Merge tag 'for-5.7/io_uring-2020-03-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Here are the io_uring changes for this merge window. Light on new
  features this time around (just splice + buffer selection), lots of
  cleanups, fixes, and improvements to existing support. In particular,
  this contains:

   - Cleanup fixed file update handling for stack fallback (Hillf)

   - Re-work of how pollable async IO is handled, we no longer require
     thread offload to handle that. Instead we rely using poll to drive
     this, with task_work execution.

   - In conjunction with the above, allow expendable buffer selection,
     so that poll+recv (for example) no longer has to be a split
     operation.

   - Make sure we honor RLIMIT_FSIZE for buffered writes

   - Add support for splice (Pavel)

   - Linked work inheritance fixes and optimizations (Pavel)

   - Async work fixes and cleanups (Pavel)

   - Improve io-wq locking (Pavel)

   - Hashed link write improvements (Pavel)

   - SETUP_IOPOLL|SETUP_SQPOLL improvements (Xiaoguang)"

* tag 'for-5.7/io_uring-2020-03-29' of git://git.kernel.dk/linux-block: (54 commits)
  io_uring: cleanup io_alloc_async_ctx()
  io_uring: fix missing 'return' in comment
  io-wq: handle hashed writes in chains
  io-uring: drop 'free_pfile' in struct io_file_put
  io-uring: drop completion when removing file
  io_uring: Fix ->data corruption on re-enqueue
  io-wq: close cancel gap for hashed linked work
  io_uring: make spdxcheck.py happy
  io_uring: honor original task RLIMIT_FSIZE
  io-wq: hash dependent work
  io-wq: split hashing and enqueueing
  io-wq: don't resched if there is no work
  io-wq: remove duplicated cancel code
  io_uring: fix truncated async read/readv and write/writev retry
  io_uring: dual license io_uring.h uapi header
  io_uring: io_uring_enter(2) don't poll while SETUP_IOPOLL|SETUP_SQPOLL enabled
  io_uring: Fix unused function warnings
  io_uring: add end-of-bits marker and build time verify it
  io_uring: provide means of removing buffers
  io_uring: add IOSQE_BUFFER_SELECT support for IORING_OP_RECVMSG
  ...

1 files changed, 1406 insertions, 609 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3affd96a98ba..358f97be9c7b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -44,6 +44,7 @@
 #include <linux/errno.h>
 #include <linux/syscalls.h>
 #include <linux/compat.h>
+#include <net/compat.h>
 #include <linux/refcount.h>
 #include <linux/uio.h>
 #include <linux/bits.h>
@@ -76,6 +77,8 @@
 #include <linux/fadvise.h>
 #include <linux/eventpoll.h>
 #include <linux/fs_struct.h>
+#include <linux/splice.h>
+#include <linux/task_work.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -193,6 +196,13 @@ struct fixed_file_data {
 	struct completion		done;
 };
 
+struct io_buffer {
+	struct list_head list;
+	__u64 addr;
+	__s32 len;
+	__u16 bid;
+};
+
 struct io_ring_ctx {
 	struct {
 		struct percpu_ref	refs;
@@ -270,6 +280,8 @@ struct io_ring_ctx {
 	struct socket		*ring_sock;
 #endif
 
+	struct idr		io_buffer_idr;
+
 	struct idr		personality_idr;
 
 	struct {
@@ -290,7 +302,6 @@ struct io_ring_ctx {
 
 	struct {
 		spinlock_t		completion_lock;
-		struct llist_head	poll_llist;
 
 		/*
 		 * ->poll_list is protected by the ctx->uring_lock for
@@ -386,7 +397,9 @@ struct io_sr_msg {
 		void __user		*buf;
 	};
 	int				msg_flags;
+	int				bgid;
 	size_t				len;
+	struct io_buffer		*kbuf;
 };
 
 struct io_open {
@@ -430,6 +443,24 @@ struct io_epoll {
 	struct epoll_event		event;
 };
 
+struct io_splice {
+	struct file			*file_out;
+	struct file			*file_in;
+	loff_t				off_out;
+	loff_t				off_in;
+	u64				len;
+	unsigned int			flags;
+};
+
+struct io_provide_buf {
+	struct file			*file;
+	__u64				addr;
+	__s32				len;
+	__u32				bgid;
+	__u16				nbufs;
+	__u16				bid;
+};
+
 struct io_async_connect {
 	struct sockaddr_storage		address;
 };
@@ -464,6 +495,7 @@ enum {
 	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_BUFFER_SELECT_BIT	= IOSQE_BUFFER_SELECT_BIT,
 
