Merge tag 'io_uring-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - Add blkcg accounting for io-wq offload (Dennis)

 - A use-after-free fix for io-wq (Hillf)

 - Cancelation fixes and improvements

 - Use proper files_struct references for offload

 - Cleanup of io_uring_get_socket() since that can now go into our own
   header

 - SQPOLL fixes and cleanups, and support for sharing the thread

 - Improvement to how page accounting is done for registered buffers and
   huge pages, accounting the real pinned state

 - Series cleaning up the xarray code (Willy)

 - Various cleanups, refactoring, and improvements (Pavel)

 - Use raw spinlock for io-wq (Sebastian)

 - Add support for ring restrictions (Stefano)

* tag 'io_uring-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (62 commits)
  io_uring: keep a pointer ref_node in file_data
  io_uring: refactor *files_register()'s error paths
  io_uring: clean file_data access in files_register
  io_uring: don't delay io_init_req() error check
  io_uring: clean leftovers after splitting issue
  io_uring: remove timeout.list after hrtimer cancel
  io_uring: use a separate struct for timeout_remove
  io_uring: improve submit_state.ios_left accounting
  io_uring: simplify io_file_get()
  io_uring: kill extra check in fixed io_file_get()
  io_uring: clean up ->files grabbing
  io_uring: don't io_prep_async_work() linked reqs
  io_uring: Convert advanced XArray uses to the normal API
  io_uring: Fix XArray usage in io_uring_add_task_file
  io_uring: Fix use of XArray in __io_uring_files_cancel
  io_uring: fix break condition for __io_uring_register() waiting
  io_uring: no need to call xa_destroy() on empty xarray
  io_uring: batch account ->req_issue and task struct references
  io_uring: kill callback_head argument for io_req_task_work_add()
  io_uring: move req preps out of io_issue_sqe()
  ...

fs/exec.c

@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1895,6 +1896,11 @@ static int bprm_execve(struct linux_binprm *bprm,
 	struct files_struct *displaced;
 	int retval;
 
+	/*
+	 * Cancel any io_uring activity across execve
+	 */
+	io_uring_task_cancel();
+
 	retval = unshare_files(&displaced);
 	if (retval)
 		return retval;

fs/file.c

@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
 #include <net/sock.h>
+#include <linux/io_uring.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -452,6 +453,7 @@ void exit_files(struct task_struct *tsk)
 	struct files_struct * files = tsk->files;
 
 	if (files) {
+		io_uring_files_cancel(files);
 		task_lock(tsk);
 		tsk->files = NULL;
 		task_unlock(tsk);

fs/io-wq.c

@@ -17,6 +17,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/fs_struct.h>
 #include <linux/task_work.h>
+#include <linux/blk-cgroup.h>
 
 #include "io-wq.h"
 
@@ -26,9 +27,8 @@ enum {
 	IO_WORKER_F_UP		= 1,	/* up and active */
 	IO_WORKER_F_RUNNING	= 2,	/* account as running */
 	IO_WORKER_F_FREE	= 4,	/* worker on free list */
-	IO_WORKER_F_EXITING	= 8,	/* worker exiting */
-	IO_WORKER_F_FIXED	= 16,	/* static idle worker */
-	IO_WORKER_F_BOUND	= 32,	/* is doing bounded work */
+	IO_WORKER_F_FIXED	= 8,	/* static idle worker */
+	IO_WORKER_F_BOUND	= 16,	/* is doing bounded work */
 };
 
 enum {
@@ -57,9 +57,13 @@ struct io_worker {
 
 	struct rcu_head rcu;
 	struct mm_struct *mm;
+#ifdef CONFIG_BLK_CGROUP
+	struct cgroup_subsys_state *blkcg_css;
+#endif
 	const struct cred *cur_creds;
 	const struct cred *saved_creds;
 	struct files_struct *restore_files;
+	struct nsproxy *restore_nsproxy;
 	struct fs_struct *restore_fs;
 };
 
@@ -87,7 +91,7 @@ enum {
  */
 struct io_wqe {
 	struct {
-		spinlock_t lock;
+		raw_spinlock_t lock;
 		struct io_wq_work_list work_list;
 		unsigned long hash_map;
 		unsigned flags;
@@ -148,11 +152,12 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 
 	if (current->files != worker->restore_files) {
 		__acquire(&wqe->lock);
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		dropped_lock = true;
 
 		task_lock(current);
 		current->files = worker->restore_files;
+		current->nsproxy = worker->restore_nsproxy;
 		task_unlock(current);
 	}
 
