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
  ...

12 files changed, 1826 insertions, 856 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5cef075c0b37..cc5cf2209fb0 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -69,6 +69,8 @@ struct io_worker {
 #define IO_WQ_HASH_ORDER	5
 #endif
 
+#define IO_WQ_NR_HASH_BUCKETS	(1u << IO_WQ_HASH_ORDER)
+
 struct io_wqe_acct {
 	unsigned nr_workers;
 	unsigned max_workers;
@@ -98,6 +100,7 @@ struct io_wqe {
 	struct list_head all_list;
 
 	struct io_wq *wq;
+	struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS];
 };
 
 /*
@@ -107,8 +110,7 @@ struct io_wq {
 	struct io_wqe **wqes;
 	unsigned long state;
 
-	get_work_fn *get_work;
-	put_work_fn *put_work;
+	free_work_fn *free_work;
 
 	struct task_struct *manager;
 	struct user_struct *user;
@@ -376,26 +378,35 @@ static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker)
 	return __io_worker_unuse(wqe, worker);
 }
 
-static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
+static inline unsigned int io_get_work_hash(struct io_wq_work *work)
+{
+	return work->flags >> IO_WQ_HASH_SHIFT;
+}
+
+static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
 	__must_hold(wqe->lock)
 {
 	struct io_wq_work_node *node, *prev;
-	struct io_wq_work *work;
+	struct io_wq_work *work, *tail;
+	unsigned int hash;
 
 	wq_list_for_each(node, prev, &wqe->work_list) {
 		work = container_of(node, struct io_wq_work, list);
 
 		/* not hashed, can run anytime */
-		if (!(work->flags & IO_WQ_WORK_HASHED)) {
-			wq_node_del(&wqe->work_list, node, prev);
+		if (!io_wq_is_hashed(work)) {
+			wq_list_del(&wqe->work_list, node, prev);
 			return work;
 		}
 
 		/* hashed, can run if not already running */
-		*hash = work->flags >> IO_WQ_HASH_SHIFT;
-		if (!(wqe->hash_map & BIT_ULL(*hash))) {
-			wqe->hash_map |= BIT_ULL(*hash);
-			wq_node_del(&wqe->work_list, node, prev);
+		hash = io_get_work_hash(work);
+		if (!(wqe->hash_map & BIT(hash))) {
+			wqe->hash_map |= BIT(hash);
+			/* all items with this hash lie in [work, tail] */
+			tail = wqe->hash_tail[hash];
+			wqe->hash_tail[hash] = NULL;
+			wq_list_cut(&wqe->work_list, &tail->list, prev);
 			return work;
 		}
 	}
@@ -440,16 +451,49 @@ static void io_wq_switch_creds(struct io_worker *worker,
 		worker->saved_creds = old_creds;
 }
 
+static void io_impersonate_work(struct io_worker *worker,
+				struct io_wq_work *work)
+{
+	if (work->files && current->files != work->files) {
+		task_lock(current);
+		current->files = work->files;
+		task_unlock(current);
+	}
+	if (work->fs && current->fs != work->fs)
+		current->fs = work->fs;
+	if (work->mm != worker->mm)
+		io_wq_switch_mm(worker, work);
+	if (worker->cur_creds != work->creds)
+		io_wq_switch_creds(worker, work);
+}
+
+static void io_assign_current_work(struct io_worker *worker,
+				   struct io_wq_work *work)
+{
+	if (work) {
+		/* flush pending signals before assigning new work */
+		if (signal_pending(current))
+			flush_signals(current);
+		cond_resched();
+	}
+
+	spin_lock_irq(&worker->lock);
+	worker->cur_work = work;
+	spin_unlock_irq(&worker->lock);
+}
+
+static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
+
 static void io_worker_handle_work(struct io_worker *worker)
 	__releases(wqe->lock)
 {
-	struct io_wq_work *work, *old_work = NULL, *put_work = NULL;
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
 
 	do {
-		unsigned hash = -1U;
-
+		struct io_wq_work *work;
+		unsigned int hash;
+get_next:
 		/*
 		 * If we got some work, mark us as busy. If we didn't, but
 		 * the list isn't empty, it means we stalled on hashed work.
@@ -457,81 +501,60 @@ static void io_worker_handle_work(struct io_worker *worker)
 		 * can't make progress, any work completion or insertion will
 		 * clear the stalled flag.
 		 */
-		work = io_get_next_work(wqe, &hash);
+		work = io_get_next_work(wqe);
 		if (work)
 			__io_worker_busy(wqe, worker, work);
 		else if (!wq_list_empty(&wqe->work_list))
 			wqe->flags |= IO_WQE_FLAG_STALLED;
 
 		spin_unlock_irq(&wqe->lock);
-		if (put_work && wq->put_work)
-			wq->put_work(old_work);
 		if (!work)
 			break;
-next:
-		/* flush any pending signals before assigning new work */
-		if (signal_pending(current))
-			flush_signals(current);
-
-		cond_resched();
-
-		spin_lock_irq(&worker->lock);
-		worker->cur_work = work;
-		spin_unlock_irq(&worker->lock);
-
-		if (work->flags & IO_WQ_WORK_CB)
-			work->func(&work);
-
-		if (work->files && current->files != work->files) {
-			task_lock(current);
-			current->files = work->files;
-			task_unlock(current);
-		}
-		if (work->fs && current->fs != work->fs)
-			current->fs = work->fs;
-		if (work->mm != worker->mm)
-			io_wq_switch_mm(worker, work);
-		if (worker->cur_creds != work->creds)
-			io_wq_switch_creds(worker, work);
-		/*
-		 * OK to set IO_WQ_WORK_CANCEL even for uncancellable work,
-		 * the worker function will do the right thing.
-		 */
-		if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
-			work->flags |= IO_WQ_WORK_CANCEL;
-		if (worker->mm)
-			work->flags |= IO_WQ_WORK_HAS_MM;
-
-		if (wq->get_work) {
-			put_work = work;
-			wq->get_work(work);
-		}
-
-		old_work = work;
-		work->func(&work);
-
-		spin_lock_irq(&worker->lock);
-		worker->cur_work = NULL;
-		spin_unlock_irq(&worker->lock);
-
-		spin_lock_irq(&wqe->lock);
-
-		if (hash != -1U) {
-			wqe->hash_map &= ~BIT_ULL(hash);
-			wqe->flags &= ~IO_WQE_FLAG_STALLED;
-		}
-		if (work && work != old_work) {
-			spin_unlock_irq(&wqe->lock);
-
-			if (put_work && wq->put_work) {
-				wq->put_work(put_work);
-				put_work = NULL;
+		io_assign_current_work(worker, work);
+
+		/* handle a whole dependent link */
+		do {
+			struct io_wq_work *old_work, *next_hashed, *linked;
+
+			next_hashed = wq_next_work(work);
+			io_impersonate_work(worker, work);
+			/*
+			 * OK to set IO_WQ_WORK_CANCEL even for uncancellable
+			 * work, the worker function will do the right thing.
+			 */
+			if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
+				work->flags |= IO_WQ_WORK_CANCEL;
+
+			hash = io_get_work_hash(work);
+			linked = old_work = work;
+			linked->func(&linked);
+			linked = (old_work == linked) ? NULL : linked;
+
+			work = next_hashed;
+			if (!work && linked && !io_wq_is_hashed(linked)) {
+				work = linked;
+				linked = NULL;
 			}
+			io_assign_current_work(worker, work);
+			wq->free_work(old_work);
+
+			if (linked)
+				io_wqe_enqueue(wqe, linked);
+
+			if (hash != -1U && !next_hashed) {
+				spin_lock_irq(&wqe->lock);
+				wqe->hash_map &= ~BIT_ULL(hash);
+				wqe->flags &= ~IO_WQE_FLAG_STALLED;
+				/* dependent work is not hashed */
+				hash = -1U;
+				/* skip unnecessary unlock-lock wqe->lock */
+				if (!work)
+					goto get_next;
+				spin_unlock_irq(&wqe->lock);
+			}
+		} while (work);
 
-			/* dependent work not hashed */
-			hash = -1U;
-			goto next;
-		}
+		spin_lock_irq(&wqe->lock);
 	} while (1);
 }
 
@@ -747,17 +770,40 @@ static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct,
 	return true;
 }
 
-static void io_run_cancel(struct io_wq_work *work)
+static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
 {
+	struct io_wq *wq = wqe->wq;
+
 	do {
 		struct io_wq_work *old_work = work;
 
 		work->flags |= IO_WQ_WORK_CANCEL;
 		work->func(&work);
 		work = (work == old_work) ? NULL : work;
+		wq->free_work(old_work);
 	} while (work);
 }
 
+static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
+{
+	unsigned int hash;
+	struct io_wq_work *tail;
+
+	if (!io_wq_is_hashed(work)) {
+append:
+		wq_list_add_tail(&work->list, &wqe->work_list);
+		return;
+	}
+
+	hash = io_get_work_hash(work);
+	tail = wqe->hash_tail[hash];
+	wqe->hash_tail[hash] = work;
+	if (!tail)
+		goto append;
+
+	wq_list_add_after(&work->list, &tail->list, &wqe->work_list);
+}
+
 static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 {
 	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
@@ -771,13 +817,13 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 	 * It's close enough to not be an issue, fork() has the same delay.
 	 */
 	if (unlikely(!io_wq_can_queue(wqe, acct, work))) {
-		io_run_cancel(work);
+		io_run_cancel(work, wqe);
 		return;
 	}
 
 	work_flags = work->flags;
 	spin_lock_irqsave(&wqe->lock, flags);
-	wq_list_add_tail(&work->list, &wqe->work_list);
+	io_wqe_insert_work(wqe, work);
 	wqe->flags &= ~IO_WQE_FLAG_STALLED;
 	spin_unlock_irqrestore(&wqe->lock, flags);
 
@@ -794,19 +840,15 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
 }
 
 /*
- * Enqueue work, hashed by some key. Work items that hash to the same value
- * will not be done in parallel. Used to limit concurrent writes, generally
- * hashed by inode.
+ * Work items that hash to the same value will not be done in parallel.
+ * Used to limit concurrent writes, generally hashed by inode.
  */
-void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val)
+void io_wq_hash_work(struct io_wq_work *work, void *val)
 {
-	struct io_wqe *wqe = wq->wqes[numa_node_id()];
-	unsigned bit;
-
+	unsigned int bit;
 
 	bit = hash_ptr(val, IO_WQ_HASH_ORDER);
 	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
-	io_wqe_enqueue(wqe, work);
 }
 
 static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
@@ -856,14 +898,13 @@ void io_wq_cancel_all(struct io_wq *wq)
 }
 
 struct io_cb_cancel_data {
-	struct io_wqe *wqe;
-	work_cancel_fn *cancel;
-	void *caller_data;
+	work_cancel_fn *fn;
+	void *data;
 };
 
-static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
+static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 {
-	struct io_cb_cancel_data *data = cancel_data;
+	struct io_cb_cancel_data *match = data;
 	unsigned long flags;
 	bool ret = false;
 