 	REQ_F_LINK_NEXT_BIT,
 	REQ_F_FAIL_LINK_BIT,
@@ -479,6 +511,11 @@ enum {
 	REQ_F_COMP_LOCKED_BIT,
 	REQ_F_NEED_CLEANUP_BIT,
 	REQ_F_OVERFLOW_BIT,
+	REQ_F_POLLED_BIT,
+	REQ_F_BUFFER_SELECTED_BIT,
+
+	/* not a real bit, just to check we're not overflowing the space */
+	__REQ_F_LAST_BIT,
 };
 
 enum {
@@ -492,6 +529,8 @@ enum {
 	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
 	/* IOSQE_ASYNC */
 	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+	/* IOSQE_BUFFER_SELECT */
+	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
 
 	/* already grabbed next link */
 	REQ_F_LINK_NEXT		= BIT(REQ_F_LINK_NEXT_BIT),
@@ -521,6 +560,15 @@ enum {
 	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
 	/* in overflow list */
 	REQ_F_OVERFLOW		= BIT(REQ_F_OVERFLOW_BIT),
+	/* already went through poll handler */
+	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
+	/* buffer already selected */
+	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+};
+
+struct async_poll {
+	struct io_poll_iocb	poll;
+	struct io_wq_work	work;
 };
 
 /*
@@ -546,32 +594,45 @@ struct io_kiocb {
 		struct io_fadvise	fadvise;
 		struct io_madvise	madvise;
 		struct io_epoll		epoll;
+		struct io_splice	splice;
+		struct io_provide_buf	pbuf;
 	};
 
 	struct io_async_ctx		*io;
-	/*
-	 * llist_node is only used for poll deferred completions
-	 */
-	struct llist_node		llist_node;
-	bool				in_async;
 	bool				needs_fixed_file;
 	u8				opcode;
 
 	struct io_ring_ctx	*ctx;
-	union {
-		struct list_head	list;
-		struct hlist_node	hash_node;
-	};
-	struct list_head	link_list;
+	struct list_head	list;
 	unsigned int		flags;
 	refcount_t		refs;
+	union {
+		struct task_struct	*task;
+		unsigned long		fsize;
+	};
 	u64			user_data;
 	u32			result;
 	u32			sequence;
 
+	struct list_head	link_list;
+
 	struct list_head	inflight_entry;
 
-	struct io_wq_work	work;
+	union {
+		/*
+		 * Only commands that never go async can use the below fields,
+		 * obviously. Right now only IORING_OP_POLL_ADD uses them, and
+		 * async armed poll handlers for regular commands. The latter
+		 * restore the work, if needed.
+		 */
+		struct {
+			struct callback_head	task_work;
+			struct hlist_node	hash_node;
+			struct async_poll	*apoll;
+			int			cflags;
+		};
+		struct io_wq_work	work;
+	};
 };
 
 #define IO_PLUG_THRESHOLD		2
@@ -615,6 +676,11 @@ struct io_op_def {
 	unsigned		file_table : 1;
 	/* needs ->fs */
 	unsigned		needs_fs : 1;
+	/* set if opcode supports polled "wait" */
+	unsigned		pollin : 1;
+	unsigned		pollout : 1;
+	/* op supports buffer selection */
+	unsigned		buffer_select : 1;
 };
 
 static const struct io_op_def io_op_defs[] = {
@@ -624,6 +690,8 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
 	},
 	[IORING_OP_WRITEV] = {
 		.async_ctx		= 1,
@@ -631,6 +699,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.hash_reg_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_FSYNC] = {
 		.needs_file		= 1,
@@ -638,11 +707,13 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_READ_FIXED] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
 	},
 	[IORING_OP_WRITE_FIXED] = {
 		.needs_file		= 1,
 		.hash_reg_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_POLL_ADD] = {
 		.needs_file		= 1,
@@ -658,6 +729,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.needs_fs		= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_RECVMSG] = {
 		.async_ctx		= 1,
@@ -665,6 +737,8 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.needs_fs		= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
 	},
 	[IORING_OP_TIMEOUT] = {
 		.async_ctx		= 1,
@@ -676,6 +750,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.file_table		= 1,
+		.pollin			= 1,
 	},
 	[IORING_OP_ASYNC_CANCEL] = {},
 	[IORING_OP_LINK_TIMEOUT] = {
@@ -687,6 +762,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_FALLOCATE] = {
 		.needs_file		= 1,
@@ -715,11 +791,14 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
 	},
 	[IORING_OP_WRITE] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_FADVISE] = {
 		.needs_file		= 1,
@@ -731,11 +810,14 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
 	},
 	[IORING_OP_RECV] = {
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
 	},
 	[IORING_OP_OPENAT2] = {
 		.needs_file		= 1,
@@ -747,6 +829,13 @@ static const struct io_op_def io_op_defs[] = {
 		.unbound_nonreg_file	= 1,
 		.file_table		= 1,
 	},
+	[IORING_OP_SPLICE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_PROVIDE_BUFFERS] = {},
+	[IORING_OP_REMOVE_BUFFERS] = {},
 };
 
