diff options
Diffstat (limited to 'io_uring')
| -rw-r--r-- | io_uring/Makefile | 6 | ||||
| -rw-r--r-- | io_uring/io-wq.c | 1414 | ||||
| -rw-r--r-- | io_uring/io-wq.h | 161 | ||||
| -rw-r--r-- | io_uring/io_uring.c | 11159 |
4 files changed, 12740 insertions, 0 deletions
diff --git a/io_uring/Makefile b/io_uring/Makefile new file mode 100644 index 000000000..3680425df --- /dev/null +++ b/io_uring/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for io_uring + +obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c new file mode 100644 index 000000000..fe8594a03 --- /dev/null +++ b/io_uring/io-wq.c @@ -0,0 +1,1414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/sched/signal.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/rculist_nulls.h> +#include <linux/cpu.h> +#include <linux/tracehook.h> +#include <uapi/linux/io_uring.h> + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +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_BOUND = 8, /* is doing bounded work */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ +}; + +enum { + IO_ACCT_STALLED_BIT = 0, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct list_head all_list; + struct task_struct *task; + struct io_wqe *wqe; + + struct io_wq_work *cur_work; + spinlock_t lock; + + struct completion ref_done; + + unsigned long create_state; + struct callback_head create_work; + int create_index; + + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#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; + int index; + atomic_t nr_running; + struct io_wq_work_list work_list; + unsigned long flags; +}; + +enum { + IO_WQ_ACCT_BOUND, + IO_WQ_ACCT_UNBOUND, + IO_WQ_ACCT_NR, +}; + +/* + * Per-node worker thread pool + */ +struct io_wqe { + raw_spinlock_t lock; + struct io_wqe_acct acct[2]; + + int node; + + struct hlist_nulls_head free_list; + struct list_head all_list; + + struct wait_queue_entry wait; + + struct io_wq *wq; + struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; + + cpumask_var_t cpu_mask; +}; + +/* + * Per io_wq state + */ +struct io_wq { + unsigned long state; + + free_work_fn *free_work; + io_wq_work_fn *do_work; + + struct io_wq_hash *hash; + + atomic_t worker_refs; + struct completion worker_done; + + struct hlist_node cpuhp_node; + + struct task_struct *task; + + struct io_wqe *wqes[]; +}; + +static enum cpuhp_state io_wq_online; + +struct io_cb_cancel_data { + work_cancel_fn *fn; + void *data; + int nr_running; + int nr_pending; + bool cancel_all; +}; + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void io_wqe_dec_running(struct io_worker *worker); +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match); +static void create_worker_cb(struct callback_head *cb); +static void io_wq_cancel_tw_create(struct io_wq *wq); + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); +} + +static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound) +{ + return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND]; +} + +static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, + struct io_wq_work *work) +{ + return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND)); +} + +static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker) +{ + return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND); +} + +static void io_worker_ref_put(struct io_wq *wq) +{ + if (atomic_dec_and_test(&wq->worker_refs)) + complete(&wq->worker_done); +} + +bool io_wq_worker_stopped(void) +{ + struct io_worker *worker = current->pf_io_worker; + + if (WARN_ON_ONCE(!io_wq_current_is_worker())) + return true; + + return test_bit(IO_WQ_BIT_EXIT, &worker->wqe->wq->state); +} + +static void io_worker_cancel_cb(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_task_worker_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker == data; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + while (1) { + struct callback_head *cb = task_work_cancel_match(wq->task, + io_task_worker_match, worker); + + if (!cb) + break; + io_worker_cancel_cb(worker); + } + + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); + wait_for_completion(&worker->ref_done); + + raw_spin_lock(&wqe->lock); + if (worker->flags & IO_WORKER_F_FREE) + hlist_nulls_del_rcu(&worker->nulls_node); + list_del_rcu(&worker->all_list); + preempt_disable(); + io_wqe_dec_running(worker); + worker->flags = 0; + current->flags &= ~PF_IO_WORKER; + preempt_enable(); + raw_spin_unlock(&wqe->lock); + + kfree_rcu(worker, rcu); + io_worker_ref_put(wqe->wq); + do_exit(0); +} + +static inline bool io_acct_run_queue(struct io_wqe_acct *acct) +{ + if (!wq_list_empty(&acct->work_list) && + !test_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + return true; + return false; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe, + struct io_wqe_acct *acct) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + /* + * Iterate free_list and see if we can find an idle worker to + * activate. If a given worker is on the free_list but in the process + * of exiting, keep trying. + */ + hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) { + if (!io_worker_get(worker)) + continue; + if (io_wqe_get_acct(worker) != acct) { + io_worker_release(worker); + continue; + } + if (wake_up_process(worker->task)) { + io_worker_release(worker); + return true; + } + io_worker_release(worker); + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, create one. + */ +static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) +{ + /* + * Most likely an attempt to queue unbounded work on an io_wq that + * wasn't setup with any unbounded workers. + */ + if (unlikely(!acct->max_workers)) + pr_warn_once("io-wq is not configured for unbound workers"); + + raw_spin_lock(&wqe->lock); + if (acct->nr_workers >= acct->max_workers) { + raw_spin_unlock(&wqe->lock); + return true; + } + acct->nr_workers++; + raw_spin_unlock(&wqe->lock); + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + return create_io_worker(wqe->wq, wqe, acct->index); +} + +static void io_wqe_inc_running(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_inc(&acct->nr_running); +} + +static void create_worker_cb(struct callback_head *cb) +{ + struct io_worker *worker; + struct io_wq *wq; + struct io_wqe *wqe; + struct io_wqe_acct *acct; + bool do_create = false; + + worker = container_of(cb, struct io_worker, create_work); + wqe = worker->wqe; + wq = wqe->wq; + acct = &wqe->acct[worker->create_index]; + raw_spin_lock(&wqe->lock); + if (acct->nr_workers < acct->max_workers) { + acct->nr_workers++; + do_create = true; + } + raw_spin_unlock(&wqe->lock); + if (do_create) { + create_io_worker(wq, wqe, worker->create_index); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_queue_worker_create(struct io_worker *worker, + struct io_wqe_acct *acct, + task_work_func_t func) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + /* raced with exit, just ignore create call */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + goto fail; + if (!io_worker_get(worker)) + goto fail; + /* + * create_state manages ownership of create_work/index. We should + * only need one entry per worker, as the worker going to sleep + * will trigger the condition, and waking will clear it once it + * runs the task_work. + */ + if (test_bit(0, &worker->create_state) || + test_and_set_bit_lock(0, &worker->create_state)) + goto fail_release; + + atomic_inc(&wq->worker_refs); + init_task_work(&worker->create_work, func); + worker->create_index = acct->index; + if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { + /* + * EXIT may have been set after checking it above, check after + * adding the task_work and remove any creation item if it is + * now set. wq exit does that too, but we can have added this + * work item after we canceled in io_wq_exit_workers(). + */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + io_wq_cancel_tw_create(wq); + io_worker_ref_put(wq); + return true; + } + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); +fail_release: + io_worker_release(worker); +fail: + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + return false; +} + +static void io_wqe_dec_running(struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + + if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + raw_spin_unlock(&wqe->lock); + io_queue_worker_create(worker, acct, create_worker_cb); + raw_spin_lock(&wqe->lock); + } +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + } +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + } +} + +static inline unsigned int io_get_work_hash(struct io_wq_work *work) +{ + return work->flags >> IO_WQ_HASH_SHIFT; +} + +static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) +{ + struct io_wq *wq = wqe->wq; + bool ret = false; + + spin_lock_irq(&wq->hash->wait.lock); + if (list_empty(&wqe->wait.entry)) { + __add_wait_queue(&wq->hash->wait, &wqe->wait); + if (!test_bit(hash, &wq->hash->map)) { + __set_current_state(TASK_RUNNING); + list_del_init(&wqe->wait.entry); + ret = true; + } + } + spin_unlock_irq(&wq->hash->wait.lock); + return ret; +} + +static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, + struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work, *tail; + unsigned int stall_hash = -1U; + struct io_wqe *wqe = worker->wqe; + + wq_list_for_each(node, prev, &acct->work_list) { + unsigned int hash; + + work = container_of(node, struct io_wq_work, list); + + /* not hashed, can run anytime */ + if (!io_wq_is_hashed(work)) { + wq_list_del(&acct->work_list, node, prev); + return work; + } + + hash = io_get_work_hash(work); + /* all items with this hash lie in [work, tail] */ + tail = wqe->hash_tail[hash]; + + /* hashed, can run if not already running */ + if (!test_and_set_bit(hash, &wqe->wq->hash->map)) { + wqe->hash_tail[hash] = NULL; + wq_list_cut(&acct->work_list, &tail->list, prev); + return work; + } + if (stall_hash == -1U) + stall_hash = hash; + /* fast forward to a next hash, for-each will fix up @prev */ + node = &tail->list; + } + + if (stall_hash != -1U) { + bool unstalled; + + /* + * Set this before dropping the lock to avoid racing with new + * work being added and clearing the stalled bit. + */ + set_bit(IO_ACCT_STALLED_BIT, &acct->flags); + raw_spin_unlock(&wqe->lock); + unstalled = io_wait_on_hash(wqe, stall_hash); + raw_spin_lock(&wqe->lock); + if (unstalled) { + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + if (wq_has_sleeper(&wqe->wq->hash->wait)) + wake_up(&wqe->wq->hash->wait); + } + } + + return NULL; +} + +static bool io_flush_signals(void) +{ + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { + __set_current_state(TASK_RUNNING); + tracehook_notify_signal(); + return true; + } + return false; +} + +static void io_assign_current_work(struct io_worker *worker, + struct io_wq_work *work) +{ + if (work) { + io_flush_signals(); + cond_resched(); + } + + spin_lock(&worker->lock); + worker->cur_work = work; + spin_unlock(&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_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); + + do { + struct io_wq_work *work; +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. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(acct, worker); + if (work) + __io_worker_busy(wqe, worker, work); + + raw_spin_unlock(&wqe->lock); + if (!work) + break; + io_assign_current_work(worker, work); + __set_current_state(TASK_RUNNING); + + /* handle a whole dependent link */ + do { + struct io_wq_work *next_hashed, *linked; + unsigned int hash = io_get_work_hash(work); + + next_hashed = wq_next_work(work); + + if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + io_assign_current_work(worker, NULL); + + linked = wq->free_work(work); + work = next_hashed; + if (!work && linked && !io_wq_is_hashed(linked)) { + work = linked; + linked = NULL; + } + io_assign_current_work(worker, work); + if (linked) + io_wqe_enqueue(wqe, linked); + + if (hash != -1U && !next_hashed) { + /* serialize hash clear with wake_up() */ + spin_lock_irq(&wq->hash->wait.lock); + clear_bit(hash, &wq->hash->map); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + spin_unlock_irq(&wq->hash->wait.lock); + if (wq_has_sleeper(&wq->hash->wait)) + wake_up(&wq->hash->wait); + raw_spin_lock(&wqe->lock); + /* skip unnecessary unlock-lock wqe->lock */ + if (!work) + goto get_next; + raw_spin_unlock(&wqe->lock); + } + } while (work); + + raw_spin_lock(&wqe->lock); + } while (1); +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool last_timeout = false; + char buf[TASK_COMM_LEN]; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + + snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); + set_task_comm(current, buf); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + long ret; + + set_current_state(TASK_INTERRUPTIBLE); +loop: + raw_spin_lock(&wqe->lock); + if (io_acct_run_queue(acct)) { + io_worker_handle_work(worker); + goto loop; + } + /* timed out, exit unless we're the last worker */ + if (last_timeout && acct->nr_workers > 1) { + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + __set_current_state(TASK_RUNNING); + break; + } + last_timeout = false; + __io_worker_idle(wqe, worker); + raw_spin_unlock(&wqe->lock); + if (io_flush_signals()) + continue; + ret = schedule_timeout(WORKER_IDLE_TIMEOUT); + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; + break; + } + last_timeout = !ret; + } + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + raw_spin_lock(&wqe->lock); + io_worker_handle_work(worker); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + io_wqe_inc_running(worker); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or create a new one. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + raw_spin_lock(&worker->wqe->lock); + io_wqe_dec_running(worker); + raw_spin_unlock(&worker->wqe->lock); +} + +static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, + struct task_struct *tsk) +{ + tsk->pf_io_worker = worker; + worker->task = tsk; + set_cpus_allowed_ptr(tsk, wqe->cpu_mask); + tsk->flags |= PF_NO_SETAFFINITY; + + raw_spin_lock(&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; + raw_spin_unlock(&wqe->lock); + wake_up_new_task(tsk); +} + +static bool io_wq_work_match_all(struct io_wq_work *work, void *data) +{ + return true; +} + +static inline bool io_should_retry_thread(long err) +{ + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + + switch (err) { + case -EAGAIN: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + return true; + default: + return false; + } +} + +static void create_worker_cont(struct callback_head *cb) +{ + struct io_worker *worker; + struct task_struct *tsk; + struct io_wqe *wqe; + + worker = container_of(cb, struct io_worker, create_work); + clear_bit_unlock(0, &worker->create_state); + wqe = worker->wqe; + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + io_worker_release(worker); + return; + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + + while (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wqe->wq); + kfree(worker); + return; + } + + /* re-create attempts grab a new worker ref, drop the existing one */ + io_worker_release(worker); + schedule_work(&worker->work); +} + +static void io_workqueue_create(struct work_struct *work) +{ + struct io_worker *worker = container_of(work, struct io_worker, work); + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + if (!io_queue_worker_create(worker, acct, create_worker_cont)) + kfree(worker); +} + +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_worker *worker; + struct task_struct *tsk; + + __set_current_state(TASK_RUNNING); + + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) { +fail: + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wq); + return false; + } + + refcount_set(&worker->ref, 1); + worker->wqe = wqe; + spin_lock_init(&worker->lock); + init_completion(&worker->ref_done); + + if (index == IO_WQ_ACCT_BOUND) + worker->flags |= IO_WORKER_F_BOUND; + + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + kfree(worker); + goto fail; + } else { + INIT_WORK(&worker->work, io_workqueue_create); + schedule_work(&worker->work); + } + + return true; +} + +/* + * 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) +{ + set_notify_signal(worker->task); + wake_up_process(worker->task); + return false; +} + +static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) +{ + struct io_wq *wq = wqe->wq; + + do { + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + work = wq->free_work(work); + } while (work); +} + +static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash; + struct io_wq_work *tail; + + if (!io_wq_is_hashed(work)) { +append: + wq_list_add_tail(&work->list, &acct->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, &acct->work_list); +} + +static bool io_wq_work_match_item(struct io_wq_work *work, void *data) +{ + return work == data; +} + +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); + unsigned work_flags = work->flags; + bool do_create; + + /* + * If io-wq is exiting for this task, or if the request has explicitly + * been marked as one that should not get executed, cancel it here. + */ + if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) || + (work->flags & IO_WQ_WORK_CANCEL)) { + io_run_cancel(work, wqe); + return; + } + + raw_spin_lock(&wqe->lock); + io_wqe_insert_work(wqe, work); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + + rcu_read_lock(); + do_create = !io_wqe_activate_free_worker(wqe, acct); + rcu_read_unlock(); + + raw_spin_unlock(&wqe->lock); + + if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) || + !atomic_read(&acct->nr_running))) { + bool did_create; + + did_create = io_wqe_create_worker(wqe, acct); + if (likely(did_create)) + return; + + raw_spin_lock(&wqe->lock); + /* fatal condition, failed to create the first worker */ + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; + + if (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + } +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * 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_hash_work(struct io_wq_work *work, void *val) +{ + unsigned int bit; + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_cb_cancel_data *match = data; + + /* + * Hold the lock to avoid ->cur_work going out of scope, caller + * may dereference the passed in work. + */ + spin_lock(&worker->lock); + if (worker->cur_work && + match->fn(worker->cur_work, match->data)) { + set_notify_signal(worker->task); + match->nr_running++; + } + spin_unlock(&worker->lock); + + return match->nr_running && !match->cancel_all; +} + +static inline void io_wqe_remove_pending(struct io_wqe *wqe, + struct io_wq_work *work, + struct io_wq_work_node *prev) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash = io_get_work_hash(work); + struct io_wq_work *prev_work = NULL; + + if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { + if (prev) + prev_work = container_of(prev, struct io_wq_work, list); + if (prev_work && io_get_work_hash(prev_work) == hash) + wqe->hash_tail[hash] = prev_work; + else + wqe->hash_tail[hash] = NULL; + } + wq_list_del(&acct->work_list, &work->list, prev); +} + +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match) + __releases(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work; + + wq_list_for_each(node, prev, &acct->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); + raw_spin_unlock(&wqe->lock); + io_run_cancel(work, wqe); + match->nr_pending++; + /* not safe to continue after unlock */ + return true; + } + + return false; +} + +static void io_wqe_cancel_pending_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + int i; +retry: + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = io_get_acct(wqe, i == 0); + + if (io_acct_cancel_pending_work(wqe, acct, match)) { + if (match->cancel_all) + goto retry; + return; + } + } + raw_spin_unlock(&wqe->lock); +} + +static void io_wqe_cancel_running_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + rcu_read_lock(); + io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); + rcu_read_unlock(); +} + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data, bool cancel_all) +{ + struct io_cb_cancel_data match = { + .fn = cancel, + .data = data, + .cancel_all = cancel_all, + }; + int node; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_pending_work(wqe, &match); + if (match.nr_pending && !match.cancel_all) + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempt to signal cancellation. The + * completion will run normally in this case. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_running_work(wqe, &match); + if (match.nr_running && !match.cancel_all) + return IO_WQ_CANCEL_RUNNING; + } + + if (match.nr_running) + return IO_WQ_CANCEL_RUNNING; + if (match.nr_pending) + return IO_WQ_CANCEL_OK; + return IO_WQ_CANCEL_NOTFOUND; +} + +static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode, + int sync, void *key) +{ + struct io_wqe *wqe = container_of(wait, struct io_wqe, wait); + int i; + + list_del_init(&wait->entry); + + rcu_read_lock(); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + io_wqe_activate_free_worker(wqe, acct); + } + rcu_read_unlock(); + return 1; +} + +struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) +{ + int ret, node, i; + struct io_wq *wq; + + if (WARN_ON_ONCE(!data->free_work || !data->do_work)) + return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(!bounded)) + return ERR_PTR(-EINVAL); + + wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); + if (ret) + goto err_wq; + + refcount_inc(&data->hash->refs); + wq->hash = data->hash; + wq->free_work = data->free_work; + wq->do_work = data->do_work; + + ret = -ENOMEM; + for_each_node(node) { + struct io_wqe *wqe; + int alloc_node = node; + + if (!node_online(alloc_node)) + alloc_node = NUMA_NO_NODE; + wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); + if (!wqe) + goto err; + wq->wqes[node] = wqe; + if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL)) + goto err; + cpumask_copy(wqe->cpu_mask, cpumask_of_node(node)); + wqe->node = alloc_node; + wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; + wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = + task_rlimit(current, RLIMIT_NPROC); + INIT_LIST_HEAD(&wqe->wait.entry); + wqe->wait.func = io_wqe_hash_wake; + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + acct->index = i; + atomic_set(&acct->nr_running, 0); + INIT_WQ_LIST(&acct->work_list); + } + wqe->wq = wq; + raw_spin_lock_init(&wqe->lock); + INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); + INIT_LIST_HEAD(&wqe->all_list); + } + + wq->task = get_task_struct(data->task); + atomic_set(&wq->worker_refs, 1); + init_completion(&wq->worker_done); + return wq; +err: + io_wq_put_hash(data->hash); + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + for_each_node(node) { + if (!wq->wqes[node]) + continue; + free_cpumask_var(wq->wqes[node]->cpu_mask); + kfree(wq->wqes[node]); + } +err_wq: + kfree(wq); + return ERR_PTR(ret); +} + +static bool io_task_work_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb && cb->func != create_worker_cont) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker->wqe->wq == data; +} + +void io_wq_exit_start(struct io_wq *wq) +{ + set_bit(IO_WQ_BIT_EXIT, &wq->state); +} + +static void io_wq_cancel_tw_create(struct io_wq *wq) +{ + struct callback_head *cb; + + while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { + struct io_worker *worker; + + worker = container_of(cb, struct io_worker, create_work); + io_worker_cancel_cb(worker); + /* + * Only the worker continuation helper has worker allocated and + * hence needs freeing. + */ + if (cb->func == create_worker_cont) + kfree(worker); + } +} + +static void io_wq_exit_workers(struct io_wq *wq) +{ + int node; + + if (!wq->task) + return; + + io_wq_cancel_tw_create(wq); + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); + } + rcu_read_unlock(); + io_worker_ref_put(wq); + wait_for_completion(&wq->worker_done); + + for_each_node(node) { + spin_lock_irq(&wq->hash->wait.lock); + list_del_init(&wq->wqes[node]->wait.entry); + spin_unlock_irq(&wq->hash->wait.lock); + } + put_task_struct(wq->task); + wq->task = NULL; +} + +static void io_wq_destroy(struct io_wq *wq) +{ + int node; + + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + io_wqe_cancel_pending_work(wqe, &match); + free_cpumask_var(wqe->cpu_mask); + kfree(wqe); + } + io_wq_put_hash(wq->hash); + kfree(wq); +} + +void io_wq_put_and_exit(struct io_wq *wq) +{ + WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); + + io_wq_exit_workers(wq); + io_wq_destroy(wq); +} + +struct online_data { + unsigned int cpu; + bool online; +}; + +static bool io_wq_worker_affinity(struct io_worker *worker, void *data) +{ + struct online_data *od = data; + + if (od->online) + cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask); + else + cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask); + return false; +} + +static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online) +{ + struct online_data od = { + .cpu = cpu, + .online = online + }; + int i; + + rcu_read_lock(); + for_each_node(i) + io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od); + rcu_read_unlock(); + return 0; +} + +static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, true); +} + +static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, false); +} + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask) +{ + int i; + + rcu_read_lock(); + for_each_node(i) { + struct io_wqe *wqe = wq->wqes[i]; + + if (mask) + cpumask_copy(wqe->cpu_mask, mask); + else + cpumask_copy(wqe->cpu_mask, cpumask_of_node(i)); + } + rcu_read_unlock(); + return 0; +} + +/* + * Set max number of unbounded workers, returns old value. If new_count is 0, + * then just return the old value. + */ +int io_wq_max_workers(struct io_wq *wq, int *new_count) +{ + int prev[IO_WQ_ACCT_NR]; + bool first_node = true; + int i, node; + + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + + for (i = 0; i < 2; i++) { + if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) + new_count[i] = task_rlimit(current, RLIMIT_NPROC); + } + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + prev[i] = 0; + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_wqe_acct *acct; + + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + acct = &wqe->acct[i]; + if (first_node) + prev[i] = max_t(int, acct->max_workers, prev[i]); + if (new_count[i]) + acct->max_workers = new_count[i]; + } + raw_spin_unlock(&wqe->lock); + first_node = false; + } + rcu_read_unlock(); + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + new_count[i] = prev[i]; + + return 0; +} + +static __init int io_wq_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", + io_wq_cpu_online, io_wq_cpu_offline); + if (ret < 0) + return ret; + io_wq_online = ret; + return 0; +} +subsys_initcall(io_wq_init); diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h new file mode 100644 index 000000000..48721cbd5 --- /dev/null +++ b/io_uring/io-wq.h @@ -0,0 +1,161 @@ +#ifndef INTERNAL_IO_WQ_H +#define INTERNAL_IO_WQ_H + +#include <linux/refcount.h> + +struct io_wq; + +enum { + IO_WQ_WORK_CANCEL = 1, + IO_WQ_WORK_HASHED = 2, + IO_WQ_WORK_UNBOUND = 4, + IO_WQ_WORK_CONCURRENT = 16, + + IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ +}; + +enum io_wq_cancel { + IO_WQ_CANCEL_OK, /* cancelled before started */ + IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ + IO_WQ_CANCEL_NOTFOUND, /* work not found */ +}; + +struct io_wq_work_node { + struct io_wq_work_node *next; +}; + +struct io_wq_work_list { + struct io_wq_work_node *first; + 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) +{ + node->next = NULL; + if (!list->first) { + list->last = node; + WRITE_ONCE(list->first, node); + } else { + list->last->next = node; + list->last = 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) +{ + /* 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; + 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) \ + for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) + +#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) +#define INIT_WQ_LIST(list) do { \ + (list)->first = NULL; \ + (list)->last = NULL; \ +} while (0) + +struct io_wq_work { + struct io_wq_work_node list; + unsigned flags; +}; + +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 struct io_wq_work *(free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work *); + +struct io_wq_hash { + refcount_t refs; + unsigned long map; + struct wait_queue_head wait; +}; + +static inline void io_wq_put_hash(struct io_wq_hash *hash) +{ + if (refcount_dec_and_test(&hash->refs)) + kfree(hash); +} + +struct io_wq_data { + struct io_wq_hash *hash; + struct task_struct *task; + io_wq_work_fn *do_work; + free_work_fn *free_work; +}; + +struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); +void io_wq_exit_start(struct io_wq *wq); +void io_wq_put_and_exit(struct io_wq *wq); + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); +void io_wq_hash_work(struct io_wq_work *work, void *val); + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_max_workers(struct io_wq *wq, int *new_count); +bool io_wq_worker_stopped(void); + +static inline bool io_wq_is_hashed(struct io_wq_work *work) +{ + return work->flags & IO_WQ_WORK_HASHED; +} + +typedef bool (work_cancel_fn)(struct io_wq_work *, void *); + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data, bool cancel_all); + +#if defined(CONFIG_IO_WQ) +extern void io_wq_worker_sleeping(struct task_struct *); +extern void io_wq_worker_running(struct task_struct *); +#else +static inline void io_wq_worker_sleeping(struct task_struct *tsk) +{ +} +static inline void io_wq_worker_running(struct task_struct *tsk) +{ +} +#endif + +static inline bool io_wq_current_is_worker(void) +{ + return in_task() && (current->flags & PF_IO_WORKER) && + current->pf_io_worker; +} +#endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c new file mode 100644 index 000000000..936abc6ee --- /dev/null +++ b/io_uring/io_uring.c @@ -0,0 +1,11159 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared application/kernel submission and completion ring pairs, for + * supporting fast/efficient IO. + * + * A note on the read/write ordering memory barriers that