@@ -874,83 +915,7 @@ static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
 	spin_lock_irqsave(&worker->lock, flags);
 	if (worker->cur_work &&
 	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
-	    data->cancel(worker->cur_work, data->caller_data)) {
-		send_sig(SIGINT, worker->task, 1);
-		ret = true;
-	}
-	spin_unlock_irqrestore(&worker->lock, flags);
-
-	return ret;
-}
-
-static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe,
-					       work_cancel_fn *cancel,
-					       void *cancel_data)
-{
-	struct io_cb_cancel_data data = {
-		.wqe = wqe,
-		.cancel = cancel,
-		.caller_data = cancel_data,
-	};
-	struct io_wq_work_node *node, *prev;
-	struct io_wq_work *work;
-	unsigned long flags;
-	bool found = false;
-
-	spin_lock_irqsave(&wqe->lock, flags);
-	wq_list_for_each(node, prev, &wqe->work_list) {
-		work = container_of(node, struct io_wq_work, list);
-
-		if (cancel(work, cancel_data)) {
-			wq_node_del(&wqe->work_list, node, prev);
-			found = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&wqe->lock, flags);
-
-	if (found) {
-		io_run_cancel(work);
-		return IO_WQ_CANCEL_OK;
-	}
-
-	rcu_read_lock();
-	found = io_wq_for_each_worker(wqe, io_work_cancel, &data);
-	rcu_read_unlock();
-	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
-}
-
-enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
-				  void *data)
-{
-	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
-	int node;
-
-	for_each_node(node) {
-		struct io_wqe *wqe = wq->wqes[node];
-
-		ret = io_wqe_cancel_cb_work(wqe, cancel, data);
-		if (ret != IO_WQ_CANCEL_NOTFOUND)
-			break;
-	}
-
-	return ret;
-}
-
-struct work_match {
-	bool (*fn)(struct io_wq_work *, void *data);
-	void *data;
-};
-
-static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
-{
-	struct work_match *match = data;
-	unsigned long flags;
-	bool ret = false;
-
-	spin_lock_irqsave(&worker->lock, flags);
-	if (match->fn(worker->cur_work, match->data) &&
-	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
+	    match->fn(worker->cur_work, match->data)) {
 		send_sig(SIGINT, worker->task, 1);
 		ret = true;
 	}
@@ -960,7 +925,7 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 }
 
 static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
-					    struct work_match *match)
+					    struct io_cb_cancel_data *match)
 {
 	struct io_wq_work_node *node, *prev;
 	struct io_wq_work *work;
@@ -977,7 +942,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
 		work = container_of(node, struct io_wq_work, list);
 
 		if (match->fn(work, match->data)) {
-			wq_node_del(&wqe->work_list, node, prev);
+			wq_list_del(&wqe->work_list, node, prev);
 			found = true;
 			break;
 		}
@@ -985,7 +950,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
 	spin_unlock_irqrestore(&wqe->lock, flags);
 
 	if (found) {
-		io_run_cancel(work);
+		io_run_cancel(work, wqe);
 		return IO_WQ_CANCEL_OK;
 	}
 
@@ -1001,22 +966,16 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
 	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
 }
 
-static bool io_wq_work_match(struct io_wq_work *work, void *data)
-{
-	return work == data;
-}
-
-enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+				  void *data)
 {
-	struct work_match match = {
-		.fn	= io_wq_work_match,
-		.data	= cwork
+	struct io_cb_cancel_data match = {
+		.fn	= cancel,
+		.data	= data,
 	};
 	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
 	int node;
 
-	cwork->flags |= IO_WQ_WORK_CANCEL;
-
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
@@ -1028,33 +987,28 @@ enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
 	return ret;
 }
 
+static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
+{
+	return work == data;
+}
+
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+{
+	return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork);
+}
+
 static bool io_wq_pid_match(struct io_wq_work *work, void *data)
 {
 	pid_t pid = (pid_t) (unsigned long) data;
 
-	if (work)
-		return work->task_pid == pid;
-	return false;
+	return work->task_pid == pid;
 }
 
 enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
 {
-	struct work_match match = {
-		.fn	= io_wq_pid_match,
-		.data	= (void *) (unsigned long) pid
-	};
-	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
-	int node;
-
-	for_each_node(node) {
-		struct io_wqe *wqe = wq->wqes[node];
+	void *data = (void *) (unsigned long) pid;
 
-		ret = io_wqe_cancel_work(wqe, &match);
-		if (ret != IO_WQ_CANCEL_NOTFOUND)
-			break;
-	}
-
-	return ret;
+	return io_wq_cancel_cb(wq, io_wq_pid_match, data);
 }
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
@@ -1062,6 +1016,9 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	int ret = -ENOMEM, node;
 	struct io_wq *wq;
 
+	if (WARN_ON_ONCE(!data->free_work))
+		return ERR_PTR(-EINVAL);
+
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
 	if (!wq)
 		return ERR_PTR(-ENOMEM);
@@ -1072,8 +1029,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	wq->get_work = data->get_work;
-	wq->put_work = data->put_work;
+	wq->free_work = data->free_work;
 
 	/* caller must already hold a reference to this */
 	wq->user = data->user;
@@ -1130,7 +1086,7 @@ err:
 
 bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
 {
-	if (data->get_work != wq->get_work || data->put_work != wq->put_work)
+	if (data->free_work != wq->free_work)
 		return false;
 
 	return refcount_inc_not_zero(&wq->use_refs);
diff --git a/fs/io-wq.h b/fs/io-wq.h
index e5e15f2c93ec..3ee7356d6be5 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -5,10 +5,8 @@ struct io_wq;
 
 enum {
 	IO_WQ_WORK_CANCEL	= 1,
-	IO_WQ_WORK_HAS_MM	= 2,
 	IO_WQ_WORK_HASHED	= 4,
 	IO_WQ_WORK_UNBOUND	= 32,
-	IO_WQ_WORK_CB		= 128,
 	IO_WQ_WORK_NO_CANCEL	= 256,
 	IO_WQ_WORK_CONCURRENT	= 512,
 
@@ -30,6 +28,18 @@ struct io_wq_work_list {
 	struct io_wq_work_node *last;
 };
 
+static inline void wq_list_add_after(struct io_wq_work_node *node,
+				     struct io_wq_work_node *pos,
+				     struct io_wq_work_list *list)
+{
+	struct io_wq_work_node *next = pos->next;
+
+	pos->next = node;
+	node->next = next;
+	if (!next)
+		list->last = node;
+}
+
 static inline void wq_list_add_tail(struct io_wq_work_node *node,
 				    struct io_wq_work_list *list)
 {
@@ -42,17 +52,26 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
 	}
 }
 
-static inline void wq_node_del(struct io_wq_work_list *list,
-			       struct io_wq_work_node *node,
+static inline void wq_list_cut(struct io_wq_work_list *list,
+			       struct io_wq_work_node *last,
 			       struct io_wq_work_node *prev)
 {
-	if (node == list->first)
-		WRITE_ONCE(list->first, node->next);
-	if (node == list->last)
+	/* first in the list, if prev==NULL */
+	if (!prev)
+		WRITE_ONCE(list->first, last->next);
+	else
+		prev->next = last->next;
+
+	if (last == list->last)
 		list->last = prev;
-	if (prev)
-		prev->next = node->next;
-	node->next = NULL;
+	last->next = NULL;
+}
+
+static inline void wq_list_del(struct io_wq_work_list *list,
+			       struct io_wq_work_node *node,
+			       struct io_wq_work_node *prev)
+{
+	wq_list_cut(list, node, prev);
 }
 
 #define wq_list_for_each(pos, prv, head)			\
@@ -65,10 +84,7 @@ static inline void wq_node_del(struct io_wq_work_list *list,
 } while (0)
 
 struct io_wq_work {
-	union {
-		struct io_wq_work_node list;
-		void *data;
-	};
+	struct io_wq_work_node list;
 	void (*func)(struct io_wq_work **);
 	struct files_struct *files;
 	struct mm_struct *mm;
@@ -83,14 +99,20 @@ struct io_wq_work {
 		*(work) = (struct io_wq_work){ .func = _func };	\
 	} while (0)						\
 
-typedef void (get_work_fn)(struct io_wq_work *);
-typedef void (put_work_fn)(struct io_wq_work *);
+static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
+{
+	if (!work->list.next)
+		return NULL;
+
+	return container_of(work->list.next, struct io_wq_work, list);
+}
+
+typedef void (free_work_fn)(struct io_wq_work *);
 
 struct io_wq_data {
 	struct user_struct *user;
 
-	get_work_fn *get_work;
-	put_work_fn *put_work;
+	free_work_fn *free_work;
 };
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
@@ -98,7 +120,12 @@ bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
 void io_wq_destroy(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
-void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_hash_work(struct io_wq_work *work, void *val);
+
+static inline bool io_wq_is_hashed(struct io_wq_work *work)
+{
+	return work->flags & IO_WQ_WORK_HASHED;
+}
 
 void io_wq_cancel_all(struct io_wq *wq);
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
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))
+		return true;
+	return !(file->f_mode & O_NONBLOCK);
+}
+
+static int io_splice(struct io_kiocb *req, bool force_nonblock)
+{
+	struct io_splice *sp = &req->splice;
+	struct file *in = sp->file_in;
+	struct file *out = sp->file_out;
+	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+	loff_t *poff_in, *poff_out;
+	long ret;
+
+	if (force_nonblock) {
+		if (io_splice_punt(in) || io_splice_punt(out))
+			return -EAGAIN;
+		flags |= SPLICE_F_NONBLOCK;
+	}
+
+	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
+	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
+	ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+	if (force_nonblock && ret == -EAGAIN)
+		return -EAGAIN;
+
+	io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+
+	io_cqring_add_event(req, ret);
+	if (ret != sp->len)
+		req_set_fail_links(req);
+	io_put_req(req);
+	return 0;
+}
+
 /*
  * IORING_OP_NOP just posts a completion event, nothing else.
  */
@@ -2442,85 +2829,63 @@ static bool io_req_cancelled(struct io_kiocb *req)
 	return false;
 }
 
-static void io_link_work_cb(struct io_wq_work **workptr)
-{
-	struct io_wq_work *work = *workptr;
-	struct io_kiocb *link = work->data;
-
-	io_queue_linked_timeout(link);
-	work->func = io_wq_submit_work;
-}
-
-static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
+static void __io_fsync(struct io_kiocb *req)
 {
-	struct io_kiocb *link;
-
-	io_prep_async_work(nxt, &link);
-	*workptr = &nxt->work;
-	if (link) {
-		nxt->work.flags |= IO_WQ_WORK_CB;
-		nxt->work.func = io_link_work_cb;
-		nxt->work.data = link;
-	}
-}
-
-static void io_fsync_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
 	loff_t end = req->sync.off + req->sync.len;
-	struct io_kiocb *nxt = NULL;
 	int ret;
 
-	if (io_req_cancelled(req))
-		return;
-
 	ret = vfs_fsync_range(req->file, req->sync.off,
 				end > 0 ? end : LLONG_MAX,
 				req->sync.flags & IORING_FSYNC_DATASYNC);
 	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);
+	io_put_req(req);
 }
 
-static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
-		    bool force_nonblock)
+static void io_fsync_finish(struct io_wq_work **workptr)
 {
-	struct io_wq_work *work, *old_work;
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+
+	if (io_req_cancelled(req))
+		return;
+	__io_fsync(req);
+	io_steal_work(req, workptr);
+}
 
+static int io_fsync(struct io_kiocb *req, bool force_nonblock)
+{
 	/* fsync always requires a blocking context */
 	if (force_nonblock) {
-		io_put_req(req);
 		req->work.func = io_fsync_finish;
 		return -EAGAIN;
 	}
-
-	work = old_work = &req->work;
-	io_fsync_finish(&work);
-	if (work && work != old_work)
-		*nxt = container_of(work, struct io_kiocb, work);
+	__io_fsync(req);
 	return 0;
 }
 
-static void io_fallocate_finish(struct io_wq_work **workptr)
+static void __io_fallocate(struct io_kiocb *req)
 {
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct io_kiocb *nxt = NULL;
 	int ret;
 