 static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -761,6 +850,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 static int io_grab_files(struct io_kiocb *req);
 static void io_ring_file_ref_flush(struct fixed_file_data *data);
 static void io_cleanup_req(struct io_kiocb *req);
+static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
+		       int fd, struct file **out_file, bool fixed);
+static void __io_queue_sqe(struct io_kiocb *req,
+			   const struct io_uring_sqe *sqe);
 
 static struct kmem_cache *req_cachep;
 
@@ -827,11 +920,11 @@ 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->io_buffer_idr);
 	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);
@@ -952,15 +1045,14 @@ static inline void io_req_work_drop_env(struct io_kiocb *req)
 	}
 }
 
-static inline bool io_prep_async_work(struct io_kiocb *req,
+static inline void 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;
 
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file)
-			do_hashed = true;
+			io_wq_hash_work(&req->work, file_inode(req->file));
 	} else {
 		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
@@ -969,25 +1061,18 @@ static inline bool io_prep_async_work(struct io_kiocb *req,
 	io_req_work_grab_env(req, def);
 
 	*link = io_prep_linked_timeout(req);
-	return do_hashed;
 }
 
 static inline void io_queue_async_work(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *link;
-	bool do_hashed;
 
-	do_hashed = io_prep_async_work(req, &link);
+	io_prep_async_work(req, &link);
 
-	trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work,
-					req->flags);
-	if (!do_hashed) {
-		io_wq_enqueue(ctx->io_wq, &req->work);
-	} else {
-		io_wq_enqueue_hashed(ctx->io_wq, &req->work,
-					file_inode(req->file));
-	}
+	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+					&req->work, req->flags);
+	io_wq_enqueue(ctx->io_wq, &req->work);
 
 	if (link)
 		io_queue_linked_timeout(link);
@@ -1054,24 +1139,19 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
 		return false;
 	if (!ctx->eventfd_async)
 		return true;
-	return io_wq_current_is_worker() || in_interrupt();
+	return io_wq_current_is_worker();
 }
 
-static void __io_cqring_ev_posted(struct io_ring_ctx *ctx, bool trigger_ev)
+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 (trigger_ev)
+	if (io_should_trigger_evfd(ctx))
 		eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
-static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
-{
-	__io_cqring_ev_posted(ctx, io_should_trigger_evfd(ctx));
-}
-
 /* Returns true if there are no backlogged entries after the flush */
 static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 {
@@ -1108,7 +1188,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 		if (cqe) {
 			WRITE_ONCE(cqe->user_data, req->user_data);
 			WRITE_ONCE(cqe->res, req->result);
-			WRITE_ONCE(cqe->flags, 0);
+			WRITE_ONCE(cqe->flags, req->cflags);
 		} else {
 			WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1132,7 +1212,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	return cqe != NULL;
 }
 
-static void io_cqring_fill_event(struct io_kiocb *req, long res)
+static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_uring_cqe *cqe;
@@ -1148,7 +1228,7 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
 	if (likely(cqe)) {
 		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
-		WRITE_ONCE(cqe->flags, 0);
+		WRITE_ONCE(cqe->flags, cflags);
 	} else if (ctx->cq_overflow_flushed) {
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
@@ -1160,23 +1240,34 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
 		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
 		req->result = res;
+		req->cflags = cflags;
 		list_add_tail(&req->list, &ctx->cq_overflow_list);
 	}
 }
 