@@ -166,7 +171,7 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 	if (worker->mm) {
 		if (!dropped_lock) {
 			__acquire(&wqe->lock);
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 			dropped_lock = true;
 		}
 		__set_current_state(TASK_RUNNING);
@@ -175,6 +180,13 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 		worker->mm = NULL;
 	}
 
+#ifdef CONFIG_BLK_CGROUP
+	if (worker->blkcg_css) {
+		kthread_associate_blkcg(NULL);
+		worker->blkcg_css = NULL;
+	}
+#endif
+
 	return dropped_lock;
 }
 
@@ -200,7 +212,6 @@ static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker);
-	unsigned nr_workers;
 
 	/*
 	 * If we're not at zero, someone else is holding a brief reference
@@ -220,23 +231,19 @@ static void io_worker_exit(struct io_worker *worker)
 	worker->flags = 0;
 	preempt_enable();
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	hlist_nulls_del_rcu(&worker->nulls_node);
 	list_del_rcu(&worker->all_list);
 	if (__io_worker_unuse(wqe, worker)) {
 		__release(&wqe->lock);
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 	}
 	acct->nr_workers--;
-	nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers +
-			wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers;
-	spin_unlock_irq(&wqe->lock);
-
-	/* all workers gone, wq exit can proceed */
-	if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs))
-		complete(&wqe->wq->done);
+	raw_spin_unlock_irq(&wqe->lock);
 
 	kfree_rcu(worker, rcu);
+	if (refcount_dec_and_test(&wqe->wq->refs))
+		complete(&wqe->wq->done);
 }
 
 static inline bool io_wqe_run_queue(struct io_wqe *wqe)
@@ -318,6 +325,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	worker->restore_files = current->files;
+	worker->restore_nsproxy = current->nsproxy;
 	worker->restore_fs = current->fs;
 	io_wqe_inc_running(wqe, worker);
 }
@@ -436,6 +444,17 @@ static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work)
 	work->flags |= IO_WQ_WORK_CANCEL;
 }
 
+static inline void io_wq_switch_blkcg(struct io_worker *worker,
+				      struct io_wq_work *work)
+{
+#ifdef CONFIG_BLK_CGROUP
+	if (work->blkcg_css != worker->blkcg_css) {
+		kthread_associate_blkcg(work->blkcg_css);
+		worker->blkcg_css = work->blkcg_css;
+	}
+#endif
+}
+
 static void io_wq_switch_creds(struct io_worker *worker,
 			       struct io_wq_work *work)
 {
@@ -454,6 +473,7 @@ static void io_impersonate_work(struct io_worker *worker,
 	if (work->files && current->files != work->files) {
 		task_lock(current);
 		current->files = work->files;
+		current->nsproxy = work->nsproxy;
 		task_unlock(current);
 	}
 	if (work->fs && current->fs != work->fs)
@@ -463,6 +483,7 @@ static void io_impersonate_work(struct io_worker *worker,
 	if (worker->cur_creds != work->creds)
 		io_wq_switch_creds(worker, work);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->fsize;
+	io_wq_switch_blkcg(worker, work);
 }
 
 static void io_assign_current_work(struct io_worker *worker,
@@ -504,7 +525,7 @@ static void io_worker_handle_work(struct io_worker *worker)
 		else if (!wq_list_empty(&wqe->work_list))
 			wqe->flags |= IO_WQE_FLAG_STALLED;
 
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		if (!work)
 			break;
 		io_assign_current_work(worker, work);
@@ -538,17 +559,17 @@ static void io_worker_handle_work(struct io_worker *worker)
 				io_wqe_enqueue(wqe, linked);
 
 			if (hash != -1U && !next_hashed) {
-				spin_lock_irq(&wqe->lock);
+				raw_spin_lock_irq(&wqe->lock);
 				wqe->hash_map &= ~BIT_ULL(hash);
 				wqe->flags &= ~IO_WQE_FLAG_STALLED;
 				/* skip unnecessary unlock-lock wqe->lock */
 				if (!work)
 					goto get_next;
-				spin_unlock_irq(&wqe->lock);
+				raw_spin_unlock_irq(&wqe->lock);
 			}
 		} while (work);
 