-	if (io_req_cancelled(req))
-		return;
-
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
 	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
 				req->sync.len);
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
 	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);
+	io_put_req(req);
+}
+
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+
+	if (io_req_cancelled(req))
+		return;
+	__io_fallocate(req);
+	io_steal_work(req, workptr);
 }
 
 static int io_fallocate_prep(struct io_kiocb *req,
@@ -2532,26 +2897,19 @@ static int io_fallocate_prep(struct io_kiocb *req,
 	req->sync.off = READ_ONCE(sqe->off);
 	req->sync.len = READ_ONCE(sqe->addr);
 	req->sync.mode = READ_ONCE(sqe->len);
+	req->fsize = rlimit(RLIMIT_FSIZE);
 	return 0;
 }
 
-static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt,
-			bool force_nonblock)
+static int io_fallocate(struct io_kiocb *req, 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);
-
+	__io_fallocate(req);
 	return 0;
 }
 
@@ -2626,8 +2984,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_openat2(struct io_kiocb *req, bool force_nonblock)
 {
 	struct open_flags op;
 	struct file *file;
@@ -2658,15 +3015,171 @@ err:
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 }
 
-static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
-		     bool force_nonblock)
+static int io_openat(struct io_kiocb *req, bool force_nonblock)
 {
 	req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
-	return io_openat2(req, nxt, force_nonblock);
+	return io_openat2(req, force_nonblock);
+}
+
+static int io_remove_buffers_prep(struct io_kiocb *req,
+				  const struct io_uring_sqe *sqe)
+{
+	struct io_provide_buf *p = &req->pbuf;
+	u64 tmp;
+
+	if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off)
+		return -EINVAL;
+
+	tmp = READ_ONCE(sqe->fd);
+	if (!tmp || tmp > USHRT_MAX)
+		return -EINVAL;
+
+	memset(p, 0, sizeof(*p));
+	p->nbufs = tmp;
+	p->bgid = READ_ONCE(sqe->buf_group);
+	return 0;
+}
+
+static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
+			       int bgid, unsigned nbufs)
+{
+	unsigned i = 0;
+
+	/* shouldn't happen */
+	if (!nbufs)
+		return 0;
+
+	/* the head kbuf is the list itself */
+	while (!list_empty(&buf->list)) {
+		struct io_buffer *nxt;
+
+		nxt = list_first_entry(&buf->list, struct io_buffer, list);
+		list_del(&nxt->list);
+		kfree(nxt);
+		if (++i == nbufs)
+			return i;
+	}
+	i++;
+	kfree(buf);
+	idr_remove(&ctx->io_buffer_idr, bgid);
+
+	return i;
+}
+
+static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock)
+{
+	struct io_provide_buf *p = &req->pbuf;
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_buffer *head;
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, !force_nonblock);
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	ret = -ENOENT;
+	head = idr_find(&ctx->io_buffer_idr, p->bgid);
+	if (head)
+		ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
+
+	io_ring_submit_lock(ctx, !force_nonblock);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req(req);
+	return 0;
+}
+
+static int io_provide_buffers_prep(struct io_kiocb *req,
+				   const struct io_uring_sqe *sqe)
+{
+	struct io_provide_buf *p = &req->pbuf;
+	u64 tmp;
+
+	if (sqe->ioprio || sqe->rw_flags)
+		return -EINVAL;
+
+	tmp = READ_ONCE(sqe->fd);
+	if (!tmp || tmp > USHRT_MAX)
+		return -E2BIG;
+	p->nbufs = tmp;
+	p->addr = READ_ONCE(sqe->addr);
+	p->len = READ_ONCE(sqe->len);
+
+	if (!access_ok(u64_to_user_ptr(p->addr), p->len))
+		return -EFAULT;
+
+	p->bgid = READ_ONCE(sqe->buf_group);
+	tmp = READ_ONCE(sqe->off);
+	if (tmp > USHRT_MAX)
+		return -E2BIG;
+	p->bid = tmp;
+	return 0;
+}
+
+static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
+{
+	struct io_buffer *buf;
+	u64 addr = pbuf->addr;
+	int i, bid = pbuf->bid;
+
+	for (i = 0; i < pbuf->nbufs; i++) {
+		buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+		if (!buf)
+			break;
+
+		buf->addr = addr;
+		buf->len = pbuf->len;
+		buf->bid = bid;
+		addr += pbuf->len;
+		bid++;
+		if (!*head) {
+			INIT_LIST_HEAD(&buf->list);
+			*head = buf;
+		} else {
+			list_add_tail(&buf->list, &(*head)->list);
+		}
+	}
+
+	return i ? i : -ENOMEM;
+}
+
+static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock)
+{
+	struct io_provide_buf *p = &req->pbuf;
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_buffer *head, *list;
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, !force_nonblock);
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	list = head = idr_find(&ctx->io_buffer_idr, p->bgid);
+
+	ret = io_add_buffers(p, &head);
+	if (ret < 0)
+		goto out;
+
+	if (!list) {
+		ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1,
+					GFP_KERNEL);
+		if (ret < 0) {
+			__io_remove_buffers(ctx, head, p->bgid, -1U);
+			goto out;
+		}
+	}
+out:
+	io_ring_submit_unlock(ctx, !force_nonblock);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req(req);
+	return 0;
 }
 
 static int io_epoll_ctl_prep(struct io_kiocb *req,
@@ -2694,8 +3207,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req,
 #endif
 }
 
-static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
-			bool force_nonblock)
+static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock)
 {
 #if defined(CONFIG_EPOLL)
 	struct io_epoll *ie = &req->epoll;
@@ -2708,7 +3220,7 @@ static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 #else
 	return -EOPNOTSUPP;
@@ -2730,8 +3242,7 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 #endif
 }
 
-static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_madvise(struct io_kiocb *req, bool force_nonblock)
 {
 #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
 	struct io_madvise *ma = &req->madvise;
@@ -2744,7 +3255,7 @@ static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 #else
 	return -EOPNOTSUPP;
@@ -2762,8 +3273,7 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_fadvise *fa = &req->fadvise;
 	int ret;
@@ -2783,7 +3293,7 @@ static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 }
 
@@ -2820,8 +3330,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt,
-		    bool force_nonblock)
+static int io_statx(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_open *ctx = &req->open;
 	unsigned lookup_flags;
@@ -2858,7 +3367,7 @@ err:
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 }
 
@@ -2885,7 +3394,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 }
 
 /* only called when __close_fd_get_file() is done */
-static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt)
+static void __io_close_finish(struct io_kiocb *req)
 {
 	int ret;
 
@@ -2894,22 +3403,19 @@ static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
 	fput(req->close.put_file);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 }
 
 static void io_close_finish(struct io_wq_work **workptr)
 {
 	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct io_kiocb *nxt = NULL;
 
 	/* not cancellable, don't do io_req_cancelled() */
-	__io_close_finish(req, &nxt);
-	if (nxt)
-		io_wq_assign_next(workptr, nxt);
+	__io_close_finish(req);
+	io_steal_work(req, workptr);
 }
 
-static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
-		    bool force_nonblock)
+static int io_close(struct io_kiocb *req, bool force_nonblock)
 {
 	int ret;
 
@@ -2919,23 +3425,25 @@ static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
 		return ret;
 
 	/* if the file has a flush method, be safe and punt to async */
-	if (req->close.put_file->f_op->flush && !io_wq_current_is_worker())
-		goto eagain;
+	if (req->close.put_file->f_op->flush && force_nonblock) {
+		/* submission ref will be dropped, take it for async */
+		refcount_inc(&req->refs);
+
+		req->work.func = io_close_finish;
+		/*
+		 * Do manual async queue here to avoid grabbing files - we don't
+		 * need the files, and it'll cause io_close_finish() to close
+		 * the file again and cause a double CQE entry for this request
+		 */
+		io_queue_async_work(req);
+		return 0;
+	}
 
 	/*
 	 * No ->flush(), safely close from here and just punt the
 	 * fput() to async context.
 	 */
-	__io_close_finish(req, nxt);
-	return 0;
-eagain:
-	req->work.func = io_close_finish;
-	/*
-	 * Do manual async queue here to avoid grabbing files - we don't
-	 * need the files, and it'll cause io_close_finish() to close
-	 * the file again and cause a double CQE entry for this request
-	 */
-	io_queue_async_work(req);
+	__io_close_finish(req);
 	return 0;
 }
 
@@ -2957,47 +3465,62 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static void io_sync_file_range_finish(struct io_wq_work **workptr)
+static void __io_sync_file_range(struct io_kiocb *req)
 {
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct io_kiocb *nxt = NULL;
 	int ret;
 
-	if (io_req_cancelled(req))
-		return;
-
 	ret = sync_file_range(req->file, req->sync.off, req->sync.len,
 				req->sync.flags);
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, &nxt);
+	io_put_req(req);
+}
+
+
+static void io_sync_file_range_finish(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct io_kiocb *nxt = NULL;
+
+	if (io_req_cancelled(req))
+		return;
+	__io_sync_file_range(req);
+	io_put_req(req); /* put submission ref */
 	if (nxt)
 		io_wq_assign_next(workptr, nxt);
 }
 
-static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt,
-			      bool force_nonblock)
+static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
 {
-	struct io_wq_work *work, *old_work;
-
 	/* sync_file_range always requires a blocking context */
 	if (force_nonblock) {
-		io_put_req(req);
 		req->work.func = io_sync_file_range_finish;
 		return -EAGAIN;
 	}
 
-	work = old_work = &req->work;
-	io_sync_file_range_finish(&work);
-	if (work && work != old_work)
-		*nxt = container_of(work, struct io_kiocb, work);
+	__io_sync_file_range(req);
 	return 0;
 }
 
+#if defined(CONFIG_NET)
+static int io_setup_async_msg(struct io_kiocb *req,
+			      struct io_async_msghdr *kmsg)
+{
+	if (req->io)
+		return -EAGAIN;
+	if (io_alloc_async_ctx(req)) {
+		if (kmsg->iov != kmsg->fast_iov)
+			kfree(kmsg->iov);
+		return -ENOMEM;
+	}
+	req->flags |= REQ_F_NEED_CLEANUP;
+	memcpy(&req->io->msg, kmsg, sizeof(*kmsg));
+	return -EAGAIN;
+}
+
 static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-#if defined(CONFIG_NET)
 	struct io_sr_msg *sr = &req->sr_msg;
 	struct io_async_ctx *io = req->io;
 	int ret;
@@ -3023,15 +3546,10 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (!ret)
 		req->flags |= REQ_F_NEED_CLEANUP;
 	return ret;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
 	struct io_async_msghdr *kmsg = NULL;
 	struct socket *sock;
 	int ret;
@@ -3071,18 +3589,8 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 			flags |= MSG_DONTWAIT;
 
 		ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
-		if (force_nonblock && ret == -EAGAIN) {
-			if (req->io)
-				return -EAGAIN;
-			if (io_alloc_async_ctx(req)) {
-				if (kmsg->iov != kmsg->fast_iov)
-					kfree(kmsg->iov);
-				return -ENOMEM;
-			}
-			req->flags |= REQ_F_NEED_CLEANUP;
-			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
-			return -EAGAIN;
-		}
+		if (force_nonblock && ret == -EAGAIN)
+			return io_setup_async_msg(req, kmsg);
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 	}
@@ -3093,17 +3601,12 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-static int io_send(struct io_kiocb *req, struct io_kiocb **nxt,
-		   bool force_nonblock)
+static int io_send(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
 	struct socket *sock;
 	int ret;
 