-static void io_cqring_add_event(struct io_kiocb *req, long res)
+static void io_cqring_fill_event(struct io_kiocb *req, long res)
+{
+	__io_cqring_fill_event(req, res, 0);
+}
+
+static void __io_cqring_add_event(struct io_kiocb *req, long res, long cflags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
-	io_cqring_fill_event(req, res);
+	__io_cqring_fill_event(req, res, cflags);
 	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	io_cqring_ev_posted(ctx);
 }
 
+static void io_cqring_add_event(struct io_kiocb *req, long res)
+{
+	__io_cqring_add_event(req, res, 0);
+}
+
 static inline bool io_is_fallback_req(struct io_kiocb *req)
 {
 	return req == (struct io_kiocb *)
@@ -1246,6 +1337,15 @@ fallback:
 	return NULL;
 }
 
+static inline void io_put_file(struct io_kiocb *req, struct file *file,
+			  bool fixed)
+{
+	if (fixed)
+		percpu_ref_put(&req->ctx->file_data->refs);
+	else
+		fput(file);
+}
+
 static void __io_req_do_free(struct io_kiocb *req)
 {
 	if (likely(!io_is_fallback_req(req)))
@@ -1256,18 +1356,12 @@ static void __io_req_do_free(struct io_kiocb *req)
 
 static void __io_req_aux_free(struct io_kiocb *req)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		io_cleanup_req(req);
 
 	kfree(req->io);
-	if (req->file) {
-		if (req->flags & REQ_F_FIXED_FILE)
-			percpu_ref_put(&ctx->file_data->refs);
-		else
-			fput(req->file);
-	}
+	if (req->file)
+		io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
 
 	io_req_work_drop_env(req);
 }
@@ -1474,6 +1568,30 @@ static void io_free_req(struct io_kiocb *req)
 		io_queue_async_work(nxt);
 }
 
+static void io_link_work_cb(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct io_kiocb *link;
+
+	link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
+	io_queue_linked_timeout(link);
+	io_wq_submit_work(workptr);
+}
+
+static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
+{
+	struct io_kiocb *link;
+	const struct io_op_def *def = &io_op_defs[nxt->opcode];
+
+	if ((nxt->flags & REQ_F_ISREG) && def->hash_reg_file)
+		io_wq_hash_work(&nxt->work, file_inode(nxt->file));
+
+	*workptr = &nxt->work;
+	link = io_prep_linked_timeout(nxt);
+	if (link)
+		nxt->work.func = io_link_work_cb;
+}
+
 /*
  * Drop reference to request, return next in chain (if there is one) if this
  * was the last reference to this request.
@@ -1493,6 +1611,26 @@ static void io_put_req(struct io_kiocb *req)
 		io_free_req(req);
 }
 
+static void io_steal_work(struct io_kiocb *req,
+			  struct io_wq_work **workptr)
+{
+	/*
+	 * It's in an io-wq worker, so there always should be at least
+	 * one reference, which will be dropped in io_put_work() just
+	 * after the current handler returns.
+	 *
+	 * It also means, that if the counter dropped to 1, then there is
+	 * no asynchronous users left, so it's safe to steal the next work.
+	 */
+	if (refcount_read(&req->refs) == 1) {
+		struct io_kiocb *nxt = NULL;
+
+		io_req_find_next(req, &nxt);
+		if (nxt)
+			io_wq_assign_next(workptr, nxt);
+	}
+}
+
 /*
  * Must only be used if we don't need to care about links, usually from
  * within the completion handling itself.
@@ -1554,6 +1692,19 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
 	return true;
 }
 
+static int io_put_kbuf(struct io_kiocb *req)
+{
+	struct io_buffer *kbuf;
+	int cflags;
+
+	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
+	cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
+	cflags |= IORING_CQE_F_BUFFER;
+	req->rw.addr = 0;
+	kfree(kbuf);
+	return cflags;
+}
+
 /*
  * Find and free completed poll iocbs
  */
@@ -1565,10 +1716,15 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 
 	rb.to_free = rb.need_iter = 0;
 	while (!list_empty(done)) {
+		int cflags = 0;
+
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
 
-		io_cqring_fill_event(req, req->result);
+		if (req->flags & REQ_F_BUFFER_SELECTED)
+			cflags = io_put_kbuf(req);
+
+		__io_cqring_fill_event(req, req->result, cflags);
 		(*nr_events)++;
 
 		if (refcount_dec_and_test(&req->refs) &&
@@ -1577,6 +1733,8 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 	}
 
 	io_commit_cqring(ctx);
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		io_cqring_ev_posted(ctx);
 	io_free_req_many(ctx, &rb);
 }
 