are matched between + * the application and kernel side. + * + * After the application reads the CQ ring tail, it must use an + * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses + * before writing the tail (using smp_load_acquire to read the tail will + * do). It also needs a smp_mb() before updating CQ head (ordering the + * entry load(s) with the head store), pairing with an implicit barrier + * through a control-dependency in io_get_cqe (smp_store_release to + * store head will do). Failure to do so could lead to reading invalid + * CQ entries. + * + * Likewise, the application must use an appropriate smp_wmb() before + * writing the SQ tail (ordering SQ entry stores with the tail store), + * which pairs with smp_load_acquire in io_get_sqring (smp_store_release + * to store the tail will do). And it needs a barrier ordering the SQ + * head load before writing new SQ entries (smp_load_acquire to read + * head will do). + * + * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application + * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* + * updating the SQ tail; a full memory barrier smp_mb() is needed + * between. + * + * Also see the examples in the liburing library: + * + * git://git.kernel.dk/liburing + * + * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens + * from data shared between the kernel and application. This is done both + * for ordering purposes, but also to ensure that once a value is loaded from + * data that the application could potentially modify, it remains stable. + * + * Copyright (C) 2018-2019 Jens Axboe + * Copyright (c) 2018-2019 Christoph Hellwig + */ +#include <linux/kernel.h> +#include <linux/init.h> +#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> + +#include <linux/sched/signal.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <linux/bvec.h> +#include <linux/net.h> +#include <net/sock.h> +#include <net/af_unix.h> +#include <net/scm.h> +#include <linux/anon_inodes.h> +#include <linux/sched/mm.h> +#include <linux/uaccess.h> +#include <linux/nospec.h> +#include <linux/sizes.h> +#include <linux/hugetlb.h> +#include <linux/highmem.h> +#include <linux/namei.h> +#include <linux/fsnotify.h> +#include <linux/fadvise.h> +#include <linux/eventpoll.h> +#include <linux/splice.h> +#include <linux/task_work.h> +#include <linux/pagemap.h> +#include <linux/io_uring.h> +#include <linux/tracehook.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/io_uring.h> + +#include <uapi/linux/io_uring.h> + +#include "../fs/internal.h" +#include "io-wq.h" + +#define IORING_MAX_ENTRIES 32768 +#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 + +/* only define max */ +#define IORING_MAX_FIXED_FILES (1U << 15) +#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ + IORING_REGISTER_LAST + IORING_OP_LAST) + +#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) +#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) +#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) + +#define IORING_MAX_REG_BUFFERS (1U << 14) + +#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ + IOSQE_BUFFER_SELECT) +#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) + +#define IO_TCTX_REFS_CACHE_NR (1U << 10) + +struct io_uring { + u32 head ____cacheline_aligned_in_smp; + u32 tail ____cacheline_aligned_in_smp; +}; + +/* + * This data is shared with the application through the mmap at offsets + * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ +struct io_rings { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head of the sq ring and the tail of the cq ring, + * and the application controls tail of the sq ring and the head of the + * cq ring. + */ + struct io_uring sq, cq; + /* + * Bitmasks to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ + u32 sq_ring_mask, cq_ring_mask; + /* Ring sizes (constant, power of 2) */ + u32 sq_ring_entries, cq_ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ + u32 sq_dropped; + /* + * Runtime SQ flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ + u32 sq_flags; + /* + * Runtime CQ flags + * + * Written by the application, shouldn't be modified by the + * kernel. + */ + u32 cq_flags; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending than there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ + u32 cq_overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ + struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; +}; + +enum io_uring_cmd_flags { + IO_URING_F_NONBLOCK = 1, + IO_URING_F_COMPLETE_DEFER = 2, +}; + +struct io_mapped_ubuf { + u64 ubuf; + u64 ubuf_end; + unsigned int nr_bvecs; + unsigned long acct_pages; + struct bio_vec bvec[]; +}; + +struct io_ring_ctx; + +struct io_overflow_cqe { + struct io_uring_cqe cqe; + struct list_head list; +}; + +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + +struct io_rsrc_put { + struct list_head list; + u64 tag; + union { + void *rsrc; + struct file *file; + struct io_mapped_ubuf *buf; + }; +}; + +struct io_file_table { + struct io_fixed_file *files; +}; + +struct io_rsrc_node { + struct percpu_ref refs; + struct list_head node; + struct list_head rsrc_list; + struct io_rsrc_data *rsrc_data; + struct llist_node llist; + bool done; +}; + +typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); + +struct io_rsrc_data { + struct io_ring_ctx *ctx; + + u64 **tags; + unsigned int nr; + rsrc_put_fn *do_put; + atomic_t refs; + struct completion done; + bool quiesce; +}; + +struct io_buffer { + struct list_head list; + __u64 addr; + __u32 len; + __u16 bid; +}; + +struct io_restriction { + DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); + DECLARE_BITMAP(sqe_op, IORING_OP_LAST); + u8 sqe_flags_allowed; + u8 sqe_flags_required; + bool registered; +}; + +enum { + IO_SQ_THREAD_SHOULD_STOP = 0, + IO_SQ_THREAD_SHOULD_PARK, +}; + +struct io_sq_data { + refcount_t refs; + atomic_t park_pending; + struct mutex lock; + + /* ctx's that are using this sqd */ + struct list_head ctx_list; + + struct task_struct *thread; + struct wait_queue_head wait; + + unsigned sq_thread_idle; + int sq_cpu; + pid_t task_pid; + pid_t task_tgid; + + unsigned long state; + struct completion exited; +}; + +#define IO_COMPL_BATCH 32 +#define IO_REQ_CACHE_SIZE 32 +#define IO_REQ_ALLOC_BATCH 8 + +struct io_submit_link { + struct io_kiocb *head; + struct io_kiocb *last; +}; + +struct io_submit_state { + struct blk_plug plug; + struct io_submit_link link; + + /* + * io_kiocb alloc cache + */ + void *reqs[IO_REQ_CACHE_SIZE]; + unsigned int free_reqs; + + bool plug_started; + + /* + * Batch completion logic + */ + struct io_kiocb *compl_reqs[IO_COMPL_BATCH]; + unsigned int compl_nr; + /* inline/task_work completion list, under ->uring_lock */ + struct list_head free_list; + + unsigned int ios_left; +}; + +struct io_ring_ctx { + /* const or read-mostly hot data */ + struct { + struct percpu_ref refs; + + struct io_rings *rings; + unsigned int flags; + unsigned int compat: 1; + unsigned int drain_next: 1; + unsigned int eventfd_async: 1; + unsigned int restricted: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; + + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ + u32 *sq_array; + struct io_uring_sqe *sq_sqes; + unsigned cached_sq_head; + unsigned sq_entries; + struct list_head defer_list; + + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; + struct list_head timeout_list; + struct list_head ltimeout_list; + struct list_head cq_overflow_list; + struct xarray io_buffers; + struct xarray personalities; + u32 pers_next; + unsigned sq_thread_idle; + } ____cacheline_aligned_in_smp; + + /* IRQ completion list, under ->completion_lock */ + struct list_head locked_free_list; + unsigned int locked_free_nr; + + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ + struct io_sq_data *sq_data; /* if using sq thread polling */ + + struct wait_queue_head sqo_sq_wait; + struct list_head sqd_list; + + unsigned long check_cq_overflow; + + struct { + unsigned cached_cq_tail; + unsigned cq_entries; + struct eventfd_ctx *cq_ev_fd; + struct wait_queue_head poll_wait; + struct wait_queue_head cq_wait; + unsigned cq_extra; + atomic_t cq_timeouts; + unsigned cq_last_tm_flush; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t completion_lock; + + spinlock_t timeout_lock; + + /* + * ->iopoll_list is protected by the ctx->uring_lock for + * io_uring instances that don't use IORING_SETUP_SQPOLL. + * For SQPOLL, only the single threaded io_sq_thread() will + * manipulate the list, hence no extra locking is needed there. + */ + struct list_head iopoll_list; + struct hlist_head *cancel_hash; + unsigned cancel_hash_bits; + bool poll_multi_queue; + } ____cacheline_aligned_in_smp; + + struct io_restriction restrictions; + + /* slow path rsrc auxilary data, used by update/register */ + struct { + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + }; + + /* Keep this last, we don't need it for the fast path */ + struct { + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct llist_head fallback_llist; + struct delayed_work fallback_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + u32 iowq_limits[2]; + bool iowq_limits_set; + }; +}; + +struct io_uring_task { + /* submission side */ + int cached_refs; + struct xarray xa; + struct wait_queue_head wait; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct percpu_counter inflight; + atomic_t inflight_tracked; + atomic_t in_idle; + + spinlock_t task_lock; + struct io_wq_work_list task_list; + struct callback_head task_work; + bool task_running; +}; + +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in <linux/fs.h> + */ +struct io_poll_iocb { + struct file *file; + struct wait_queue_head *head; + __poll_t events; + int retries; + struct wait_queue_entry wait; +}; + +struct io_poll_update { + struct file *file; + u64 old_user_data; + u64 new_user_data; + __poll_t events; + bool update_events; + bool update_user_data; +}; + +struct io_close { + struct file *file; + int fd; + u32 file_slot; +}; + +struct io_timeout_data { + struct io_kiocb *req; + struct hrtimer timer; + struct timespec64 ts; + enum hrtimer_mode mode; + u32 