@@ -3144,17 +3647,120 @@ static int io_send(struct io_kiocb *req, struct io_kiocb **nxt,
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
-#else
-	return -EOPNOTSUPP;
+}
+
+static int __io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
+{
+	struct io_sr_msg *sr = &req->sr_msg;
+	struct iovec __user *uiov;
+	size_t iov_len;
+	int ret;
+
+	ret = __copy_msghdr_from_user(&io->msg.msg, sr->msg, &io->msg.uaddr,
+					&uiov, &iov_len);
+	if (ret)
+		return ret;
+
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		if (iov_len > 1)
+			return -EINVAL;
+		if (copy_from_user(io->msg.iov, uiov, sizeof(*uiov)))
+			return -EFAULT;
+		sr->len = io->msg.iov[0].iov_len;
+		iov_iter_init(&io->msg.msg.msg_iter, READ, io->msg.iov, 1,
+				sr->len);
+		io->msg.iov = NULL;
+	} else {
+		ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+					&io->msg.iov, &io->msg.msg.msg_iter);
+		if (ret > 0)
+			ret = 0;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
+					struct io_async_ctx *io)
+{
+	struct compat_msghdr __user *msg_compat;
+	struct io_sr_msg *sr = &req->sr_msg;
+	struct compat_iovec __user *uiov;
+	compat_uptr_t ptr;
+	compat_size_t len;
+	int ret;
+
+	msg_compat = (struct compat_msghdr __user *) sr->msg;
+	ret = __get_compat_msghdr(&io->msg.msg, msg_compat, &io->msg.uaddr,
+					&ptr, &len);
+	if (ret)
+		return ret;
+
+	uiov = compat_ptr(ptr);
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		compat_ssize_t clen;
+
+		if (len > 1)
+			return -EINVAL;
+		if (!access_ok(uiov, sizeof(*uiov)))
+			return -EFAULT;
+		if (__get_user(clen, &uiov->iov_len))
+			return -EFAULT;
+		if (clen < 0)
+			return -EINVAL;
+		sr->len = io->msg.iov[0].iov_len;
+		io->msg.iov = NULL;
+	} else {
+		ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
+						&io->msg.iov,
+						&io->msg.msg.msg_iter);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
+{
+	io->msg.iov = io->msg.fast_iov;
+
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		return __io_compat_recvmsg_copy_hdr(req, io);
 #endif
+
+	return __io_recvmsg_copy_hdr(req, io);
+}
+
+static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
+					       int *cflags, bool needs_lock)
+{
+	struct io_sr_msg *sr = &req->sr_msg;
+	struct io_buffer *kbuf;
+
+	if (!(req->flags & REQ_F_BUFFER_SELECT))
+		return NULL;
+
+	kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock);
+	if (IS_ERR(kbuf))
+		return kbuf;
+
+	sr->kbuf = kbuf;
+	req->flags |= REQ_F_BUFFER_SELECTED;
+
+	*cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
+	*cflags |= IORING_CQE_F_BUFFER;
+	return kbuf;
 }
 
 static int io_recvmsg_prep(struct io_kiocb *req,
 			   const struct io_uring_sqe *sqe)
 {
-#if defined(CONFIG_NET)
 	struct io_sr_msg *sr = &req->sr_msg;
 	struct io_async_ctx *io = req->io;
 	int ret;
@@ -3162,6 +3768,7 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
+	sr->bgid = READ_ONCE(sqe->buf_group);
 
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
@@ -3174,30 +3781,24 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
-	io->msg.iov = io->msg.fast_iov;
-	ret = recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
-					&io->msg.uaddr, &io->msg.iov);
+	ret = io_recvmsg_copy_hdr(req, io);
 	if (!ret)
 		req->flags |= REQ_F_NEED_CLEANUP;
 	return ret;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
 	struct io_async_msghdr *kmsg = NULL;
 	struct socket *sock;
-	int ret;
+	int ret, cflags = 0;
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
 
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
+		struct io_buffer *kbuf;
 		struct io_async_ctx io;
 		unsigned flags;
 
@@ -3209,19 +3810,23 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 				kmsg->iov = kmsg->fast_iov;
 			kmsg->msg.msg_iter.iov = kmsg->iov;
 		} else {
-			struct io_sr_msg *sr = &req->sr_msg;
-
 			kmsg = &io.msg;
 			kmsg->msg.msg_name = &io.msg.addr;
 
-			io.msg.iov = io.msg.fast_iov;
-			ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg,
-					sr->msg_flags, &io.msg.uaddr,
-					&io.msg.iov);
+			ret = io_recvmsg_copy_hdr(req, &io);
 			if (ret)
 				return ret;
 		}
 
+		kbuf = io_recv_buffer_select(req, &cflags, !force_nonblock);
+		if (IS_ERR(kbuf)) {
+			return PTR_ERR(kbuf);
+		} else if (kbuf) {
+			kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
+			iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->iov,
+					1, req->sr_msg.len);
+		}
+
 		flags = req->sr_msg.msg_flags;
 		if (flags & MSG_DONTWAIT)
 			req->flags |= REQ_F_NOWAIT;
@@ -3230,18 +3835,8 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 
 		ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
 						kmsg->uaddr, flags);
-		if (force_nonblock && ret == -EAGAIN) {
-			if (req->io)
-				return -EAGAIN;
-			if (io_alloc_async_ctx(req)) {
-				if (kmsg->iov != kmsg->fast_iov)
-					kfree(kmsg->iov);
-				return -ENOMEM;
-			}
-			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
-			req->flags |= REQ_F_NEED_CLEANUP;
-			return -EAGAIN;
-		}
+		if (force_nonblock && ret == -EAGAIN)
+			return io_setup_async_msg(req, kmsg);
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 	}
@@ -3249,22 +3844,18 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (kmsg && kmsg->iov != kmsg->fast_iov)
 		kfree(kmsg->iov);
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	io_cqring_add_event(req, ret);
+	__io_cqring_add_event(req, ret, cflags);
 	if (ret < 0)
 		req_set_fail_links(req);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
-		   bool force_nonblock)
+static int io_recv(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
+	struct io_buffer *kbuf = NULL;
 	struct socket *sock;
-	int ret;
+	int ret, cflags = 0;
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
@@ -3272,15 +3863,25 @@ static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_sr_msg *sr = &req->sr_msg;
+		void __user *buf = sr->buf;
 		struct msghdr msg;
 		struct iovec iov;
 		unsigned flags;
 
-		ret = import_single_range(READ, sr->buf, sr->len, &iov,
+		kbuf = io_recv_buffer_select(req, &cflags, !force_nonblock);
+		if (IS_ERR(kbuf))
+			return PTR_ERR(kbuf);
+		else if (kbuf)
+			buf = u64_to_user_ptr(kbuf->addr);
+
+		ret = import_single_range(READ, buf, sr->len, &iov,
 						&msg.msg_iter);
-		if (ret)
+		if (ret) {
+			kfree(kbuf);
 			return ret;
+		}
 
+		req->flags |= REQ_F_NEED_CLEANUP;
 		msg.msg_name = NULL;
 		msg.msg_control = NULL;
 		msg.msg_controllen = 0;
@@ -3301,20 +3902,17 @@ static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
 			ret = -EINTR;
 	}
 
-	io_cqring_add_event(req, ret);
+	kfree(kbuf);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	__io_cqring_add_event(req, ret, cflags);
 	if (ret < 0)
 		req_set_fail_links(req);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-
 static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-#if defined(CONFIG_NET)
 	struct io_accept *accept = &req->accept;
 
 	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
@@ -3327,14 +3925,9 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	accept->flags = READ_ONCE(sqe->accept_flags);
 	accept->nofile = rlimit(RLIMIT_NOFILE);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-#if defined(CONFIG_NET)
-static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
-		       bool force_nonblock)
+static int __io_accept(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_accept *accept = &req->accept;
 	unsigned file_flags;
@@ -3351,44 +3944,34 @@ static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
 }
 
 static void io_accept_finish(struct io_wq_work **workptr)
 {
 	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct io_kiocb *nxt = NULL;
 
 	if (io_req_cancelled(req))
 		return;
-	__io_accept(req, &nxt, false);
-	if (nxt)
-		io_wq_assign_next(workptr, nxt);
+	__io_accept(req, false);
+	io_steal_work(req, workptr);
 }
-#endif
 
-static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
-		     bool force_nonblock)
+static int io_accept(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
 	int ret;
 
-	ret = __io_accept(req, nxt, force_nonblock);
+	ret = __io_accept(req, force_nonblock);
 	if (ret == -EAGAIN && force_nonblock) {
 		req->work.func = io_accept_finish;
-		io_put_req(req);
 		return -EAGAIN;
 	}
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-#if defined(CONFIG_NET)
 	struct io_connect *conn = &req->connect;
 	struct io_async_ctx *io = req->io;
 
@@ -3405,15 +3988,10 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	return move_addr_to_kernel(conn->addr, conn->addr_len,
 					&io->connect.address);
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
-static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt,
-		      bool force_nonblock)
+static int io_connect(struct io_kiocb *req, bool force_nonblock)
 {
-#if defined(CONFIG_NET)
 	struct io_async_ctx __io, *io;
 	unsigned file_flags;
 	int ret;
@@ -3449,25 +4027,301 @@ out:
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 	return 0;
-#else
+}
+#else /* !CONFIG_NET */
+static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
 	return -EOPNOTSUPP;
-#endif
 }
 