@@ -1743,13 +1901,16 @@ static inline void req_set_fail_links(struct io_kiocb *req)
 static void io_complete_rw_common(struct kiocb *kiocb, long res)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
+	int cflags = 0;
 
 	if (kiocb->ki_flags & IOCB_WRITE)
 		kiocb_end_write(req);
 
 	if (res != req->result)
 		req_set_fail_links(req);
-	io_cqring_add_event(req, res);
+	if (req->flags & REQ_F_BUFFER_SELECTED)
+		cflags = io_put_kbuf(req);
+	__io_cqring_add_event(req, res, cflags);
 }
 
 static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
@@ -1760,17 +1921,6 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 	io_put_req(req);
 }
 
-static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res)
-{
-	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
-	struct io_kiocb *nxt = NULL;
-
-	io_complete_rw_common(kiocb, res);
-	io_put_req_find_next(req, &nxt);
-
-	return nxt;
-}
-
 static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
@@ -1841,7 +1991,7 @@ static void io_file_put(struct io_submit_state *state)
  * assuming most submissions are for one file, or at least that each file
  * has more than one submission.
  */
-static struct file *io_file_get(struct io_submit_state *state, int fd)
+static struct file *__io_file_get(struct io_submit_state *state, int fd)
 {
 	if (!state)
 		return fget(fd);
@@ -1938,7 +2088,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);
-	/* we own ->private, reuse it for the buffer index */
+	/* we own ->private, reuse it for the buffer index  / buffer ID */
 	req->rw.kiocb.private = (void *) (unsigned long)
 					READ_ONCE(sqe->buf_index);
 	return 0;
@@ -1965,15 +2115,14 @@ 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)
+static void kiocb_done(struct kiocb *kiocb, ssize_t ret)
 {
 	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);
+	if (ret >= 0 && kiocb->ki_complete == io_complete_rw)
+		io_complete_rw(kiocb, ret, 0);
 	else
 		io_rw_done(kiocb, ret);
 }
@@ -2052,11 +2201,147 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	return len;
 }
 
+static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
+{
+	if (needs_lock)
+		mutex_unlock(&ctx->uring_lock);
+}
+
+static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
+{
+	/*
+	 * "Normal" inline submissions always hold the uring_lock, since we
+	 * grab it from the system call. Same is true for the SQPOLL offload.
+	 * The only exception is when we've detached the request and issue it
+	 * from an async worker thread, grab the lock for that case.
+	 */
+	if (needs_lock)
+		mutex_lock(&ctx->uring_lock);
+}
+
+static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
+					  int bgid, struct io_buffer *kbuf,
+					  bool needs_lock)
+{
+	struct io_buffer *head;
+
+	if (req->flags & REQ_F_BUFFER_SELECTED)
+		return kbuf;
+
+	io_ring_submit_lock(req->ctx, needs_lock);
+
+	lockdep_assert_held(&req->ctx->uring_lock);
+
+	head = idr_find(&req->ctx->io_buffer_idr, bgid);
+	if (head) {
+		if (!list_empty(&head->list)) {
+			kbuf = list_last_entry(&head->list, struct io_buffer,
+							list);
+			list_del(&kbuf->list);
+		} else {
+			kbuf = head;
+			idr_remove(&req->ctx->io_buffer_idr, bgid);
+		}
+		if (*len > kbuf->len)
+			*len = kbuf->len;
+	} else {
+		kbuf = ERR_PTR(-ENOBUFS);
+	}
+
+	io_ring_submit_unlock(req->ctx, needs_lock);
+
+	return kbuf;
+}
+
+static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
+					bool needs_lock)
+{
+	struct io_buffer *kbuf;
+	int bgid;
+
+	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
+	bgid = (int) (unsigned long) req->rw.kiocb.private;
+	kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
+	if (IS_ERR(kbuf))
+		return kbuf;
+	req->rw.addr = (u64) (unsigned long) kbuf;
+	req->flags |= REQ_F_BUFFER_SELECTED;
+	return u64_to_user_ptr(kbuf->addr);
+}
+
+#ifdef CONFIG_COMPAT
+static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
+				bool needs_lock)
+{
+	struct compat_iovec __user *uiov;
+	compat_ssize_t clen;
+	void __user *buf;
+	ssize_t len;
+
+	uiov = u64_to_user_ptr(req->rw.addr);
+	if (!access_ok(uiov, sizeof(*uiov)))
+		return -EFAULT;
+	if (__get_user(clen, &uiov->iov_len))
+		return -EFAULT;
+	if (clen < 0)
+		return -EINVAL;
+
+	len = clen;
+	buf = io_rw_buffer_select(req, &len, needs_lock);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+	iov[0].iov_base = buf;
+	iov[0].iov_len = (compat_size_t) len;
+	return 0;
+}
+#endif
+
+static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+				      bool needs_lock)
+{
+	struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
+	void __user *buf;
+	ssize_t len;
+
+	if (copy_from_user(iov, uiov, sizeof(*uiov)))
+		return -EFAULT;
+
+	len = iov[0].iov_len;
+	if (len < 0)
+		return -EINVAL;
+	buf = io_rw_buffer_select(req, &len, needs_lock);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+	iov[0].iov_base = buf;
+	iov[0].iov_len = len;
+	return 0;
+}
+
+static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+				    bool needs_lock)
+{
+	if (req->flags & REQ_F_BUFFER_SELECTED)
+		return 0;
+	if (!req->rw.len)
+		return 0;
+	else if (req->rw.len > 1)
+		return -EINVAL;
+
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		return io_compat_import(req, iov, needs_lock);
+#endif
+
+	return __io_iov_buffer_select(req, iov, needs_lock);
+}
+
 static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
-			       struct iovec **iovec, struct iov_iter *iter)
+			       struct iovec **iovec, struct iov_iter *iter,
+			       bool needs_lock)
 {
 	void __user *buf = u64_to_user_ptr(req->rw.addr);
 	size_t sqe_len = req->rw.len;
+	ssize_t ret;
 	u8 opcode;
 