flags; +}; + +struct io_accept { + struct file *file; + struct sockaddr __user *addr; + int __user *addr_len; + int flags; + u32 file_slot; + unsigned long nofile; +}; + +struct io_sync { + struct file *file; + loff_t len; + loff_t off; + int flags; + int mode; +}; + +struct io_cancel { + struct file *file; + u64 addr; +}; + +struct io_timeout { + struct file *file; + u32 off; + u32 target_seq; + struct list_head list; + /* head of the link, used by linked timeouts only */ + struct io_kiocb *head; + /* for linked completions */ + struct io_kiocb *prev; +}; + +struct io_timeout_rem { + struct file *file; + u64 addr; + + /* timeout update */ + struct timespec64 ts; + u32 flags; + bool ltimeout; +}; + +struct io_rw { + /* NOTE: kiocb has the file as the first member, so don't do it here */ + struct kiocb kiocb; + u64 addr; + u64 len; +}; + +struct io_connect { + struct file *file; + struct sockaddr __user *addr; + int addr_len; +}; + +struct io_sr_msg { + struct file *file; + union { + struct compat_msghdr __user *umsg_compat; + struct user_msghdr __user *umsg; + void __user *buf; + }; + int msg_flags; + int bgid; + size_t len; + size_t done_io; + struct io_buffer *kbuf; + void __user *msg_control; +}; + +struct io_open { + struct file *file; + int dfd; + u32 file_slot; + struct filename *filename; + struct open_how how; + unsigned long nofile; +}; + +struct io_rsrc_update { + struct file *file; + u64 arg; + u32 nr_args; + u32 offset; +}; + +struct io_fadvise { + struct file *file; + u64 offset; + u32 len; + u32 advice; +}; + +struct io_madvise { + struct file *file; + u64 addr; + u32 len; + u32 advice; +}; + +struct io_epoll { + struct file *file; + int epfd; + int op; + int fd; + struct epoll_event event; +}; + +struct io_splice { + struct file *file_out; + loff_t off_out; + loff_t off_in; + u64 len; + int splice_fd_in; + unsigned int flags; +}; + +struct io_provide_buf { + struct file *file; + __u64 addr; + __u32 len; + __u32 bgid; + __u16 nbufs; + __u16 bid; +}; + +struct io_statx { + struct file *file; + int dfd; + unsigned int mask; + unsigned int flags; + const char __user *filename; + struct statx __user *buffer; +}; + +struct io_shutdown { + struct file *file; + int how; +}; + +struct io_rename { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +struct io_unlink { + struct file *file; + int dfd; + int flags; + struct filename *filename; +}; + +struct io_mkdir { + struct file *file; + int dfd; + umode_t mode; + struct filename *filename; +}; + +struct io_symlink { + struct file *file; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; +}; + +struct io_hardlink { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +struct io_completion { + struct file *file; + u32 cflags; +}; + +struct io_async_connect { + struct sockaddr_storage address; +}; + +struct io_async_msghdr { + struct iovec fast_iov[UIO_FASTIOV]; + /* points to an allocated iov, if NULL we use fast_iov instead */ + struct iovec *free_iov; + struct sockaddr __user *uaddr; + struct msghdr msg; + struct sockaddr_storage addr; +}; + +struct io_async_rw { + struct iovec fast_iov[UIO_FASTIOV]; + const struct iovec *free_iovec; + struct iov_iter iter; + struct iov_iter_state iter_state; + size_t bytes_done; + struct wait_page_queue wpq; +}; + +enum { + REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, + REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, + REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, + REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, + REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, + REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, + + /* first byte is taken by user flags, shift it to not overlap */ + REQ_F_FAIL_BIT = 8, + REQ_F_INFLIGHT_BIT, + REQ_F_CUR_POS_BIT, + REQ_F_NOWAIT_BIT, + REQ_F_LINK_TIMEOUT_BIT, + REQ_F_NEED_CLEANUP_BIT, + REQ_F_POLLED_BIT, + REQ_F_BUFFER_SELECTED_BIT, + REQ_F_COMPLETE_INLINE_BIT, + REQ_F_REISSUE_BIT, + REQ_F_CREDS_BIT, + REQ_F_REFCOUNT_BIT, + REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_PARTIAL_IO_BIT, + /* keep async read/write and isreg together and in order */ + REQ_F_NOWAIT_READ_BIT, + REQ_F_NOWAIT_WRITE_BIT, + REQ_F_ISREG_BIT, + + /* not a real bit, just to check we're not overflowing the space */ + __REQ_F_LAST_BIT, +}; + +enum { + /* ctx owns file */ + REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), + /* drain existing IO first */ + REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), + /* linked sqes */ + REQ_F_LINK = BIT(REQ_F_LINK_BIT), + /* doesn't sever on completion < 0 */ + REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), + /* IOSQE_ASYNC */ + REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), + /* IOSQE_BUFFER_SELECT */ + REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + + /* fail rest of links */ + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + /* on inflight list, should be cancelled and waited on exit reliably */ + REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), + /* read/write uses file position */ + REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), + /* must not punt to workers */ + REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), + /* has or had linked timeout */ + REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), + /* needs cleanup */ + REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_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), + /* completion is deferred through io_comp_state */ + REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + /* supports async reads */ + REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), + /* supports async writes */ + REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + /* skip refcounting if not set */ + REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + /* there is a linked timeout that has to be armed */ + REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), +}; + +struct async_poll { + struct io_poll_iocb poll; + struct io_poll_iocb *double_poll; +}; + +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); + +struct io_task_work { + union { + struct io_wq_work_node node; + struct llist_node fallback_node; + }; + io_req_tw_func_t func; +}; + +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + +/* + * NOTE! Each of the iocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'ki_filp' in this struct. + */ +struct io_kiocb { + union { + struct file *file; + struct io_rw rw; + struct io_poll_iocb poll; + struct io_poll_update poll_update; + struct io_accept accept; + struct io_sync sync; + struct io_cancel cancel; + struct io_timeout timeout; + struct io_timeout_rem timeout_rem; + struct io_connect connect; + struct io_sr_msg sr_msg; + struct io_open open; + struct io_close close; + struct io_rsrc_update rsrc_update; + struct io_fadvise fadvise; + struct io_madvise madvise; + struct io_epoll epoll; + struct io_splice splice; + struct io_provide_buf pbuf; + struct io_statx statx; + struct io_shutdown shutdown; + struct io_rename rename; + struct io_unlink unlink; + struct io_mkdir mkdir; + struct io_symlink symlink; + struct io_hardlink hardlink; + /* use only after cleaning per-op data, see io_clean_op() */ + struct io_completion compl; + }; + + /* opcode allocated if it needs to store data for async defer */ + void *async_data; + u8 opcode; + /* polled IO has completed */ + u8 iopoll_completed; + + u16 buf_index; + u32 result; + + struct io_ring_ctx *ctx; + unsigned int flags; + atomic_t refs; + struct task_struct *task; + u64 user_data; + + struct io_kiocb *link; + struct percpu_ref *fixed_rsrc_refs; + + /* used with ctx->iopoll_list with reads/writes */ + struct list_head inflight_entry; + struct io_task_work io_task_work; + /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ + struct hlist_node hash_node; + struct async_poll *apoll; + struct io_wq_work work; + const struct cred *creds; + + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + atomic_t poll_refs; +}; + +struct io_tctx_node { + struct list_head ctx_node; + struct task_struct *task; + struct io_ring_ctx *ctx; +}; + +struct io_defer_entry { + struct list_head list; + struct io_kiocb *req; + u32 seq; +}; + +struct io_op_def { + /* needs req->file assigned */ + unsigned needs_file : 1; + /* hash wq insertion if file is a regular file */ + unsigned hash_reg_file : 1; + /* unbound wq insertion if file is a non-regular file */ + unsigned unbound_nonreg_file : 1; + /* opcode is not supported by this kernel */ + unsigned not_supported : 1; + /* set if opcode supports polled "wait" */ + unsigned pollin : 1; + unsigned pollout : 1; + /* op supports buffer selection */ + unsigned buffer_select : 1; + /* do prep async if is going to be punted */ + unsigned needs_async_setup : 1; + /* should block plug */ + unsigned plug : 1; + /* size of async data needed, if any */ + unsigned short async_size; +}; + +static const struct io_op_def io_op_defs[] = { + [IORING_OP_NOP] = {}, + [IORING_OP_READV] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .needs_async_setup = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_WRITEV] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .needs_async_setup = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_FSYNC] = { + .needs_file = 1, + }, + [IORING_OP_READ_FIXED] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_WRITE_FIXED] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_POLL_ADD] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_POLL_REMOVE] = {}, + [IORING_OP_SYNC_FILE_RANGE] = { + .needs_file = 1, + }, + [IORING_OP_SENDMSG] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .needs_async_setup = 1, + .async_size = sizeof(struct io_async_msghdr), + }, + [IORING_OP_RECVMSG] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .needs_async_setup = 1, + .async_size = sizeof(struct io_async_msghdr), + }, + [IORING_OP_TIMEOUT] = { + .async_size = sizeof(struct io_timeout_data), + }, + [IORING_OP_TIMEOUT_REMOVE] = { + /* used by timeout updates' prep() */ + }, + [IORING_OP_ACCEPT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + }, + [IORING_OP_ASYNC_CANCEL] = {}, + [IORING_OP_LINK_TIMEOUT] = { + .async_size = sizeof(struct io_timeout_data), + }, + [IORING_OP_CONNECT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .needs_async_setup = 1, + .async_size = sizeof(struct io_async_connect), + }, + [IORING_OP_FALLOCATE] = { + .needs_file = 1, + }, + [IORING_OP_OPENAT] = {}, + [IORING_OP_CLOSE] = {}, + [IORING_OP_FILES_UPDATE] = {}, + [IORING_OP_STATX] = {}, + [IORING_OP_READ] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_WRITE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .plug = 1, + .async_size = sizeof(struct io_async_rw), + }, + [IORING_OP_FADVISE] = { + .needs_file = 1, + }, + [IORING_OP_MADVISE] = {}, + [IORING_OP_SEND] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + }, + [IORING_OP_RECV] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + }, + [IORING_OP_OPENAT2] = { + }, + [IORING_OP_EPOLL_CTL] = { + .unbound_nonreg_file = 1, + }, + [IORING_OP_SPLICE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_PROVIDE_BUFFERS] = {}, + [IORING_OP_REMOVE_BUFFERS] = {}, + [IORING_OP_TEE] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_SHUTDOWN] = { + .needs_file = 1, + }, + [IORING_OP_RENAMEAT] = {}, + [IORING_OP_UNLINKAT] = {}, +}; + +/* requests with any of those set should undergo io_disarm_next() */ +#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) + +static bool io_disarm_next(struct io_kiocb *req); +static void io_uring_del_tctx_node(unsigned long index); +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all); +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); + +static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); + +static void io_put_req(struct io_kiocb *req); +static void io_put_req_deferred(struct io_kiocb *req); +static void io_dismantle_req(struct io_kiocb *req); +static void io_queue_linked_timeout(struct io_kiocb *req); +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args); +static void io_clean_op(struct io_kiocb *req); +static struct file *io_file_get(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags); +static void __io_queue_sqe(struct io_kiocb *req); +static void io_rsrc_put_work(struct work_struct *work); + +static void io_req_task_queue(struct io_kiocb *req); +static void io_submit_flush_completions(struct io_ring_ctx *ctx); +static int io_req_prep_async(struct io_kiocb *req); + +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index); +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); + +static struct kmem_cache *req_cachep; + +static const struct file_operations io_uring_fops; + +struct sock *io_uring_get_socket(struct file *file) +{ +#if defined(CONFIG_UNIX) + if (file->f_op == &io_uring_fops) { + struct io_ring_ctx *ctx = file->private_data; + + return ctx->ring_sock->sk; + } +#endif + return NULL; +} +EXPORT_SYMBOL(io_uring_get_socket); + +static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) +{ + if (!*locked) { + mutex_lock(&ctx->uring_lock); + *locked = true; + } +} + +#define io_for_each_link(pos, head) \ + for (pos = (head); pos; pos = pos->link) + +/* + * Shamelessly stolen from the mm implementation of page reference checking, + * see commit f958d7b528b1 for details. + */ +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + return atomic_inc_not_zero(&req->refs); +} + +static inline bool req_ref_put_and_test(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_REFCOUNT))) + return true; + + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->refs); +} + +static inline void req_ref_get(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + atomic_inc(&req->refs); +} + +static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) +{ + if (!(req->flags & REQ_F_REFCOUNT)) { + req->flags |= REQ_F_REFCOUNT; + atomic_set(&req->refs, nr); + } +} + +static inline void io_req_set_refcount(struct io_kiocb *req) +{ + __io_req_set_refcount(req, 1); +} + +static inline void io_req_set_rsrc_node(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!req->fixed_rsrc_refs) { + req->fixed_rsrc_refs = &ctx->rsrc_node->refs; + percpu_ref_get(req->fixed_rsrc_refs); + } +} + +static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) +{ + bool got = percpu_ref_tryget(ref); + + /* already at zero, wait for ->release() */ + if (!got) + wait_for_completion(compl); + percpu_ref_resurrect(ref); + if (got) + percpu_ref_put(ref); +} + +static bool io_match_task(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_kiocb *req; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +static bool io_match_linked(struct io_kiocb *head) +{ + struct io_kiocb *req; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +/* + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. + */ +static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) +{ + bool matched; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); + } + return matched; +} + +static inline void req_set_fail(struct io_kiocb *req) +{ + req->flags |= REQ_F_FAIL; +} + +static inline void req_fail_link_node(struct io_kiocb *req, int res) +{ + req_set_fail(req); + req->result = res; +} + +static void io_ring_ctx_ref_free(struct percpu_ref *ref) +{ + struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); + + complete(&ctx->ref_comp); +} + +static inline bool io_is_timeout_noseq(struct io_kiocb *req) +{ + return !req->timeout.off; +} + +static void io_fallback_req_func(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, + fallback_work.work); + struct llist_node *node = llist_del_all(&ctx->fallback_llist); + struct io_kiocb *req, *tmp; + bool locked = false; + + percpu_ref_get(&ctx->refs); + llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node) + req->io_task_work.func(req, &locked); + + if (locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + } + percpu_ref_put(&ctx->refs); + +} + +static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) +{ + struct io_ring_ctx *ctx; + int hash_bits; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + /* + * Use 5 bits less than the max cq entries, that should give us around + * 32 entries per hash list if totally full and uniformly spread. + */ + hash_bits = ilog2(p->cq_entries); + hash_bits -= 5; + if (hash_bits <= 0) + hash_bits = 1; + ctx->cancel_hash_bits = hash_bits; + ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head), + GFP_KERNEL); + if (!ctx->cancel_hash) + goto err; + __hash_init(ctx->cancel_hash, 1U << hash_bits); + + ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); + if (!ctx->dummy_ubuf) + goto err; + /* set invalid range, so io_import_fixed() fails meeting it */ + ctx->dummy_ubuf->ubuf = -1UL; + + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) + goto err; + + ctx->flags = p->flags; + init_waitqueue_head(&ctx->sqo_sq_wait); + INIT_LIST_HEAD(&ctx->sqd_list); + init_waitqueue_head(&ctx->poll_wait); + INIT_LIST_HEAD(&ctx->cq_overflow_list); + init_completion(&ctx->ref_comp); + xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); + xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); + mutex_init(&ctx->uring_lock); + init_waitqueue_head(&ctx->cq_wait); + spin_lock_init(&ctx->completion_lock); + spin_lock_init(&ctx->timeout_lock); + INIT_LIST_HEAD(&ctx->iopoll_list); + INIT_LIST_HEAD(&ctx->defer_list); + INIT_LIST_HEAD(&ctx->timeout_list); + INIT_LIST_HEAD(&ctx->ltimeout_list); + spin_lock_init(&ctx->rsrc_ref_lock); + INIT_LIST_HEAD(&ctx->rsrc_ref_list); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); + INIT_LIST_HEAD(&ctx->tctx_list); + INIT_LIST_HEAD(&ctx->submit_state.free_list); + INIT_LIST_HEAD(&ctx->locked_free_list); + INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); + return ctx; +err: + kfree(ctx->dummy_ubuf); + kfree(ctx->cancel_hash); + kfree(ctx); + return NULL; +} + +static void io_account_cq_overflow(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); + ctx->cq_extra--; +} + +static bool req_need_defer(struct io_kiocb *req, u32 seq) +{ + if (unlikely(req->flags & REQ_F_IO_DRAIN)) { + struct io_ring_ctx *ctx = req->ctx; + + return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; + } + + return false; +} + +#define FFS_ASYNC_READ 0x1UL +#define FFS_ASYNC_WRITE 0x2UL +#ifdef CONFIG_64BIT +#define FFS_ISREG 0x4UL +#else +#define FFS_ISREG 0x0UL +#endif +#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG) + +static inline bool io_req_ffs_set(struct io_kiocb *req) +{ + return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE); +} + +static void io_req_track_inflight(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + atomic_inc(&req->task->io_uring->inflight_tracked); + } +} + +static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) +{ + if (WARN_ON_ONCE(!req->link)) + return NULL; + + req->flags &= ~REQ_F_ARM_LTIMEOUT; + req->flags |= REQ_F_LINK_TIMEOUT; + + /* linked timeouts should have two refs once prep'ed */ + io_req_set_refcount(req); + __io_req_set_refcount(req->link, 2); + return req->link; +} + +static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) + return NULL; + return __io_prep_linked_timeout(req); +} + +static void io_prep_async_work(struct io_kiocb *req) +{ + const struct io_op_def *def = &io_op_defs[req->opcode]; + struct io_ring_ctx *ctx = req->ctx; + + if (!