-static void io_poll_remove_one(struct io_kiocb *req)
+static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)
 {
-	struct io_poll_iocb *poll = &req->poll;
+	return -EOPNOTSUPP;
+}
+
+static int io_send(struct io_kiocb *req, bool force_nonblock)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_recvmsg_prep(struct io_kiocb *req,
+			   const struct io_uring_sqe *sqe)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_recv(struct io_kiocb *req, bool force_nonblock)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_accept(struct io_kiocb *req, bool force_nonblock)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	return -EOPNOTSUPP;
+}
+
+static int io_connect(struct io_kiocb *req, bool force_nonblock)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_NET */
+
+struct io_poll_table {
+	struct poll_table_struct pt;
+	struct io_kiocb *req;
+	int error;
+};
+
+static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
+			    struct wait_queue_head *head)
+{
+	if (unlikely(poll->head)) {
+		pt->error = -EINVAL;
+		return;
+	}
+
+	pt->error = 0;
+	poll->head = head;
+	add_wait_queue(head, &poll->wait);
+}
+
+static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+			       struct poll_table_struct *p)
+{
+	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+
+	__io_queue_proc(&pt->req->apoll->poll, pt, head);
+}
+
+static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
+			   __poll_t mask, task_work_func_t func)
+{
+	struct task_struct *tsk;
+
+	/* for instances that support it check for an event match first: */
+	if (mask && !(mask & poll->events))
+		return 0;
+
+	trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);
+
+	list_del_init(&poll->wait.entry);
+
+	tsk = req->task;
+	req->result = mask;
+	init_task_work(&req->task_work, func);
+	/*
+	 * If this fails, then the task is exiting. If that is the case, then
+	 * the exit check will ultimately cancel these work items. Hence we
+	 * don't need to check here and handle it specifically.
+	 */
+	task_work_add(tsk, &req->task_work, true);
+	wake_up_process(tsk);
+	return 1;
+}
+
+static void io_async_task_func(struct callback_head *cb)
+{
+	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+	struct async_poll *apoll = req->apoll;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	trace_io_uring_task_run(req->ctx, req->opcode, req->user_data);
+
+	WARN_ON_ONCE(!list_empty(&req->apoll->poll.wait.entry));
+
+	if (hash_hashed(&req->hash_node)) {
+		spin_lock_irq(&ctx->completion_lock);
+		hash_del(&req->hash_node);
+		spin_unlock_irq(&ctx->completion_lock);
+	}
+
+	/* restore ->work in case we need to retry again */
+	memcpy(&req->work, &apoll->work, sizeof(req->work));
+
+	__set_current_state(TASK_RUNNING);
+	mutex_lock(&ctx->uring_lock);
+	__io_queue_sqe(req, NULL);
+	mutex_unlock(&ctx->uring_lock);
+
+	kfree(apoll);
+}
+
+static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+			void *key)
+{
+	struct io_kiocb *req = wait->private;
+	struct io_poll_iocb *poll = &req->apoll->poll;
+
+	trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data,
+					key_to_poll(key));
+
+	return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func);
+}
+
+static void io_poll_req_insert(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct hlist_head *list;
+
+	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
+	hlist_add_head(&req->hash_node, list);
+}
+
+static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
+				      struct io_poll_iocb *poll,
+				      struct io_poll_table *ipt, __poll_t mask,
+				      wait_queue_func_t wake_func)
+	__acquires(&ctx->completion_lock)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	bool cancel = false;
+
+	poll->file = req->file;
+	poll->head = NULL;
+	poll->done = poll->canceled = false;
+	poll->events = mask;
+
+	ipt->pt._key = mask;
+	ipt->req = req;
+	ipt->error = -EINVAL;
+
+	INIT_LIST_HEAD(&poll->wait.entry);
+	init_waitqueue_func_entry(&poll->wait, wake_func);
+	poll->wait.private = req;
+
+	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
+
+	spin_lock_irq(&ctx->completion_lock);
+	if (likely(poll->head)) {
+		spin_lock(&poll->head->lock);
+		if (unlikely(list_empty(&poll->wait.entry))) {
+			if (ipt->error)
+				cancel = true;
+			ipt->error = 0;
+			mask = 0;
+		}
+		if (mask || ipt->error)
+			list_del_init(&poll->wait.entry);
+		else if (cancel)
+			WRITE_ONCE(poll->canceled, true);
+		else if (!poll->done) /* actually waiting for an event */
+			io_poll_req_insert(req);
+		spin_unlock(&poll->head->lock);
+	}
+
+	return mask;
+}
+
+static bool io_arm_poll_handler(struct io_kiocb *req)
+{
+	const struct io_op_def *def = &io_op_defs[req->opcode];
+	struct io_ring_ctx *ctx = req->ctx;
+	struct async_poll *apoll;
+	struct io_poll_table ipt;
+	__poll_t mask, ret;
+
+	if (!req->file || !file_can_poll(req->file))
+		return false;
+	if (req->flags & (REQ_F_MUST_PUNT | REQ_F_POLLED))
+		return false;
+	if (!def->pollin && !def->pollout)
+		return false;
+
+	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
+	if (unlikely(!apoll))
+		return false;
+
+	req->flags |= REQ_F_POLLED;
+	memcpy(&apoll->work, &req->work, sizeof(req->work));
+
+	/*
+	 * Don't need a reference here, as we're adding it to the task
+	 * task_works list. If the task exits, the list is pruned.
+	 */
+	req->task = current;
+	req->apoll = apoll;
+	INIT_HLIST_NODE(&req->hash_node);
+
+	mask = 0;
+	if (def->pollin)
+		mask |= POLLIN | POLLRDNORM;
+	if (def->pollout)
+		mask |= POLLOUT | POLLWRNORM;
+	mask |= POLLERR | POLLPRI;
+
+	ipt.pt._qproc = io_async_queue_proc;
+
+	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
+					io_async_wake);
+	if (ret) {
+		ipt.error = 0;
+		apoll->poll.done = true;
+		spin_unlock_irq(&ctx->completion_lock);
+		memcpy(&req->work, &apoll->work, sizeof(req->work));
+		kfree(apoll);
+		return false;
+	}
+	spin_unlock_irq(&ctx->completion_lock);
+	trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask,
+					apoll->poll.events);
+	return true;
+}
+
+static bool __io_poll_remove_one(struct io_kiocb *req,
+				 struct io_poll_iocb *poll)
+{
+	bool do_complete = false;
 
 	spin_lock(&poll->head->lock);
 	WRITE_ONCE(poll->canceled, true);
 	if (!list_empty(&poll->wait.entry)) {
 		list_del_init(&poll->wait.entry);
-		io_queue_async_work(req);
+		do_complete = true;
 	}
 	spin_unlock(&poll->head->lock);
+	return do_complete;
+}
+
+static bool io_poll_remove_one(struct io_kiocb *req)
+{
+	bool do_complete;
+
+	if (req->opcode == IORING_OP_POLL_ADD) {
+		do_complete = __io_poll_remove_one(req, &req->poll);
+	} else {
+		/* non-poll requests have submit ref still */
+		do_complete = __io_poll_remove_one(req, &req->apoll->poll);
+		if (do_complete)
+			io_put_req(req);
+	}
+
 	hash_del(&req->hash_node);
+
+	if (do_complete) {
+		io_cqring_fill_event(req, -ECANCELED);
+		io_commit_cqring(req->ctx);
+		req->flags |= REQ_F_COMP_LOCKED;
+		io_put_req(req);
+	}
+
+	return do_complete;
 }
 
 static void io_poll_remove_all(struct io_ring_ctx *ctx)
@@ -3485,6 +4339,8 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx)
 			io_poll_remove_one(req);
 	}
 	spin_unlock_irq(&ctx->completion_lock);
+
+	io_cqring_ev_posted(ctx);
 }
 
 static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
@@ -3494,10 +4350,11 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
 
 	list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
 	hlist_for_each_entry(req, list, hash_node) {
-		if (sqe_addr == req->user_data) {
-			io_poll_remove_one(req);
+		if (sqe_addr != req->user_data)
+			continue;
+		if (io_poll_remove_one(req))
 			return 0;
-		}
+		return -EALREADY;
 	}
 
 	return -ENOENT;
@@ -3543,186 +4400,54 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
 	struct io_ring_ctx *ctx = req->ctx;
 
 	req->poll.done = true;
-	if (error)
-		io_cqring_fill_event(req, error);
-	else
-		io_cqring_fill_event(req, mangle_poll(mask));
+	io_cqring_fill_event(req, error ? error : mangle_poll(mask));
 	io_commit_cqring(ctx);
 }
 
-static void io_poll_complete_work(struct io_wq_work **workptr)
+static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
 {
-	struct io_wq_work *work = *workptr;
-	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-	struct io_poll_iocb *poll = &req->poll;
-	struct poll_table_struct pt = { ._key = poll->events };
 	struct io_ring_ctx *ctx = req->ctx;
-	struct io_kiocb *nxt = NULL;
-	__poll_t mask = 0;
-	int ret = 0;
 
-	if (work->flags & IO_WQ_WORK_CANCEL) {
-		WRITE_ONCE(poll->canceled, true);
-		ret = -ECANCELED;
-	} else if (READ_ONCE(poll->canceled)) {
-		ret = -ECANCELED;
-	}
-
-	if (ret != -ECANCELED)
-		mask = vfs_poll(poll->file, &pt) & poll->events;
-
-	/*
-	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
-	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
-	 * synchronize with them.  In the cancellation case the list_del_init
-	 * itself is not actually needed, but harmless so we keep it in to
-	 * avoid further branches in the fast path.
-	 */
 	spin_lock_irq(&ctx->completion_lock);
-	if (!mask && ret != -ECANCELED) {
-		add_wait_queue(poll->head, &poll->wait);
-		spin_unlock_irq(&ctx->completion_lock);
-		return;
-	}
 	hash_del(&req->hash_node);
-	io_poll_complete(req, mask, ret);
+	io_poll_complete(req, req->result, 0);
+	req->flags |= REQ_F_COMP_LOCKED;
+	io_put_req_find_next(req, nxt);
 	spin_unlock_irq(&ctx->completion_lock);
 
 	io_cqring_ev_posted(ctx);
-
-	if (ret < 0)
-		req_set_fail_links(req);
-	io_put_req_find_next(req, &nxt);
-	if (nxt)
-		io_wq_assign_next(workptr, nxt);
 }
 
-static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes)
+static void io_poll_task_func(struct callback_head *cb)
 {
-	struct io_kiocb *req, *tmp;
-	struct req_batch rb;
+	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+	struct io_kiocb *nxt = NULL;
 
-	rb.to_free = rb.need_iter = 0;
-	spin_lock_irq(&ctx->completion_lock);
-	llist_for_each_entry_safe(req, tmp, nodes, llist_node) {
-		hash_del(&req->hash_node);
-		io_poll_complete(req, req->result, 0);
+	io_poll_task_handler(req, &nxt);
+	if (nxt) {
+		struct io_ring_ctx *ctx = nxt->ctx;
 
-		if (refcount_dec_and_test(&req->refs) &&
-		    !io_req_multi_free(&rb, req)) {
-			req->flags |= REQ_F_COMP_LOCKED;
-			io_free_req(req);
-		}
+		mutex_lock(&ctx->uring_lock);
+		__io_queue_sqe(nxt, NULL);
+		mutex_unlock(&ctx->uring_lock);
 	}
-	spin_unlock_irq(&ctx->completion_lock);
-
-	io_cqring_ev_posted(ctx);
-	io_free_req_many(ctx, &rb);
-}
-
-static void io_poll_flush(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct llist_node *nodes;
-
-	nodes = llist_del_all(&req->ctx->poll_llist);
-	if (nodes)
-		__io_poll_flush(req->ctx, nodes);
-}
-
-static void io_poll_trigger_evfd(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
-	eventfd_signal(req->ctx->cq_ev_fd, 1);
-	io_put_req(req);
 }
 
 static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 			void *key)
 {
-	struct io_poll_iocb *poll = wait->private;
-	struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
-	struct io_ring_ctx *ctx = req->ctx;
-	__poll_t mask = key_to_poll(key);
-
-	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & poll->events))
-		return 0;
-
-	list_del_init(&poll->wait.entry);
-
-	/*
-	 * Run completion inline if we can. We're using trylock here because
-	 * we are violating the completion_lock -> poll wq lock ordering.
-	 * If we have a link timeout we're going to need the completion_lock
-	 * for finalizing the request, mark us as having grabbed that already.
-	 */
-	if (mask) {
-		unsigned long flags;
-
-		if (llist_empty(&ctx->poll_llist) &&
-		    spin_trylock_irqsave(&ctx->completion_lock, flags)) {
-			bool trigger_ev;
-
-			hash_del(&req->hash_node);
-			io_poll_complete(req, mask, 0);
-
-			trigger_ev = io_should_trigger_evfd(ctx);
-			if (trigger_ev && eventfd_signal_count()) {
-				trigger_ev = false;
-				req->work.func = io_poll_trigger_evfd;
-			} else {
-				req->flags |= REQ_F_COMP_LOCKED;
-				io_put_req(req);
-				req = NULL;
-			}
-			spin_unlock_irqrestore(&ctx->completion_lock, flags);
-			__io_cqring_ev_posted(ctx, trigger_ev);
-		} else {
-			req->result = mask;
-			req->llist_node.next = NULL;
-			/* if the list wasn't empty, we're done */
-			if (!llist_add(&req->llist_node, &ctx->poll_llist))
-				req = NULL;
-			else
-				req->work.func = io_poll_flush;
-		}
-	}
-	if (req)
-		io_queue_async_work(req);
+	struct io_kiocb *req = wait->private;
+	struct io_poll_iocb *poll = &req->poll;
 
-	return 1;
+	return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func);
 }
 
-struct io_poll_table {
-	struct poll_table_struct pt;
-	struct io_kiocb *req;
-	int error;
-};
-
 static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 			       struct poll_table_struct *p)
 {
 	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
 