 	opcode = req->opcode;
@@ -2065,12 +2350,20 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 		return io_import_fixed(req, rw, iter);
 	}
 
-	/* buffer index only valid with fixed read/write */
-	if (req->rw.kiocb.private)
+	/* buffer index only valid with fixed read/write, or buffer select  */
+	if (req->rw.kiocb.private && !(req->flags & REQ_F_BUFFER_SELECT))
 		return -EINVAL;
 
 	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
-		ssize_t ret;
+		if (req->flags & REQ_F_BUFFER_SELECT) {
+			buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
+			if (IS_ERR(buf)) {
+				*iovec = NULL;
+				return PTR_ERR(buf);
+			}
+			req->rw.len = sqe_len;
+		}
+
 		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
 		*iovec = NULL;
 		return ret < 0 ? ret : sqe_len;
@@ -2086,6 +2379,16 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 		return iorw->size;
 	}
 
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		ret = io_iov_buffer_select(req, *iovec, needs_lock);
+		if (!ret) {
+			ret = (*iovec)->iov_len;
+			iov_iter_init(iter, rw, *iovec, 1, ret);
+		}
+		*iovec = NULL;
+		return ret;
+	}
+
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
@@ -2169,12 +2472,18 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
 	}
 }
 
+static inline int __io_alloc_async_ctx(struct io_kiocb *req)
+{
+	req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
+	return req->io == NULL;
+}
+
 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;
+
+	return  __io_alloc_async_ctx(req);
 }
 
 static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
@@ -2184,7 +2493,7 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
 	if (!io_op_defs[req->opcode].async_ctx)
 		return 0;
 	if (!req->io) {
-		if (io_alloc_async_ctx(req))
+		if (__io_alloc_async_ctx(req))
 			return -ENOMEM;
 
 		io_req_map_rw(req, io_size, iovec, fast_iov, iter);
@@ -2213,7 +2522,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	io = req->io;
 	io->rw.iov = io->rw.fast_iov;
 	req->io = NULL;
-	ret = io_import_iovec(READ, req, &io->rw.iov, &iter);
+	ret = io_import_iovec(READ, req, &io->rw.iov, &iter, !force_nonblock);
 	req->io = io;
 	if (ret < 0)
 		return ret;
@@ -2222,8 +2531,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
-static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
-		   bool force_nonblock)
+static int io_read(struct io_kiocb *req, bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw.kiocb;
@@ -2231,13 +2539,13 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
 	size_t iov_count;
 	ssize_t io_size, ret;
 
-	ret = io_import_iovec(READ, req, &iovec, &iter);
+	ret = io_import_iovec(READ, req, &iovec, &iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
 