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 	} while (1);
 }
 
@@ -563,7 +584,7 @@ static int io_wqe_worker(void *data)
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
 		set_current_state(TASK_INTERRUPTIBLE);
 loop:
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 		if (io_wqe_run_queue(wqe)) {
 			__set_current_state(TASK_RUNNING);
 			io_worker_handle_work(worker);
@@ -574,7 +595,7 @@ static int io_wqe_worker(void *data)
 			__release(&wqe->lock);
 			goto loop;
 		}
-		spin_unlock_irq(&wqe->lock);
+		raw_spin_unlock_irq(&wqe->lock);
 		if (signal_pending(current))
 			flush_signals(current);
 		if (schedule_timeout(WORKER_IDLE_TIMEOUT))
@@ -586,11 +607,11 @@ static int io_wqe_worker(void *data)
 	}
 
 	if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
-		spin_lock_irq(&wqe->lock);
+		raw_spin_lock_irq(&wqe->lock);
 		if (!wq_list_empty(&wqe->work_list))
 			io_worker_handle_work(worker);
 		else
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 	}
 
 	io_worker_exit(worker);
@@ -630,14 +651,14 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
 
 	worker->flags &= ~IO_WORKER_F_RUNNING;
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	io_wqe_dec_running(wqe, worker);
-	spin_unlock_irq(&wqe->lock);
+	raw_spin_unlock_irq(&wqe->lock);
 }
 
 static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 {
-	struct io_wqe_acct *acct =&wqe->acct[index];
+	struct io_wqe_acct *acct = &wqe->acct[index];
 	struct io_worker *worker;
 
 	worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
@@ -656,7 +677,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 		return false;
 	}
 
-	spin_lock_irq(&wqe->lock);
+	raw_spin_lock_irq(&wqe->lock);
 	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
 	list_add_tail_rcu(&worker->all_list, &wqe->all_list);
 	worker->flags |= IO_WORKER_F_FREE;
@@ -665,11 +686,12 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
 	if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND))
 		worker->flags |= IO_WORKER_F_FIXED;
 	acct->nr_workers++;
-	spin_unlock_irq(&wqe->lock);
+	raw_spin_unlock_irq(&wqe->lock);
 
 	if (index == IO_WQ_ACCT_UNBOUND)
 		atomic_inc(&wq->user->processes);
 
+	refcount_inc(&wq->refs);
 	wake_up_process(worker->task);
 	return true;
 }
@@ -685,28 +707,63 @@ static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
 	return acct->nr_workers < acct->max_workers;
 }
 
+static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
+{
+	send_sig(SIGINT, worker->task, 1);
+	return false;
+}
+
+/*
+ * Iterate the passed in list and call the specific function for each
+ * worker that isn't exiting
+ */
+static bool io_wq_for_each_worker(struct io_wqe *wqe,
+				  bool (*func)(struct io_worker *, void *),
+				  void *data)
+{
+	struct io_worker *worker;
+	bool ret = false;
+
+	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
+		if (io_worker_get(worker)) {
+			/* no task if node is/was offline */
+			if (worker->task)
+				ret = func(worker, data);
+			io_worker_release(worker);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+static bool io_wq_worker_wake(struct io_worker *worker, void *data)
+{
+	wake_up_process(worker->task);
+	return false;
+}
+
 /*
  * Manager thread. Tasked with creating new workers, if we need them.
  */
 static int io_wq_manager(void *data)
 {
 	struct io_wq *wq = data;
-	int workers_to_create = num_possible_nodes();
 	int node;
 
 	/* create fixed workers */
-	refcount_set(&wq->refs, workers_to_create);
+	refcount_set(&wq->refs, 1);
 	for_each_node(node) {
 		if (!node_online(node))
 			continue;
-		if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
-			goto err;
-		workers_to_create--;
+		if (create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
+			continue;
+		set_bit(IO_WQ_BIT_ERROR, &wq->state);
+		set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		goto out;
 	}
 
-	while (workers_to_create--)
-		refcount_dec(&wq->refs);
-
 	complete(&wq->done);
 
 	while (!kthread_should_stop()) {
@@ -720,12 +777,12 @@ static int io_wq_manager(void *data)
 			if (!node_online(node))
 				continue;
 