-	if (unlikely(pt->req->poll.head)) {
-		pt->error = -EINVAL;
-		return;
-	}
-
-	pt->error = 0;
-	pt->req->poll.head = head;
-	add_wait_queue(head, &pt->req->poll.wait);
-}
-
-static void io_poll_req_insert(struct io_kiocb *req)
-{
-	struct io_ring_ctx *ctx = req->ctx;
-	struct hlist_head *list;
-
-	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
-	hlist_add_head(&req->hash_node, list);
+	__io_queue_proc(&pt->req->poll, pt, head);
 }
 
 static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -3739,55 +4464,29 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 
 	events = READ_ONCE(sqe->poll_events);
 	poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
+
+	/*
+	 * Don't need a reference here, as we're adding it to the task
+	 * task_works list. If the task exits, the list is pruned.
+	 */
+	req->task = current;
 	return 0;
 }
 
-static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt)
+static int io_poll_add(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_poll_table ipt;
-	bool cancel = false;
 	__poll_t mask;
 
-	INIT_IO_WORK(&req->work, io_poll_complete_work);
 	INIT_HLIST_NODE(&req->hash_node);
-
-	poll->head = NULL;
-	poll->done = false;
-	poll->canceled = false;
-
-	ipt.pt._qproc = io_poll_queue_proc;
-	ipt.pt._key = poll->events;
-	ipt.req = req;
-	ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
-
-	/* initialized the list so that we can do list_empty checks */
-	INIT_LIST_HEAD(&poll->wait.entry);
-	init_waitqueue_func_entry(&poll->wait, io_poll_wake);
-	poll->wait.private = poll;
-
 	INIT_LIST_HEAD(&req->list);
+	ipt.pt._qproc = io_poll_queue_proc;
 
-	mask = vfs_poll(poll->file, &ipt.pt) & poll->events;
+	mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events,
+					io_poll_wake);
 
-	spin_lock_irq(&ctx->completion_lock);
-	if (likely(poll->head)) {
-		spin_lock(&poll->head->lock);
-		if (unlikely(list_empty(&poll->wait.entry))) {
-			if (ipt.error)
-				cancel = true;
-			ipt.error = 0;
-			mask = 0;
-		}
-		if (mask || ipt.error)
-			list_del_init(&poll->wait.entry);
-		else if (cancel)
-			WRITE_ONCE(poll->canceled, true);
-		else if (!poll->done) /* actually waiting for an event */
-			io_poll_req_insert(req);
-		spin_unlock(&poll->head->lock);
-	}
 	if (mask) { /* no async, we'd stolen it */
 		ipt.error = 0;
 		io_poll_complete(req, mask, 0);
@@ -3796,7 +4495,7 @@ static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt)
 
 	if (mask) {
 		io_cqring_ev_posted(ctx);
-		io_put_req_find_next(req, nxt);
+		io_put_req(req);
 	}
 	return ipt.error;
 }
@@ -4045,7 +4744,7 @@ static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr)
 
 static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
 				     struct io_kiocb *req, __u64 sqe_addr,
-				     struct io_kiocb **nxt, int success_ret)
+				     int success_ret)
 {
 	unsigned long flags;
 	int ret;
@@ -4071,7 +4770,7 @@ done:
 
 	if (ret < 0)
 		req_set_fail_links(req);
-	io_put_req_find_next(req, nxt);
+	io_put_req(req);
 }
 
 static int io_async_cancel_prep(struct io_kiocb *req,
@@ -4087,11 +4786,11 @@ static int io_async_cancel_prep(struct io_kiocb *req,
 	return 0;
 }
 
-static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt)
+static int io_async_cancel(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0);
+	io_async_find_and_cancel(ctx, req, req->cancel.addr, 0);
 	return 0;
 }
 
@@ -4226,6 +4925,15 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	case IORING_OP_EPOLL_CTL:
 		ret = io_epoll_ctl_prep(req, sqe);
 		break;
+	case IORING_OP_SPLICE:
+		ret = io_splice_prep(req, sqe);
+		break;
+	case IORING_OP_PROVIDE_BUFFERS:
+		ret = io_provide_buffers_prep(req, sqe);
+		break;
+	case IORING_OP_REMOVE_BUFFERS:
+		ret = io_remove_buffers_prep(req, sqe);
+		break;
 	default:
 		printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
 				req->opcode);
@@ -4272,29 +4980,43 @@ static void io_cleanup_req(struct io_kiocb *req)
 	case IORING_OP_READV:
 	case IORING_OP_READ_FIXED:
 	case IORING_OP_READ:
+		if (req->flags & REQ_F_BUFFER_SELECTED)
+			kfree((void *)(unsigned long)req->rw.addr);
+		/* fallthrough */
 	case IORING_OP_WRITEV:
 	case IORING_OP_WRITE_FIXED:
 	case IORING_OP_WRITE:
 		if (io->rw.iov != io->rw.fast_iov)
 			kfree(io->rw.iov);
 		break;
-	case IORING_OP_SENDMSG:
 	case IORING_OP_RECVMSG:
+		if (req->flags & REQ_F_BUFFER_SELECTED)
+			kfree(req->sr_msg.kbuf);
+		/* fallthrough */
+	case IORING_OP_SENDMSG:
 		if (io->msg.iov != io->msg.fast_iov)
 			kfree(io->msg.iov);
 		break;
+	case IORING_OP_RECV:
+		if (req->flags & REQ_F_BUFFER_SELECTED)
+			kfree(req->sr_msg.kbuf);
+		break;
 	case IORING_OP_OPENAT:
 	case IORING_OP_OPENAT2:
 	case IORING_OP_STATX:
 		putname(req->open.filename);
 		break;
+	case IORING_OP_SPLICE:
+		io_put_file(req, req->splice.file_in,
+			    (req->splice.flags & SPLICE_F_FD_IN_FIXED));
+		break;
 	}
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 }
 
 static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-			struct io_kiocb **nxt, bool force_nonblock)
+			bool force_nonblock)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret;
@@ -4311,7 +5033,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret < 0)
 				break;
 		}
-		ret = io_read(req, nxt, force_nonblock);
+		ret = io_read(req, force_nonblock);
 		break;
 	case IORING_OP_WRITEV:
 	case IORING_OP_WRITE_FIXED:
@@ -4321,7 +5043,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret < 0)
 				break;
 		}
-		ret = io_write(req, nxt, force_nonblock);
+		ret = io_write(req, force_nonblock);
 		break;
 	case IORING_OP_FSYNC:
 		if (sqe) {
@@ -4329,7 +5051,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret < 0)
 				break;
 		}
-		ret = io_fsync(req, nxt, force_nonblock);
+		ret = io_fsync(req, force_nonblock);
 		break;
 	case IORING_OP_POLL_ADD:
 		if (sqe) {
@@ -4337,7 +5059,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_poll_add(req, nxt);
+		ret = io_poll_add(req);
 		break;
 	case IORING_OP_POLL_REMOVE:
 		if (sqe) {
@@ -4353,7 +5075,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret < 0)
 				break;
 		}
-		ret = io_sync_file_range(req, nxt, force_nonblock);
+		ret = io_sync_file_range(req, force_nonblock);
 		break;
 	case IORING_OP_SENDMSG:
 	case IORING_OP_SEND:
@@ -4363,9 +5085,9 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 				break;
 		}
 		if (req->opcode == IORING_OP_SENDMSG)
-			ret = io_sendmsg(req, nxt, force_nonblock);
+			ret = io_sendmsg(req, force_nonblock);
 		else
-			ret = io_send(req, nxt, force_nonblock);
+			ret = io_send(req, force_nonblock);
 		break;
 	case IORING_OP_RECVMSG:
 	case IORING_OP_RECV:
@@ -4375,9 +5097,9 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 				break;
 		}
 		if (req->opcode == IORING_OP_RECVMSG)
-			ret = io_recvmsg(req, nxt, force_nonblock);
+			ret = io_recvmsg(req, force_nonblock);
 		else
-			ret = io_recv(req, nxt, force_nonblock);
+			ret = io_recv(req, force_nonblock);
 		break;
 	case IORING_OP_TIMEOUT:
 		if (sqe) {
@@ -4401,7 +5123,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_accept(req, nxt, force_nonblock);
+		ret = io_accept(req, force_nonblock);
 		break;
 	case IORING_OP_CONNECT:
 		if (sqe) {
@@ -4409,7 +5131,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_connect(req, nxt, force_nonblock);
+		ret = io_connect(req, force_nonblock);
 		break;
 	case IORING_OP_ASYNC_CANCEL:
 		if (sqe) {
@@ -4417,7 +5139,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_async_cancel(req, nxt);
+		ret = io_async_cancel(req);
 		break;
 	case IORING_OP_FALLOCATE:
 		if (sqe) {
@@ -4425,7 +5147,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_fallocate(req, nxt, force_nonblock);
+		ret = io_fallocate(req, force_nonblock);
 		break;
 	case IORING_OP_OPENAT:
 		if (sqe) {
@@ -4433,7 +5155,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_openat(req, nxt, force_nonblock);
+		ret = io_openat(req, force_nonblock);
 		break;
 	case IORING_OP_CLOSE:
 		if (sqe) {
@@ -4441,7 +5163,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_close(req, nxt, force_nonblock);
+		ret = io_close(req, force_nonblock);
 		break;
 	case IORING_OP_FILES_UPDATE:
 		if (sqe) {
@@ -4457,7 +5179,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_statx(req, nxt, force_nonblock);
+		ret = io_statx(req, force_nonblock);
 		break;
 	case IORING_OP_FADVISE:
 		if (sqe) {
@@ -4465,7 +5187,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_fadvise(req, nxt, force_nonblock);
+		ret = io_fadvise(req, force_nonblock);
 		break;
 	case IORING_OP_MADVISE:
 		if (sqe) {
@@ -4473,7 +5195,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_madvise(req, nxt, force_nonblock);
+		ret = io_madvise(req, force_nonblock);
 		break;
 	case IORING_OP_OPENAT2:
 		if (sqe) {
@@ -4481,7 +5203,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_openat2(req, nxt, force_nonblock);
+		ret = io_openat2(req, force_nonblock);
 		break;
 	case IORING_OP_EPOLL_CTL:
 		if (sqe) {
@@ -4489,7 +5211,31 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			if (ret)
 				break;
 		}
-		ret = io_epoll_ctl(req, nxt, force_nonblock);
+		ret = io_epoll_ctl(req, force_nonblock);
+		break;
+	case IORING_OP_SPLICE:
+		if (sqe) {
+			ret = io_splice_prep(req, sqe);
+			if (ret < 0)
+				break;
+		}
+		ret = io_splice(req, force_nonblock);
+		break;
+	case IORING_OP_PROVIDE_BUFFERS:
+		if (sqe) {
+			ret = io_provide_buffers_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_provide_buffers(req, force_nonblock);
+		break;
+	case IORING_OP_REMOVE_BUFFERS:
+		if (sqe) {
+			ret = io_remove_buffers_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_remove_buffers(req, force_nonblock);
 		break;
 	default:
 		ret = -EINVAL;
@@ -4522,7 +5268,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 {
 	struct io_wq_work *work = *workptr;
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-	struct io_kiocb *nxt = NULL;
 	int ret = 0;
 
 	/* if NO_CANCEL is set, we must still run the work */
@@ -4532,9 +5277,8 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 	}
 
 	if (!ret) {
-		req->in_async = true;
 		do {
-			ret = io_issue_sqe(req, NULL, &nxt, false);
+			ret = io_issue_sqe(req, NULL, false);
 			/*
 			 * We can get EAGAIN for polled IO even though we're
 			 * forcing a sync submission from here, since we can't
@@ -4546,18 +5290,13 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 		} while (1);
 	}
 
-	/* drop submission reference */
-	io_put_req(req);
-
 	if (ret) {
 		req_set_fail_links(req);
 		io_cqring_add_event(req, ret);
 		io_put_req(req);
 	}
 