 	/* Ensure we clear previously set non-block flag */
 	if (!force_nonblock)
-		req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT;
+		kiocb->ki_flags &= ~IOCB_NOWAIT;
 
 	req->result = 0;
 	io_size = ret;
@@ -2248,10 +2556,8 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file)) {
-		req->flags |= REQ_F_MUST_PUNT;
+	if (force_nonblock && !io_file_supports_async(req->file))
 		goto copy_iov;
-	}
 
 	iov_count = iov_iter_count(&iter);
 	ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count);
@@ -2265,13 +2571,16 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
 
 		/* Catch -EAGAIN return for forced non-blocking submission */
 		if (!force_nonblock || ret2 != -EAGAIN) {
-			kiocb_done(kiocb, ret2, nxt, req->in_async);
+			kiocb_done(kiocb, ret2);
 		} else {
 copy_iov:
 			ret = io_setup_async_rw(req, io_size, iovec,
 						inline_vecs, &iter);
 			if (ret)
 				goto out_free;
+			/* any defer here is final, must blocking retry */
+			if (!(req->flags & REQ_F_NOWAIT))
+				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
 	}
@@ -2295,6 +2604,8 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
+	req->fsize = rlimit(RLIMIT_FSIZE);
+
 	/* either don't need iovec imported or already have it */
 	if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
@@ -2302,7 +2613,7 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	io = req->io;
 	io->rw.iov = io->rw.fast_iov;
 	req->io = NULL;
-	ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter);
+	ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter, !force_nonblock);
 	req->io = io;
 	if (ret < 0)
 		return ret;
@@ -2311,8 +2622,7 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
-static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
-		    bool force_nonblock)
+static int io_write(struct io_kiocb *req, bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw.kiocb;
@@ -2320,7 +2630,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
 	size_t iov_count;
 	ssize_t ret, io_size;
 
-	ret = io_import_iovec(WRITE, req, &iovec, &iter);
+	ret = io_import_iovec(WRITE, req, &iovec, &iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
 
@@ -2337,10 +2647,8 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file)) {
-		req->flags |= REQ_F_MUST_PUNT;
+	if (force_nonblock && !io_file_supports_async(req->file))
 		goto copy_iov;
-	}
 
 	/* file path doesn't support NOWAIT for non-direct_IO */
 	if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
@@ -2367,24 +2675,33 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
 		}
 		kiocb->ki_flags |= IOCB_WRITE;
 
+		if (!force_nonblock)
+			current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
+
 		if (req->file->f_op->write_iter)
 			ret2 = call_write_iter(req->file, kiocb, &iter);
 		else
 			ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter);
+
+		if (!force_nonblock)
+			current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
+
 		/*
-		 * Raw bdev writes will -EOPNOTSUPP for IOCB_NOWAIT. Just
+		 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
 		 * retry them without IOCB_NOWAIT.
 		 */
 		if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
 			ret2 = -EAGAIN;
 		if (!force_nonblock || ret2 != -EAGAIN) {
-			kiocb_done(kiocb, ret2, nxt, req->in_async);
+			kiocb_done(kiocb, ret2);
 		} else {
 copy_iov:
 			ret = io_setup_async_rw(req, io_size, iovec,
 						inline_vecs, &iter);
 			if (ret)
 				goto out_free;
+			/* any defer here is final, must blocking retry */
+			req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
 	}
@@ -2394,6 +2711,76 @@ out_free:
 	return ret;
 }
 
+static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_splice* sp = &req->splice;
+	unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
+	int ret;
+
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
+
+	sp->file_in = NULL;
+	sp->off_in = READ_ONCE(sqe->splice_off_in);
+	sp->off_out = READ_ONCE(sqe->off);
+	sp->len = READ_ONCE(sqe->len);
+	sp->flags = READ_ONCE(sqe->splice_flags);
+
+	if (unlikely(sp->flags & ~valid_flags))
+		return -EINVAL;
+
+	ret = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in), &sp->file_in,
+			  (sp->flags & SPLICE_F_FD_IN_FIXED));
+	if (ret)
+		return ret;
+	req->flags |= REQ_F_NEED_CLEANUP;
+
+	if (!S_ISREG(file_inode(sp->file_in)->i_mode))
+		req->work.flags |= IO_WQ_WORK_UNBOUND;
+
+	return 0;
+}
+
+static bool io_splice_punt(struct file *file)
+{
+	if (get_pipe_info(file))
+		return false;
+	if (!io_file_supports_async(file))