(req->flags & REQ_F_CREDS)) { + req->flags |= REQ_F_CREDS; + req->creds = get_current_cred(); + } + + req->work.list.next = NULL; + req->work.flags = 0; + if (req->flags & REQ_F_FORCE_ASYNC) + req->work.flags |= IO_WQ_WORK_CONCURRENT; + + if (req->flags & REQ_F_ISREG) { + if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) + io_wq_hash_work(&req->work, file_inode(req->file)); + } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { + if (def->unbound_nonreg_file) + req->work.flags |= IO_WQ_WORK_UNBOUND; + } +} + +static void io_prep_async_link(struct io_kiocb *req) +{ + struct io_kiocb *cur; + + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + io_for_each_link(cur, req) + io_prep_async_work(cur); + spin_unlock_irq(&ctx->timeout_lock); + } else { + io_for_each_link(cur, req) + io_prep_async_work(cur); + } +} + +static void io_queue_async_work(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *link = io_prep_linked_timeout(req); + struct io_uring_task *tctx = req->task->io_uring; + + /* must not take the lock, NULL it as a precaution */ + locked = NULL; + + BUG_ON(!tctx); + BUG_ON(!tctx->io_wq); + + /* init ->work of the whole link before punting */ + io_prep_async_link(req); + + /* + * Not expected to happen, but if we do have a bug where this _can_ + * happen, catch it here and ensure the request is marked as + * canceled. That will make io-wq go through the usual work cancel + * procedure rather than attempt to run this request (or create a new + * worker for it). + */ + if (WARN_ON_ONCE(!same_thread_group(req->task, current))) + req->work.flags |= IO_WQ_WORK_CANCEL; + + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, + &req->work, req->flags); + io_wq_enqueue(tctx->io_wq, &req->work); + if (link) + io_queue_linked_timeout(link); +} + +static void io_kill_timeout(struct io_kiocb *req, int status) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_timeout_data *io = req->async_data; + + if (hrtimer_try_to_cancel(&io->timer) != -1) { + if (status) + req_set_fail(req); + atomic_set(&req->ctx->cq_timeouts, + atomic_read(&req->ctx->cq_timeouts) + 1); + list_del_init(&req->timeout.list); + io_fill_cqe_req(req, status, 0); + io_put_req_deferred(req); + } +} + +static void io_queue_deferred(struct io_ring_ctx *ctx) +{ + lockdep_assert_held(&ctx->completion_lock); + + while (!list_empty(&ctx->defer_list)) { + struct io_defer_entry *de = list_first_entry(&ctx->defer_list, + struct io_defer_entry, list); + + if (req_need_defer(de->req, de->seq)) + break; + list_del_init(&de->list); + io_req_task_queue(de->req); + kfree(de); + } +} + +static void io_flush_timeouts(struct io_ring_ctx *ctx) + __must_hold(&ctx->completion_lock) +{ + u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; + + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + u32 events_needed, events_got; + + if (io_is_timeout_noseq(req)) + break; + + /* + * Since seq can easily wrap around over time, subtract + * the last seq at which timeouts were flushed before comparing. + * Assuming not more than 2^31-1 events have happened since, + * these subtractions won't have wrapped, so we can check if + * target is in [last_seq, current_seq] by comparing the two. + */ + events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; + events_got = seq - ctx->cq_last_tm_flush; + if (events_got < events_needed) + break; + + io_kill_timeout(req, 0); + } + ctx->cq_last_tm_flush = seq; + spin_unlock_irq(&ctx->timeout_lock); +} + +static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) +{ + if (ctx->off_timeout_used) + io_flush_timeouts(ctx); + if (ctx->drain_active) + io_queue_deferred(ctx); +} + +static inline bool io_commit_needs_flush(struct io_ring_ctx *ctx) +{ + return ctx->off_timeout_used || ctx->drain_active; +} + +static inline void __io_commit_cqring(struct io_ring_ctx *ctx) +{ + /* order cqe stores with ring update */ + smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); +} + +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + if (unlikely(io_commit_needs_flush(ctx))) + __io_commit_cqring_flush(ctx); + __io_commit_cqring(ctx); +} + +static inline bool io_sqring_full(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; +} + +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); +} + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + unsigned tail, mask = ctx->cq_entries - 1; + + /* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ + if (__io_cqring_events(ctx) == ctx->cq_entries) + return NULL; + + tail = ctx->cached_cq_tail++; + return &rings->cqes[tail & mask]; +} + +static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) +{ + if (likely(!ctx->cq_ev_fd)) + return false; + if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + return false; + return !ctx->eventfd_async || io_wq_current_is_worker(); +} + +/* + * This should only get called when at least one event has been posted. + * Some applications rely on the eventfd notification count only changing + * IFF a new CQE has been added to the CQ ring. There's no depedency on + * 1:1 relationship between how many times this function is called (and + * hence the eventfd count) and number of CQEs posted to the CQ ring. + */ +static void io_cqring_ev_posted(struct io_ring_ctx *ctx) +{ + /* + * wake_up_all() may seem excessive, but io_wake_function() and + * io_should_wake() handle the termination of the loop and only + * wake as many waiters as we need to. + */ + if (wq_has_sleeper(&ctx->cq_wait)) + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); + if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + if (io_should_trigger_evfd(ctx)) + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); + if (waitqueue_active(&ctx->poll_wait)) + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); +} + +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) +{ + /* see waitqueue_active() comment */ + smp_mb(); + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (waitqueue_active(&ctx->cq_wait)) + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); + } + if (io_should_trigger_evfd(ctx)) + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); + if (waitqueue_active(&ctx->poll_wait)) + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); +} + +/* Returns true if there are no backlogged entries after the flush */ +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) +{ + bool all_flushed, posted; + + if (!force && __io_cqring_events(ctx) == ctx->cq_entries) + return false; + + posted = false; + spin_lock(&ctx->completion_lock); + while (!list_empty(&ctx->cq_overflow_list)) { + struct io_uring_cqe *cqe = io_get_cqe(ctx); + struct io_overflow_cqe *ocqe; + + if (!cqe && !force) + break; + ocqe = list_first_entry(&ctx->cq_overflow_list, + struct io_overflow_cqe, list); + if (cqe) + memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); + else + io_account_cq_overflow(ctx); + + posted = true; + list_del(&ocqe->list); + kfree(ocqe); + } + + all_flushed = list_empty(&ctx->cq_overflow_list); + if (all_flushed) { + clear_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); + } + + if (posted) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + return all_flushed; +} + +static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) +{ + bool ret = true; + + if (test_bit(0, &ctx->check_cq_overflow)) { + /* iopoll syncs against uring_lock, not completion_lock */ + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); + ret = __io_cqring_overflow_flush(ctx, false); + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); + } + + return ret; +} + +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + struct io_uring_task *tctx = task->io_uring; + + if (likely(task == current)) { + tctx->cached_refs += nr; + } else { + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); + } +} + +static void io_task_refs_refill(struct io_uring_task *tctx) +{ + unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; + + percpu_counter_add(&tctx->inflight, refill); + refcount_add(refill, ¤t->usage); + tctx->cached_refs += refill; +} + +static inline void io_get_task_refs(int nr) +{ + struct io_uring_task *tctx = current->io_uring; + + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); +} + +static __cold void io_uring_drop_tctx_refs(struct task_struct *task) +{ + struct io_uring_task *tctx = task->io_uring; + unsigned int refs = tctx->cached_refs; + + if (refs) { + tctx->cached_refs = 0; + percpu_counter_sub(&tctx->inflight, refs); + put_task_struct_many(task, refs); + } +} + +static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + struct io_overflow_cqe *ocqe; + + ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); + if (!ocqe) { + /* + * If we're in ring overflow flush mode, or in task cancel mode, + * or cannot allocate an overflow entry, then we need to drop it + * on the floor. + */ + io_account_cq_overflow(ctx); + return false; + } + if (list_empty(&ctx->cq_overflow_list)) { + set_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + + } + ocqe->cqe.user_data = user_data; + ocqe->cqe.res = res; + ocqe->cqe.flags = cflags; + list_add_tail(&ocqe->list, &ctx->cq_overflow_list); + return true; +} + +static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + struct io_uring_cqe *cqe; + + trace_io_uring_complete(ctx, user_data, res, cflags); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, cflags); + return true; + } + return io_cqring_event_overflow(ctx, user_data, res, cflags); +} + +static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) +{ + __io_fill_cqe(req->ctx, req->user_data, res, cflags); +} + +static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + ctx->cq_extra++; + return __io_fill_cqe(ctx, user_data, res, cflags); +} + +static void io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) +{ + struct io_ring_ctx *ctx = req->ctx; + + spin_lock(&ctx->completion_lock); + __io_fill_cqe(ctx, req->user_data, res, cflags); + /* + * If we're the last reference to this request, add to our locked + * free_list cache. + */ + if (req_ref_put_and_test(req)) { + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + if (req->flags & IO_DISARM_MASK) + io_disarm_next(req); + if (req->link) { + io_req_task_queue(req->link); + req->link = NULL; + } + } + io_dismantle_req(req); + io_put_task(req->task, 1); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; + } else { + if (!percpu_ref_tryget(&ctx->refs)) + req = NULL; + } + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + + if (req) { + io_cqring_ev_posted(ctx); + percpu_ref_put(&ctx->refs); + } +} + +static inline bool io_req_needs_clean(struct io_kiocb *req) +{ + return req->flags & IO_REQ_CLEAN_FLAGS; +} + +static inline void io_req_complete_state(struct io_kiocb *req, s32 res, + u32 cflags) +{ + if (io_req_needs_clean(req)) + io_clean_op(req); + req->result = res; + req->compl.cflags = cflags; + req->flags |= REQ_F_COMPLETE_INLINE; +} + +static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, + s32 