-	/* if a dependent link is ready, pass it back */
-	if (!ret && nxt)
-		io_wq_assign_next(workptr, nxt);
+	io_steal_work(req, workptr);
 }
 
 static int io_req_needs_file(struct io_kiocb *req, int fd)
@@ -4578,41 +5317,52 @@ static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
 	return table->files[index & IORING_FILE_TABLE_MASK];;
 }
 
-static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
-			   const struct io_uring_sqe *sqe)
+static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
+			int fd, struct file **out_file, bool fixed)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	unsigned flags;
-	int fd;
-
-	flags = READ_ONCE(sqe->flags);
-	fd = READ_ONCE(sqe->fd);
-
-	if (!io_req_needs_file(req, fd))
-		return 0;
+	struct file *file;
 
-	if (flags & IOSQE_FIXED_FILE) {
+	if (fixed) {
 		if (unlikely(!ctx->file_data ||
 		    (unsigned) fd >= ctx->nr_user_files))
 			return -EBADF;
 		fd = array_index_nospec(fd, ctx->nr_user_files);
-		req->file = io_file_from_index(ctx, fd);
-		if (!req->file)
+		file = io_file_from_index(ctx, fd);
+		if (!file)
 			return -EBADF;
-		req->flags |= REQ_F_FIXED_FILE;
 		percpu_ref_get(&ctx->file_data->refs);
 	} else {
-		if (req->needs_fixed_file)
-			return -EBADF;
 		trace_io_uring_file_get(ctx, fd);
-		req->file = io_file_get(state, fd);
-		if (unlikely(!req->file))
+		file = __io_file_get(state, fd);
+		if (unlikely(!file))
 			return -EBADF;
 	}
 
+	*out_file = file;
 	return 0;
 }
 
+static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
+			   const struct io_uring_sqe *sqe)
+{
+	unsigned flags;
+	int fd;
+	bool fixed;
+
+	flags = READ_ONCE(sqe->flags);
+	fd = READ_ONCE(sqe->fd);
+
+	if (!io_req_needs_file(req, fd))
+		return 0;
+
+	fixed = (flags & IOSQE_FIXED_FILE);
+	if (unlikely(!fixed && req->needs_fixed_file))
+		return -EBADF;
+
+	return io_file_get(state, req, fd, &req->file, fixed);
+}
+
 static int io_grab_files(struct io_kiocb *req)
 {
 	int ret = -EBADF;
@@ -4672,8 +5422,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
 
 	if (prev) {
 		req_set_fail_links(prev);
-		io_async_find_and_cancel(ctx, req, prev->user_data, NULL,
-						-ETIME);
+		io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME);
 		io_put_req(prev);
 	} else {
 		io_cqring_add_event(req, -ETIME);
@@ -4710,6 +5459,9 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
 
 	if (!(req->flags & REQ_F_LINK))
 		return NULL;
+	/* for polled retry, if flag is set, we already went through here */
+	if (req->flags & REQ_F_POLLED)
+		return NULL;
 
 	nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb,
 					link_list);
@@ -4723,7 +5475,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
 static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_kiocb *linked_timeout;
-	struct io_kiocb *nxt = NULL;
+	struct io_kiocb *nxt;
 	const struct cred *old_creds = NULL;
 	int ret;
 
@@ -4739,7 +5491,7 @@ again:
 			old_creds = override_creds(req->work.creds);
 	}
 
-	ret = io_issue_sqe(req, sqe, &nxt, true);
+	ret = io_issue_sqe(req, sqe, true);
 
 	/*
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
@@ -4747,6 +5499,11 @@ again:
 	 */
 	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
 	    (req->flags & REQ_F_MUST_PUNT))) {
+		if (io_arm_poll_handler(req)) {
+			if (linked_timeout)
+				io_queue_linked_timeout(linked_timeout);
+			goto exit;
+		}
 punt:
 		if (io_op_defs[req->opcode].file_table) {
 			ret = io_grab_files(req);
@@ -4759,10 +5516,11 @@ punt:
 		 * submit reference when the iocb is actually submitted.
 		 */
 		io_queue_async_work(req);
-		goto done_req;
+		goto exit;
 	}
 
 err:
+	nxt = NULL;
 	/* drop submission reference */
 	io_put_req_find_next(req, &nxt);
 
@@ -4779,15 +5537,14 @@ err:
 		req_set_fail_links(req);
 		io_put_req(req);
 	}
-done_req:
 	if (nxt) {
 		req = nxt;
-		nxt = NULL;
 
 		if (req->flags & REQ_F_FORCE_ASYNC)
 			goto punt;
 		goto again;
 	}
+exit:
 	if (old_creds)
 		revert_creds(old_creds);
 }
@@ -4829,7 +5586,8 @@ static inline void io_queue_link_head(struct io_kiocb *req)
 }
 
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
-				IOSQE_IO_HARDLINK | IOSQE_ASYNC)
+				IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
+				IOSQE_BUFFER_SELECT)
 
 static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			  struct io_submit_state *state, struct io_kiocb **link)
@@ -4846,6 +5604,12 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		goto err_req;
 	}
 
+	if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
+	    !io_op_defs[req->opcode].buffer_select) {
+		ret = -EOPNOTSUPP;
+		goto err_req;
+	}
+
 	id = READ_ONCE(sqe->personality);
 	if (id) {
 		req->work.creds = idr_find(&ctx->personality_idr, id);
@@ -4857,8 +5621,9 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	}
 
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
-	req->flags |= sqe_flags & (IOSQE_IO_DRAIN|IOSQE_IO_HARDLINK|
-					IOSQE_ASYNC);
+	req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK |
+					IOSQE_ASYNC | IOSQE_FIXED_FILE |
+					IOSQE_BUFFER_SELECT);
 
 	ret = io_req_set_file(state, req, sqe);
 	if (unlikely(ret)) {
@@ -5079,7 +5844,6 @@ fail_req:
 			*mm = ctx->sqo_mm;
 		}
 
-		req->in_async = async;
 		req->needs_fixed_file = async;
 		trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
 						true, async);
@@ -5163,6 +5927,8 @@ static int io_sq_thread(void *data)
 			if (!list_empty(&ctx->poll_list) ||
 			    (!time_after(jiffies, timeout) && ret != -EBUSY &&
 			    !percpu_ref_is_dying(&ctx->refs))) {
+				if (current->task_works)
+					task_work_run();
 				cond_resched();
 				continue;
 			}
@@ -5194,6 +5960,10 @@ static int io_sq_thread(void *data)
 					finish_wait(&ctx->sqo_wait, &wait);
 					break;
 				}
+				if (current->task_works) {
+					task_work_run();
+					continue;
+				}
 				if (signal_pending(current))
 					flush_signals(current);
 				schedule();
@@ -5213,6 +5983,9 @@ static int io_sq_thread(void *data)
 		timeout = jiffies + ctx->sq_thread_idle;
 	}
 
+	if (current->task_works)
+		task_work_run();
+
 	set_fs(old_fs);
 	if (cur_mm) {
 		unuse_mm(cur_mm);
@@ -5277,8 +6050,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	struct io_rings *rings = ctx->rings;
 	int ret = 0;
 
-	if (io_cqring_events(ctx, false) >= min_events)
-		return 0;
+	do {
+		if (io_cqring_events(ctx, false) >= min_events)
+			return 0;
+		if (!current->task_works)
+			break;
+		task_work_run();
+	} while (1);
 
 	if (sig) {
 #ifdef CONFIG_COMPAT
@@ -5298,6 +6076,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	do {
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
+		if (current->task_works)
+			task_work_run();
 		if (io_should_wake(&iowq, false))
 			break;
 		schedule();
@@ -5607,7 +6387,6 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file)
 struct io_file_put {
 	struct llist_node llist;
 	struct file *file;
-	struct completion *done;
 };
 
 static void io_ring_file_ref_flush(struct fixed_file_data *data)
@@ -5618,10 +6397,7 @@ static void io_ring_file_ref_flush(struct fixed_file_data *data)
 	while ((node = llist_del_all(&data->put_llist)) != NULL) {
 		llist_for_each_entry_safe(pfile, tmp, node, llist) {
 			io_ring_file_put(data->ctx, pfile->file);
-			if (pfile->done)
-				complete(pfile->done);
-			else
-				kfree(pfile);
+			kfree(pfile);
 		}
 	}
 }
@@ -5816,33 +6592,18 @@ static void io_atomic_switch(struct percpu_ref *ref)
 	percpu_ref_get(&data->refs);
 }
 
-static bool io_queue_file_removal(struct fixed_file_data *data,
+static int io_queue_file_removal(struct fixed_file_data *data,
 				  struct file *file)
 {
-	struct io_file_put *pfile, pfile_stack;
-	DECLARE_COMPLETION_ONSTACK(done);
+	struct io_file_put *pfile;
 
-	/*
-	 * If we fail allocating the struct we need for doing async reomval
-	 * of this file, just punt to sync and wait for it.
-	 */
 	pfile = kzalloc(sizeof(*pfile), GFP_KERNEL);
-	if (!pfile) {
-		pfile = &pfile_stack;
-		pfile->done = &done;
-	}
+	if (!pfile)
+		return -ENOMEM;
 
 	pfile->file = file;
 	llist_add(&pfile->llist, &data->put_llist);
-
-	if (pfile == &pfile_stack) {
-		percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
-		wait_for_completion(&done);
-		flush_work(&data->ref_work);
-		return false;
-	}
-
-	return true;
+	return 0;
 }
 
 static int __io_sqe_files_update(struct io_ring_ctx *ctx,
@@ -5877,9 +6638,11 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 		index = i & IORING_FILE_TABLE_MASK;
 		if (table->files[index]) {
 			file = io_file_from_index(ctx, index);
+			err = io_queue_file_removal(data, file);
+			if (err)
+				break;
 			table->files[index] = NULL;
-			if (io_queue_file_removal(data, file))
-				ref_switch = true;
+			ref_switch = true;
 		}
 		if (fd != -1) {
 			file = fget(fd);
@@ -5932,20 +6695,14 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
 	return __io_sqe_files_update(ctx, &up, nr_args);
 }
 
-static void io_put_work(struct io_wq_work *work)
+static void io_free_work(struct io_wq_work *work)
 {
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
 
+	/* Consider that io_steal_work() relies on this ref */
 	io_put_req(req);
 }
 
-static void io_get_work(struct io_wq_work *work)
-{
-	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
-	refcount_inc(&req->refs);
-}
-
 static int io_init_wq_offload(struct io_ring_ctx *ctx,
 			      struct io_uring_params *p)
 {
@@ -5956,8 +6713,7 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx,
 	int ret = 0;
 
 	data.user = ctx->user;
-	data.get_work = io_get_work;
-	data.put_work = io_put_work;
+	data.free_work = io_free_work;
 
 	if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
 		/* Do QD, or 4 * CPUS, whatever is smallest */
@@ -6359,6 +7115,21 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx)
 	return -ENXIO;
 }
 
+static int __io_destroy_buffers(int id, void *p, void *data)
+{
+	struct io_ring_ctx *ctx = data;
+	struct io_buffer *buf = p;
+
+	__io_remove_buffers(ctx, buf, id, -1U);
+	return 0;
+}
+
+static void io_destroy_buffers(struct io_ring_ctx *ctx)
+{
+	idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx);
+	idr_destroy(&ctx->io_buffer_idr);
+}
+
 static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
 	io_finish_async(ctx);
@@ -6369,6 +7140,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_sqe_buffer_unregister(ctx);
 	io_sqe_files_unregister(ctx);
 	io_eventfd_unregister(ctx);
+	io_destroy_buffers(ctx);
 	idr_destroy(&ctx->personality_idr);
 
 #if defined(CONFIG_UNIX)
@@ -6623,6 +7395,9 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	int submitted = 0;
 	struct fd f;
 
+	if (current->task_works)
+		task_work_run();
+
 	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP))
 		return -EINVAL;
 