-			spin_lock_irq(&wqe->lock);
+			raw_spin_lock_irq(&wqe->lock);
 			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
 				fork_worker[IO_WQ_ACCT_BOUND] = true;
 			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND))
 				fork_worker[IO_WQ_ACCT_UNBOUND] = true;
-			spin_unlock_irq(&wqe->lock);
+			raw_spin_unlock_irq(&wqe->lock);
 			if (fork_worker[IO_WQ_ACCT_BOUND])
 				create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND);
 			if (fork_worker[IO_WQ_ACCT_UNBOUND])
@@ -738,12 +795,18 @@ static int io_wq_manager(void *data)
 	if (current->task_works)
 		task_work_run();
 
-	return 0;
-err:
-	set_bit(IO_WQ_BIT_ERROR, &wq->state);
-	set_bit(IO_WQ_BIT_EXIT, &wq->state);
-	if (refcount_sub_and_test(workers_to_create, &wq->refs))
+out:
+	if (refcount_dec_and_test(&wq->refs)) {
 		complete(&wq->done);
+		return 0;
+	}
+	/* if ERROR is set and we get here, we have workers to wake */
+	if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) {
+		rcu_read_lock();
+		for_each_node(node)
+			io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
+		rcu_read_unlock();
+	}
 	return 0;
 }
 
@@ -821,10 +884,10 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 	}
 
 	work_flags = work->flags;
-	spin_lock_irqsave(&wqe->lock, flags);
+	raw_spin_lock_irqsave(&wqe->lock, flags);
 	io_wqe_insert_work(wqe, work);
 	wqe->flags &= ~IO_WQE_FLAG_STALLED;
-	spin_unlock_irqrestore(&wqe->lock, flags);
+	raw_spin_unlock_irqrestore(&wqe->lock, flags);
 
 	if ((work_flags & IO_WQ_WORK_CONCURRENT) ||
 	    !atomic_read(&acct->nr_running))
@@ -850,37 +913,6 @@ void io_wq_hash_work(struct io_wq_work *work, void *val)
 	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
 }
 
-static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
-{
-	send_sig(SIGINT, worker->task, 1);
-	return false;
-}
-
-/*
- * Iterate the passed in list and call the specific function for each
- * worker that isn't exiting
- */
-static bool io_wq_for_each_worker(struct io_wqe *wqe,
-				  bool (*func)(struct io_worker *, void *),
-				  void *data)
-{
-	struct io_worker *worker;
-	bool ret = false;
-
-	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
-		if (io_worker_get(worker)) {
-			/* no task if node is/was offline */
-			if (worker->task)
-				ret = func(worker, data);
-			io_worker_release(worker);
-			if (ret)
-				break;
-		}
-	}
-
-	return ret;
-}
-
 void io_wq_cancel_all(struct io_wq *wq)
 {
 	int node;
@@ -951,13 +983,13 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
 	unsigned long flags;
 
 retry:
-	spin_lock_irqsave(&wqe->lock, flags);
+	raw_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 (!match->fn(work, match->data))
 			continue;
 		io_wqe_remove_pending(wqe, work, prev);
-		spin_unlock_irqrestore(&wqe->lock, flags);
+		raw_spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
 		match->nr_pending++;
 		if (!match->cancel_all)
@@ -966,7 +998,7 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
 		/* not safe to continue after unlock */
 		goto retry;
 	}
-	spin_unlock_irqrestore(&wqe->lock, flags);
+	raw_spin_unlock_irqrestore(&wqe->lock, flags);
 }
 
 static void io_wqe_cancel_running_work(struct io_wqe *wqe,
@@ -1074,7 +1106,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 		}
 		atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
 		wqe->wq = wq;
-		spin_lock_init(&wqe->lock);
+		raw_spin_lock_init(&wqe->lock);
 		INIT_WQ_LIST(&wqe->work_list);
 		INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
 		INIT_LIST_HEAD(&wqe->all_list);
@@ -1113,12 +1145,6 @@ bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
 	return refcount_inc_not_zero(&wq->use_refs);
 }
 
-static bool io_wq_worker_wake(struct io_worker *worker, void *data)
-{
-	wake_up_process(worker->task);
-	return false;
-}
-
 static void __io_wq_destroy(struct io_wq *wq)
 {
 	int node;

fs/io-wq.h

@@ -87,7 +87,11 @@ struct io_wq_work {
 	struct io_wq_work_node list;
 	struct files_struct *files;
 	struct mm_struct *mm;
+#ifdef CONFIG_BLK_CGROUP
+	struct cgroup_subsys_state *blkcg_css;
+#endif
 	const struct cred *creds;
+	struct nsproxy *nsproxy;
 	struct fs_struct *fs;
 	unsigned long fsize;
 	unsigned flags;

include/linux/fs.h

@@ -302,17 +302,20 @@ enum rw_hint {
 	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
 };
 
