = ctx;
 	req->flags = 0;
@@ -915,24 +1209,35 @@ fallback:
 	return NULL;
 }
 
-static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+static void __io_req_do_free(struct io_kiocb *req)
 {
-	if (*nr) {
-		kmem_cache_free_bulk(req_cachep, *nr, reqs);
-		percpu_ref_put_many(&ctx->refs, *nr);
-		*nr = 0;
+	if (likely(!io_is_fallback_req(req)))
+		kmem_cache_free(req_cachep, req);
+	else
+		clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+}
+
+static void __io_req_aux_free(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	kfree(req->io);
+	if (req->file) {
+		if (req->flags & REQ_F_FIXED_FILE)
+			percpu_ref_put(&ctx->file_data->refs);
+		else
+			fput(req->file);
 	}
+
+	io_req_work_drop_env(req);
 }
 
 static void __io_free_req(struct io_kiocb *req)
 {
-	struct io_ring_ctx *ctx = req->ctx;
+	__io_req_aux_free(req);
 
-	if (req->io)
-		kfree(req->io);
-	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
-		fput(req->file);
 	if (req->flags & REQ_F_INFLIGHT) {
+		struct io_ring_ctx *ctx = req->ctx;
 		unsigned long flags;
 
 		spin_lock_irqsave(&ctx->inflight_lock, flags);
@@ -941,11 +1246,63 @@ static void __io_free_req(struct io_kiocb *req)
 			wake_up(&ctx->inflight_wait);
 		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	}
-	percpu_ref_put(&ctx->refs);
-	if (likely(!io_is_fallback_req(req)))
-		kmem_cache_free(req_cachep, req);
-	else
-		clear_bit_unlock(0, (unsigned long *) ctx->fallback_req);
+
+	percpu_ref_put(&req->ctx->refs);
+	__io_req_do_free(req);
+}
+
+struct req_batch {
+	void *reqs[IO_IOPOLL_BATCH];
+	int to_free;
+	int need_iter;
+};
+
+static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
+{
+	int fixed_refs = rb->to_free;
+
+	if (!rb->to_free)
+		return;
+	if (rb->need_iter) {
+		int i, inflight = 0;
+		unsigned long flags;
+
+		fixed_refs = 0;
+		for (i = 0; i < rb->to_free; i++) {
+			struct io_kiocb *req = rb->reqs[i];
+
+			if (req->flags & REQ_F_FIXED_FILE) {
+				req->file = NULL;
+				fixed_refs++;
+			}
+			if (req->flags & REQ_F_INFLIGHT)
+				inflight++;
+			__io_req_aux_free(req);
+		}
+		if (!inflight)
+			goto do_free;
+
+		spin_lock_irqsave(&ctx->inflight_lock, flags);
+		for (i = 0; i < rb->to_free; i++) {
+			struct io_kiocb *req = rb->reqs[i];
+
+			if (req->flags & REQ_F_INFLIGHT) {
+				list_del(&req->inflight_entry);
+				if (!--inflight)
+					break;
+			}
+		}
+		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+
+		if (waitqueue_active(&ctx->inflight_wait))
+			wake_up(&ctx->inflight_wait);
+	}
+do_free:
+	kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
+	if (fixed_refs)
+		percpu_ref_put_many(&ctx->file_data->refs, fixed_refs);
+	percpu_ref_put_many(&ctx->refs, rb->to_free);
+	rb->to_free = rb->need_iter = 0;
 }
 
 static bool io_link_cancel_timeout(struct io_kiocb *req)
@@ -1118,19 +1475,21 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
 {
 	struct io_rings *rings = ctx->rings;
 
-	/*
-	 * noflush == true is from the waitqueue handler, just ensure we wake
-	 * up the task, and the next invocation will flush the entries. We
-	 * cannot safely to it from here.
-	 */
-	if (noflush && !list_empty(&ctx->cq_overflow_list))
-		return -1U;
+	if (test_bit(0, &ctx->cq_check_overflow)) {
+		/*
+		 * noflush == true is from the waitqueue handler, just ensure
+		 * we wake up the task, and the next invocation will flush the
+		 * entries. We cannot safely to it from here.
+		 */
+		if (noflush && !list_empty(&ctx->cq_overflow_list))
+			return -1U;
 
-	io_cqring_overflow_flush(ctx, false);
+		io_cqring_overflow_flush(ctx, false);
+	}
 
 	/* See comment at the top of this file */
 	smp_rmb();
-	return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
+	return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
 }
 
 static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
@@ -1141,17 +1500,30 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
 }
 
+static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
+{
+	if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req))
+		return false;
+
+	if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+		rb->need_iter++;
+
+	rb->reqs[rb->to_free++] = req;
+	if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
+		io_free_req_many(req->ctx, rb);
+	return true;
+}
+
 /*
  * Find and free completed poll iocbs
  */
 static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			       struct list_head *done)
 {
-	void *reqs[IO_IOPOLL_BATCH];
+	struct req_batch rb;
 	struct io_kiocb *req;
-	int to_free;
 
-	to_free = 0;
+	rb.to_free = rb.need_iter = 0;
 	while (!list_empty(done)) {
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
@@ -1159,26 +1531,13 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		io_cqring_fill_event(req, req->result);
 		(*nr_events)++;
 