@@ -6669,7 +7444,14 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 
 		min_complete = min(min_complete, ctx->cq_entries);
 
-		if (ctx->flags & IORING_SETUP_IOPOLL) {
+		/*
+		 * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
+		 * space applications don't need to do io completion events
+		 * polling again, they can rely on io_sq_thread to do polling
+		 * work, which can reduce cpu usage and uring_lock contention.
+		 */
+		if (ctx->flags & IORING_SETUP_IOPOLL &&
+		    !(ctx->flags & IORING_SETUP_SQPOLL)) {
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
 		} else {
 			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
@@ -6745,6 +7527,17 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 		seq_printf(m, "Personalities:\n");
 		idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
 	}
+	seq_printf(m, "PollList:\n");
+	spin_lock_irq(&ctx->completion_lock);
+	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
+		struct hlist_head *list = &ctx->cancel_hash[i];
+		struct io_kiocb *req;
+
+		hlist_for_each_entry(req, list, hash_node)
+			seq_printf(m, "  op=%d, task_works=%d\n", req->opcode,
+					req->task->task_works != NULL);
+	}
+	spin_unlock_irq(&ctx->completion_lock);
 	mutex_unlock(&ctx->uring_lock);
 }
 
@@ -6961,7 +7754,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 
 	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
 			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-			IORING_FEAT_CUR_PERSONALITY;
+			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
@@ -7239,6 +8032,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(8,  __u64,  off);
 	BUILD_BUG_SQE_ELEM(8,  __u64,  addr2);
 	BUILD_BUG_SQE_ELEM(16, __u64,  addr);
+	BUILD_BUG_SQE_ELEM(16, __u64,  splice_off_in);
 	BUILD_BUG_SQE_ELEM(24, __u32,  len);
 	BUILD_BUG_SQE_ELEM(28,     __kernel_rwf_t, rw_flags);
 	BUILD_BUG_SQE_ELEM(28, /* compat */   int, rw_flags);
@@ -7253,11 +8047,14 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(28, __u32,  open_flags);
 	BUILD_BUG_SQE_ELEM(28, __u32,  statx_flags);
 	BUILD_BUG_SQE_ELEM(28, __u32,  fadvise_advice);
+	BUILD_BUG_SQE_ELEM(28, __u32,  splice_flags);
 	BUILD_BUG_SQE_ELEM(32, __u64,  user_data);
 	BUILD_BUG_SQE_ELEM(40, __u16,  buf_index);
 	BUILD_BUG_SQE_ELEM(42, __u16,  personality);
+	BUILD_BUG_SQE_ELEM(44, __s32,  splice_fd_in);
 
 	BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
+	BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
 	return 0;
 };
diff --git a/fs/splice.c b/fs/splice.c
index d671936d0aad..4735defc46ee 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1109,9 +1109,9 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 /*
  * Determine where to splice to/from.
  */
-static 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)
+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)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 15f3412d481e..54338fac45cb 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -391,6 +391,10 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
 			       struct user_msghdr __user *umsg, unsigned flags,
 			       struct sockaddr __user **uaddr,
 			       struct iovec **iov);
+extern int __copy_msghdr_from_user(struct msghdr *kmsg,
+				   struct user_msghdr __user *umsg,
+				   struct sockaddr __user **save_addr,
+				   struct iovec __user **uiov, size_t *nsegs);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 74b4911ac16d..ebbbfea48aa0 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -78,6 +78,9 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *,
 			      struct pipe_buffer *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 				      splice_direct_actor *);
+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);
 
 /*
  * for dynamic pipe sizing
diff --git a/include/net/compat.h b/include/net/compat.h
index f277653c7e17..e341260642fe 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -38,6 +38,9 @@ struct compat_cmsghdr {
 #define compat_mmsghdr	mmsghdr
 #endif /* defined(CONFIG_COMPAT) */
 
+int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
+			struct sockaddr __user **save_addr, compat_uptr_t *ptr,
+			compat_size_t *len);
 int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
 		      struct sockaddr __user **, struct iovec **);
 struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 27bd9e4f927b..9f0d3b7d56b0 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -357,6 +357,109 @@ TRACE_EVENT(io_uring_submit_sqe,
 			  __entry->force_nonblock, __entry->sq_thread)
 );
 
+TRACE_EVENT(io_uring_poll_arm,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events),
+
+	TP_ARGS(ctx, opcode, user_data, mask, events),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+		__field(  int,		events		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+		__entry->mask		= mask;
+		__entry->events		= events;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
+			  __entry->mask, __entry->events)
+);
+
+TRACE_EVENT(io_uring_poll_wake,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+	TP_ARGS(ctx, opcode, user_data, mask),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+		__entry->mask		= mask;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
+			  __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_add,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+	TP_ARGS(ctx, opcode, user_data, mask),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+		__entry->mask		= mask;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx, mask %x",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
+			  __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_run,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data),
+
+	TP_ARGS(ctx, opcode, user_data),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data)
+);
+
 #endif /* _TRACE_IO_URING_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 3f7961c1c243..e48d746b8e2a 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
 /*
  * Header file for the io_uring interface.
  *
@@ -23,7 +23,10 @@ struct io_uring_sqe {
 		__u64	off;	/* offset into file */
 		__u64	addr2;
 	};
-	__u64	addr;		/* pointer to buffer or iovecs */
+	union {
+		__u64	addr;	/* pointer to buffer or iovecs */
+		__u64	splice_off_in;
+	};
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
 		__kernel_rwf_t	rw_flags;
@@ -37,14 +40,21 @@ struct io_uring_sqe {
 		__u32		open_flags;
 		__u32		statx_flags;
 		__u32		fadvise_advice;
+		__u32		splice_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
 		struct {
-			/* index into fixed buffers, if used */
-			__u16	buf_index;
+			/* pack this to avoid bogus arm OABI complaints */
+			union {
+				/* index into fixed buffers, if used */
+				__u16	buf_index;
+				/* for grouped buffer selection */
+				__u16	buf_group;
+			} __attribute__((packed));
 			/* personality to use, if used */
 			__u16	personality;
+			__s32	splice_fd_in;
 		};
 		__u64	__pad2[3];
 	};
@@ -56,6 +66,7 @@ enum {
 	IOSQE_IO_LINK_BIT,
 	IOSQE_IO_HARDLINK_BIT,
 	IOSQE_ASYNC_BIT,
+	IOSQE_BUFFER_SELECT_BIT,
 };
 
 /*
@@ -71,6 +82,8 @@ enum {
 #define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
 /* always go async */
 #define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT	(1U << IOSQE_BUFFER_SELECT_BIT)
 
 /*
  * io_uring_setup() flags
@@ -113,6 +126,9 @@ enum {
 	IORING_OP_RECV,
 	IORING_OP_OPENAT2,
 	IORING_OP_EPOLL_CTL,
+	IORING_OP_SPLICE,
+	IORING_OP_PROVIDE_BUFFERS,
+	IORING_OP_REMOVE_BUFFERS,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -129,6 +145,12 @@ enum {
 #define IORING_TIMEOUT_ABS	(1U << 0)
 
 /*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED	(1U << 31) /* the last bit of __u32 */
+
+/*
  * IO completion data structure (Completion Queue Entry)
  */
 struct io_uring_cqe {
@@ -138,6 +160,17 @@ struct io_uring_cqe {
 };
 
 /*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
+ */
+#define IORING_CQE_F_BUFFER		(1U << 0)
+
+enum {
+	IORING_CQE_BUFFER_SHIFT		= 16,
+};
+
+/*
  * Magic offsets for the application to mmap the data it needs
  */
 #define IORING_OFF_SQ_RING		0ULL
@@ -204,6 +237,7 @@ struct io_uring_params {
 #define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
 #define IORING_FEAT_RW_CUR_POS		(1U << 3)
 #define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
+#define IORING_FEAT_FAST_POLL		(1U << 5)
 
 /*
  * io_uring_register(2) opcodes and arguments
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 0fef395662a6..825f28259a19 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -97,16 +97,26 @@ void task_work_run(void)
 		 * work->func() can do task_work_add(), do not set
 		 * work_exited unless the list is empty.
 		 */
-		raw_spin_lock_irq(&task->pi_lock);
 		do {
+			head = NULL;
 			work = READ_ONCE(task->task_works);
-			head = !work && (task->flags & PF_EXITING) ?
-				&work_exited : NULL;
+			if (!work) {
+				if (task->flags & PF_EXITING)
+					head = &work_exited;
+				else
+					break;
+			}
 		} while (cmpxchg(&task->task_works, work, head) != work);
-		raw_spin_unlock_irq(&task->pi_lock);
 
 		if (!work)
 			break;
+		/*
+		 * Synchronize with task_work_cancel(). It can not remove
+		 * the first entry == work, cmpxchg(task_works) must fail.
+		 * But it can remove another entry from the ->next list.
+		 */
+		raw_spin_lock_irq(&task->pi_lock);
+		raw_spin_unlock_irq(&task->pi_lock);
 
 		do {
 			next = work->next;
diff --git a/net/compat.c b/net/compat.c
index 47d99c784947..4bed96e84d9a 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -33,10 +33,10 @@
 #include <linux/uaccess.h>
 #include <net/compat.h>
 
-int get_compat_msghdr(struct msghdr *kmsg,
-		      struct compat_msghdr __user *umsg,
-		      struct sockaddr __user **save_addr,
-		      struct iovec **iov)
+int __get_compat_msghdr(struct msghdr *kmsg,
+			struct compat_msghdr __user *umsg,
+			struct sockaddr __user **save_addr,
+			compat_uptr_t *ptr, compat_size_t *len)
 {
 	struct compat_msghdr msg;
 	ssize_t err;
@@ -79,10 +79,26 @@ int get_compat_msghdr(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	*ptr = msg.msg_iov;
+	*len = msg.msg_iovlen;
+	return 0;
+}
+
+int get_compat_msghdr(struct msghdr *kmsg,
+		      struct compat_msghdr __user *umsg,
+		      struct sockaddr __user **save_addr,
+		      struct iovec **iov)
+{
+	compat_uptr_t ptr;
+	compat_size_t len;
+	ssize_t err;
+
+	err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len);
+	if (err)
+		return err;
 
-	err = compat_import_iovec(save_addr ? READ : WRITE,
-				   compat_ptr(msg.msg_iov), msg.msg_iovlen,
-				   UIO_FASTIOV, iov, &kmsg->msg_iter);
+	err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
+				   len, UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
 
diff --git a/net/socket.c b/net/socket.c
index 2eecf1517f76..2dd739fba866 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2228,10 +2228,10 @@ struct used_address {
 	unsigned int name_len;
 };
 
-static int copy_msghdr_from_user(struct msghdr *kmsg,
-				 struct user_msghdr __user *umsg,
-				 struct sockaddr __user **save_addr,
-				 struct iovec **iov)
+int __copy_msghdr_from_user(struct msghdr *kmsg,
+			    struct user_msghdr __user *umsg,
+			    struct sockaddr __user **save_addr,
+			    struct iovec __user **uiov, size_t *nsegs)
 {
 	struct user_msghdr msg;
 	ssize_t err;
@@ -2273,6 +2273,23 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	*uiov = msg.msg_iov;
+	*nsegs = msg.msg_iovlen;
+	return 0;
+}
+
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+				 struct user_msghdr __user *umsg,
+				 struct sockaddr __user **save_addr,
+				 struct iovec **iov)
+{
+	struct user_msghdr msg;
+	ssize_t err;
+
+	err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov,
+					&msg.msg_iovlen);
+	if (err)
+		return err;
 
 	err = import_iovec(save_addr ? READ : WRITE,
 			    msg.msg_iov, msg.msg_iovlen,