-#define IOCB_EVENTFD		(1 << 0)
-#define IOCB_APPEND		(1 << 1)
-#define IOCB_DIRECT		(1 << 2)
-#define IOCB_HIPRI		(1 << 3)
-#define IOCB_DSYNC		(1 << 4)
-#define IOCB_SYNC		(1 << 5)
-#define IOCB_WRITE		(1 << 6)
-#define IOCB_NOWAIT		(1 << 7)
+/* Match RWF_* bits to IOCB bits */
+#define IOCB_HIPRI		(__force int) RWF_HIPRI
+#define IOCB_DSYNC		(__force int) RWF_DSYNC
+#define IOCB_SYNC		(__force int) RWF_SYNC
+#define IOCB_NOWAIT		(__force int) RWF_NOWAIT
+#define IOCB_APPEND		(__force int) RWF_APPEND
+
+/* non-RWF related bits - start at 16 */
+#define IOCB_EVENTFD		(1 << 16)
+#define IOCB_DIRECT		(1 << 17)
+#define IOCB_WRITE		(1 << 18)
 /* iocb->ki_waitq is valid */
-#define IOCB_WAITQ		(1 << 8)
-#define IOCB_NOIO		(1 << 9)
+#define IOCB_WAITQ		(1 << 19)
+#define IOCB_NOIO		(1 << 20)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -3302,6 +3305,9 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 {
 	int kiocb_flags = 0;
 
+	/* make sure there's no overlap between RWF and private IOCB flags */
+	BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD);
+
 	if (!flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
@@ -3310,16 +3316,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
+		kiocb_flags |= IOCB_NOIO;
 	}
-	if (flags & RWF_HIPRI)
-		kiocb_flags |= IOCB_HIPRI;
-	if (flags & RWF_DSYNC)
-		kiocb_flags |= IOCB_DSYNC;
+	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
-		kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC);
-	if (flags & RWF_APPEND)
-		kiocb_flags |= IOCB_APPEND;
+		kiocb_flags |= IOCB_DSYNC;
 
 	ki->ki_flags |= kiocb_flags;
 	return 0;
@@ -3499,15 +3500,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
 extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
 			   int advice);
 
-#if defined(CONFIG_IO_URING)
-extern struct sock *io_uring_get_socket(struct file *file);
-#else
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
-#endif
-
 int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags,
 			     unsigned int flags);
 

include/linux/io_uring.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_H
+#define _LINUX_IO_URING_H
+
+#include <linux/sched.h>
+#include <linux/xarray.h>
+#include <linux/percpu-refcount.h>
+
+struct io_uring_task {
+	/* submission side */
+	struct xarray		xa;
+	struct wait_queue_head	wait;
+	struct file		*last;
+	atomic_long_t		req_issue;
+
+	/* completion side */
+	bool			in_idle ____cacheline_aligned_in_smp;
+	atomic_long_t		req_complete;
+};
+
+#if defined(CONFIG_IO_URING)
+struct sock *io_uring_get_socket(struct file *file);
+void __io_uring_task_cancel(void);
+void __io_uring_files_cancel(struct files_struct *files);
+void __io_uring_free(struct task_struct *tsk);
+
+static inline void io_uring_task_cancel(void)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_task_cancel();
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_files_cancel(files);
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+	if (tsk->io_uring)
+		__io_uring_free(tsk);
+}
+#else
+static inline struct sock *io_uring_get_socket(struct file *file)
+{
+	return NULL;
+}
+static inline void io_uring_task_cancel(void)
+{
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+}
+#endif
+
+#endif

include/linux/sched.h

@@ -63,6 +63,7 @@ struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct io_uring_task;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -935,6 +936,10 @@ struct task_struct {
 	/* Open file information: */
 	struct files_struct		*files;
 