-		if (refcount_dec_and_test(&req->refs)) {
-			/* If we're not using fixed files, we have to pair the
-			 * completion part with the file put. Use regular
-			 * completions for those, only batch free for fixed
-			 * file and non-linked commands.
-			 */
-			if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
-			    REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
-			    !req->io) {
-				reqs[to_free++] = req;
-				if (to_free == ARRAY_SIZE(reqs))
-					io_free_req_many(ctx, reqs, &to_free);
-			} else {
-				io_free_req(req);
-			}
-		}
+		if (refcount_dec_and_test(&req->refs) &&
+		    !io_req_multi_free(&rb, req))
+			io_free_req(req);
 	}
 
 	io_commit_cqring(ctx);
-	io_free_req_many(ctx, reqs, &to_free);
+	io_free_req_many(ctx, &rb);
 }
 
 static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
@@ -1503,6 +1862,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		req->flags |= REQ_F_ISREG;
 
 	kiocb->ki_pos = READ_ONCE(sqe->off);
+	if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) {
+		req->flags |= REQ_F_CUR_POS;
+		kiocb->ki_pos = req->file->f_pos;
+	}
 	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
 	kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
 
@@ -1574,6 +1937,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
 		       bool in_async)
 {
+	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
+
+	if (req->flags & REQ_F_CUR_POS)
+		req->file->f_pos = kiocb->ki_pos;
 	if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw)
 		*nxt = __io_complete_rw(kiocb, ret);
 	else
@@ -1671,6 +2038,13 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	if (req->rw.kiocb.private)
 		return -EINVAL;
 
+	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
+		ssize_t ret;
+		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
+		*iovec = NULL;
+		return ret;
+	}
+
 	if (req->io) {
 		struct io_async_rw *iorw = &req->io->rw;
 
@@ -1767,6 +2141,8 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
 
 static int io_alloc_async_ctx(struct io_kiocb *req)
 {
+	if (!io_op_defs[req->opcode].async_ctx)
+		return 0;
 	req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
 	return req->io == NULL;
 }
@@ -1786,8 +2162,7 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
 			     struct iovec *iovec, struct iovec *fast_iov,
 			     struct iov_iter *iter)
 {
-	if (req->opcode == IORING_OP_READ_FIXED ||
-	    req->opcode == IORING_OP_WRITE_FIXED)
+	if (!io_op_defs[req->opcode].async_ctx)
 		return 0;
 	if (!req->io && io_alloc_async_ctx(req))
 		return -ENOMEM;
@@ -2101,6 +2476,421 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
 	return 0;
 }
 
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct io_kiocb *nxt = NULL;
+	int ret;
+
+	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
+				req->sync.len);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, &nxt);
+	if (nxt)
+		io_wq_assign_next(workptr, nxt);
+}
+
+static int io_fallocate_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+	if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)
+		return -EINVAL;
+
+	req->sync.off = READ_ONCE(sqe->off);
+	req->sync.len = READ_ONCE(sqe->addr);
+	req->sync.mode = READ_ONCE(sqe->len);
+	return 0;
+}
+
+static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt,
+			bool force_nonblock)
+{
+	struct io_wq_work *work, *old_work;
+
+	/* fallocate always requiring blocking context */
+	if (force_nonblock) {
+		io_put_req(req);
+		req->work.func = io_fallocate_finish;
+		return -EAGAIN;
+	}
+
+	work = old_work = &req->work;
+	io_fallocate_finish(&work);
+	if (work && work != old_work)
+		*nxt = container_of(work, struct io_kiocb, work);
+
+	return 0;
+}
+
+static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	const char __user *fname;
+	int ret;
+
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->open.dfd = READ_ONCE(sqe->fd);
+	req->open.how.mode = READ_ONCE(sqe->len);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	req->open.how.flags = READ_ONCE(sqe->open_flags);
+
+	req->open.filename = getname(fname);
+	if (IS_ERR(req->open.filename)) {
+		ret = PTR_ERR(req->open.filename);
+		req->open.filename = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct open_how __user *how;
+	const char __user *fname;
+	size_t len;
+	int ret;
+
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->open.dfd = READ_ONCE(sqe->fd);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	len = READ_ONCE(sqe->len);
+
+	if (len < OPEN_HOW_SIZE_VER0)
+		return -EINVAL;
+
+	ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how,
+					len);
+	if (ret)
+		return ret;
+
+	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
+		req->open.how.flags |= O_LARGEFILE;
+
+	req->open.filename = getname(fname);
+	if (IS_ERR(req->open.filename)) {
+		ret = PTR_ERR(req->open.filename);
+		req->open.filename = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
+		      bool force_nonblock)
+{
+	struct open_flags op;
+	struct file *file;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	ret = build_open_flags(&req->open.how, &op);
+	if (ret)
+		goto err;
+
+	ret = get_unused_fd_flags(req->open.how.flags);
+	if (ret < 0)
+		goto err;
+
+	file = do_filp_open(req->open.dfd, req->open.filename, &op);
+	if (IS_ERR(file)) {
+		put_unused_fd(ret);
+		ret = PTR_ERR(file);
+	} else {
+		fsnotify_open(file);
+		fd_install(ret, file);
+	}
+err:
+	putname(req->open.filename);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+}
+
+static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
+		     bool force_nonblock)
+{
+	req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
+	return io_openat2(req, nxt, force_nonblock);
+}
+
+static int io_epoll_ctl_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_EPOLL)
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->epoll.epfd = READ_ONCE(sqe->fd);
+	req->epoll.op = READ_ONCE(sqe->len);
+	req->epoll.fd = READ_ONCE(sqe->off);
+
+	if (ep_op_has_event(req->epoll.op)) {
+		struct epoll_event __user *ev;
+
+		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
+		if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
+			return -EFAULT;
+	}
+
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
+			bool force_nonblock)
+{
+#if defined(CONFIG_EPOLL)
+	struct io_epoll *ie = &req->epoll;
+	int ret;
+
+	ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
+	if (force_nonblock && ret == -EAGAIN)
+		return -EAGAIN;
+
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	if (sqe->ioprio || sqe->buf_index ||