+#ifdef CONFIG_IO_URING
+	struct io_uring_task		*io_uring;
+#endif
+
 	/* Namespaces: */
 	struct nsproxy			*nsproxy;
 

include/uapi/linux/io_uring.h

@@ -95,6 +95,7 @@ enum {
 #define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
 #define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
 #define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
+#define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
 
 enum {
 	IORING_OP_NOP,
@@ -224,6 +225,7 @@ struct io_cqring_offsets {
  */
 #define IORING_ENTER_GETEVENTS	(1U << 0)
 #define IORING_ENTER_SQ_WAKEUP	(1U << 1)
+#define IORING_ENTER_SQ_WAIT	(1U << 2)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
@@ -255,17 +257,24 @@ struct io_uring_params {
 /*
  * io_uring_register(2) opcodes and arguments
  */
-#define IORING_REGISTER_BUFFERS		0
-#define IORING_UNREGISTER_BUFFERS	1
-#define IORING_REGISTER_FILES		2
-#define IORING_UNREGISTER_FILES		3
-#define IORING_REGISTER_EVENTFD		4
-#define IORING_UNREGISTER_EVENTFD	5
-#define IORING_REGISTER_FILES_UPDATE	6
-#define IORING_REGISTER_EVENTFD_ASYNC	7
-#define IORING_REGISTER_PROBE		8
-#define IORING_REGISTER_PERSONALITY	9
-#define IORING_UNREGISTER_PERSONALITY	10
+enum {
+	IORING_REGISTER_BUFFERS			= 0,
+	IORING_UNREGISTER_BUFFERS		= 1,
+	IORING_REGISTER_FILES			= 2,
+	IORING_UNREGISTER_FILES			= 3,
+	IORING_REGISTER_EVENTFD			= 4,
+	IORING_UNREGISTER_EVENTFD		= 5,
+	IORING_REGISTER_FILES_UPDATE		= 6,
+	IORING_REGISTER_EVENTFD_ASYNC		= 7,
+	IORING_REGISTER_PROBE			= 8,
+	IORING_REGISTER_PERSONALITY		= 9,
+	IORING_UNREGISTER_PERSONALITY		= 10,
+	IORING_REGISTER_RESTRICTIONS		= 11,
+	IORING_REGISTER_ENABLE_RINGS		= 12,
+
+	/* this goes last */
+	IORING_REGISTER_LAST
+};
 
 struct io_uring_files_update {
 	__u32 offset;
@@ -290,4 +299,34 @@ struct io_uring_probe {
 	struct io_uring_probe_op ops[0];
 };
 
+struct io_uring_restriction {
+	__u16 opcode;
+	union {
+		__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
+		__u8 sqe_op;      /* IORING_RESTRICTION_SQE_OP */
+		__u8 sqe_flags;   /* IORING_RESTRICTION_SQE_FLAGS_* */
+	};
+	__u8 resv;
+	__u32 resv2[3];
+};
+
+/*
+ * io_uring_restriction->opcode values
+ */
+enum {
+	/* Allow an io_uring_register(2) opcode */
+	IORING_RESTRICTION_REGISTER_OP		= 0,
+
+	/* Allow an sqe opcode */
+	IORING_RESTRICTION_SQE_OP		= 1,
+
+	/* Allow sqe flags */
+	IORING_RESTRICTION_SQE_FLAGS_ALLOWED	= 2,
+
+	/* Require sqe flags (these flags must be set on each submission) */
+	IORING_RESTRICTION_SQE_FLAGS_REQUIRED	= 3,
+
+	IORING_RESTRICTION_LAST
+};
+
 #endif

init/init_task.c

@@ -114,6 +114,9 @@ struct task_struct init_task
 	.thread		= INIT_THREAD,
 	.fs		= &init_fs,
 	.files		= &init_files,
+#ifdef CONFIG_IO_URING
+	.io_uring	= NULL,
+#endif
 	.signal		= &init_signals,
 	.sighand	= &init_sighand,
 	.nsproxy	= &init_nsproxy,

kernel/fork.c

@@ -95,6 +95,7 @@
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
 #include <linux/scs.h>
+#include <linux/io_uring.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -728,6 +729,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
@@ -1983,6 +1985,10 @@ static __latent_entropy struct task_struct *copy_process(
 	p->vtime.state = VTIME_INACTIVE;
 #endif
 
+#ifdef CONFIG_IO_URING
+	p->io_uring = NULL;
+#endif
+
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif

net/unix/scm.c

@@ -8,6 +8,7 @@
 #include <net/af_unix.h>
 #include <net/scm.h>
 #include <linux/init.h>
+#include <linux/io_uring.h>
 
 #include "scm.h"