res, u32 cflags) +{ + if (issue_flags & IO_URING_F_COMPLETE_DEFER) + io_req_complete_state(req, res, cflags); + else + io_req_complete_post(req, res, cflags); +} + +static inline void io_req_complete(struct io_kiocb *req, s32 res) +{ + __io_req_complete(req, 0, res, 0); +} + +static void io_req_complete_failed(struct io_kiocb *req, s32 res) +{ + req_set_fail(req); + io_req_complete_post(req, res, 0); +} + +static void io_req_complete_fail_submit(struct io_kiocb *req) +{ + /* + * We don't submit, fail them all, for that replace hardlinks with + * normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->result); +} + +/* + * Don't initialise the fields below on every allocation, but do that in + * advance and keep them valid across allocations. + */ +static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + req->ctx = ctx; + req->link = NULL; + req->async_data = NULL; + /* not necessary, but safer to zero */ + req->result = 0; +} + +static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, + struct io_submit_state *state) +{ + spin_lock(&ctx->completion_lock); + list_splice_init(&ctx->locked_free_list, &state->free_list); + ctx->locked_free_nr = 0; + spin_unlock(&ctx->completion_lock); +} + +/* Returns true IFF there are requests in the cache */ +static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + int nr; + + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) + io_flush_cached_locked_reqs(ctx, state); + + nr = state->free_reqs; + while (!list_empty(&state->free_list)) { + struct io_kiocb *req = list_first_entry(&state->free_list, + struct io_kiocb, inflight_entry); + + list_del(&req->inflight_entry); + state->reqs[nr++] = req; + if (nr == ARRAY_SIZE(state->reqs)) + break; + } + + state->free_reqs = nr; + return nr != 0; +} + +/* + * A request might get retired back into the request caches even before opcode + * handlers and io_issue_sqe() are done with it, e.g. inline completion path. + * Because of that, io_alloc_req() should be called only under ->uring_lock + * and with extra caution to not get a request that is still worked on. + */ +static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state = &ctx->submit_state; + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + int ret, i; + + BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); + + if (likely(state->free_reqs || io_flush_cached_reqs(ctx))) + goto got_req; + + ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, + state->reqs); + + /* + * Bulk alloc is all-or-nothing. If we fail to get a batch, + * retry single alloc to be on the safe side. + */ + if (unlikely(ret <= 0)) { + state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!state->reqs[0]) + return NULL; + ret = 1; + } + + for (i = 0; i < ret; i++) + io_preinit_req(state->reqs[i], ctx); + state->free_reqs = ret; +got_req: + state->free_reqs--; + return state->reqs[state->free_reqs]; +} + +static inline void io_put_file(struct file *file) +{ + if (file) + fput(file); +} + +static void io_dismantle_req(struct io_kiocb *req) +{ + unsigned int flags = req->flags; + + if (io_req_needs_clean(req)) + io_clean_op(req); + if (!(flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); + if (req->async_data) { + kfree(req->async_data); + req->async_data = NULL; + } +} + +static void __io_free_req(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + io_dismantle_req(req); + io_put_task(req->task, 1); + + spin_lock(&ctx->completion_lock); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; + spin_unlock(&ctx->completion_lock); + + percpu_ref_put(&ctx->refs); +} + +static inline void io_remove_next_linked(struct io_kiocb *req) +{ + struct io_kiocb *nxt = req->link; + + req->link = nxt->link; + nxt->link = NULL; +} + +static bool io_kill_linked_timeout(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_kiocb *link = req->link; + + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + struct io_timeout_data *io = link->async_data; + + io_remove_next_linked(req); + link->timeout.head = NULL; + if (hrtimer_try_to_cancel(&io->timer) != -1) { + list_del(&link->timeout.list); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + return true; + } + } + return false; +} + +static void io_fail_links(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + struct io_kiocb *nxt, *link = req->link; + + req->link = NULL; + while (link) { + long res = -ECANCELED; + + if (link->flags & REQ_F_FAIL) + res = link->result; + + nxt = link->link; + link->link = NULL; + + trace_io_uring_fail_link(req, link); + io_fill_cqe_req(link, res, 0); + io_put_req_deferred(link); + link = nxt; + } +} + +static bool io_disarm_next(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + bool posted = false; + + if (req->flags & REQ_F_ARM_LTIMEOUT) { + struct io_kiocb *link = req->link; + + req->flags &= ~REQ_F_ARM_LTIMEOUT; + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + io_remove_next_linked(req); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + posted = true; + } + } else if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + posted = io_kill_linked_timeout(req); + spin_unlock_irq(&ctx->timeout_lock); + } + if (unlikely((req->flags & REQ_F_FAIL) && + !(req->flags & REQ_F_HARDLINK))) { + posted |= (req->link != NULL); + io_fail_links(req); + } + return posted; +} + +static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt; + + /* + * If LINK is set, we have dependent requests in this chain. If we + * didn't fail this request, queue the first one up, moving any other + * dependencies to the next request. In case of failure, fail the rest + * of the chain. + */ + if (req->flags & IO_DISARM_MASK) { + struct io_ring_ctx *ctx = req->ctx; + bool posted; + + spin_lock(&ctx->completion_lock); + posted = io_disarm_next(req); + if (posted) + io_commit_cqring(req->ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + } + nxt = req->link; + req->link = NULL; + return nxt; +} + +static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) +{ + if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) + return NULL; + return __io_req_find_next(req); +} + +static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) +{ + if (!ctx) + return; + if (*locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + *locked = false; + } + percpu_ref_put(&ctx->refs); +} + +static void tctx_task_work(struct callback_head *cb) +{ + bool locked = false; + struct io_ring_ctx *ctx = NULL; + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, + task_work); + + while (1) { + struct io_wq_work_node *node; + + if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + + spin_lock_irq(&tctx->task_lock); + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + if (!node) + tctx->task_running = false; + spin_unlock_irq(&tctx->task_lock); + if (!node) + break; + + do { + struct io_wq_work_node *next = node->next; + struct io_kiocb *req = container_of(node, struct io_kiocb, + io_task_work.node); + + if (req->ctx != ctx) { + ctx_flush_and_put(ctx, &locked); + ctx = req->ctx; + /* if not contended, grab and improve batching */ + locked = mutex_trylock(&ctx->uring_lock); + percpu_ref_get(&ctx->refs); + } + req->io_task_work.func(req, &locked); + node = next; + if (unlikely(need_resched())) { + ctx_flush_and_put(ctx, &locked); + ctx = NULL; + cond_resched(); + } + } while (node); + } + + ctx_flush_and_put(ctx, &locked); + + /* relaxed read is enough as only the task itself sets ->in_idle */ + if (unlikely(atomic_read(&tctx->in_idle))) + io_uring_drop_tctx_refs(current); +} + +static void io_req_task_work_add(struct io_kiocb *req) +{ + struct task_struct *tsk = req->task; + struct io_uring_task *tctx = tsk->io_uring; + enum task_work_notify_mode notify; + struct io_wq_work_node *node; + unsigned long flags; + bool running; + + WARN_ON_ONCE(!tctx); + + spin_lock_irqsave(&tctx->task_lock, flags); + wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + running = tctx->task_running; + if (!running) + tctx->task_running = true; + spin_unlock_irqrestore(&tctx->task_lock, flags); + + /* task_work already pending, we're done */ + if (running) + return; + + /* + * SQPOLL kernel thread doesn't need notification, just a wakeup. For + * all other cases, use TWA_SIGNAL unconditionally to ensure we're + * processing task_work. There's no reliable way to tell if TWA_RESUME + * will do the job. + */ + notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; + if (!task_work_add(tsk, &tctx->task_work, notify)) { + wake_up_process(tsk); + return; + } + + spin_lock_irqsave(&tctx->task_lock, flags); + tctx->task_running = false; + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + spin_unlock_irqrestore(&tctx->task_lock, flags); + + while (node) { + req = container_of(node, struct io_kiocb, io_task_work.node); + node = node->next; + if (llist_add(&req->io_task_work.fallback_node, + &req->ctx->fallback_llist)) + schedule_delayed_work(&req->ctx->fallback_work, 1); + } +} + +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + + /* not needed for normal modes, but SQPOLL depends on it */ + io_tw_lock(ctx, locked); + io_req_complete_failed(req, req->result); +} + +static void io_req_task_submit(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + + io_tw_lock(ctx, locked); + /* req->task == current here, checking PF_EXITING is safe */ + if (likely(!(req->task->flags & PF_EXITING))) + __io_queue_sqe(req); + else + io_req_complete_failed(req, -EFAULT); +} + +static void io_req_task_queue_fail(struct io_kiocb *req, int ret) +{ + req->result = ret; + req->io_task_work.func = io_req_task_cancel; + io_req_task_work_add(req); +} + +static void io_req_task_queue(struct io_kiocb *req) +{ + req->io_task_work.func = io_req_task_submit; + io_req_task_work_add(req); +} + +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_async_work; + io_req_task_work_add(req); +} + +static inline void io_queue_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt = io_req_find_next(req); + + if (nxt) + io_req_task_queue(nxt); +} + +static void io_free_req(struct io_kiocb *req) +{ + io_queue_next(req); + __io_free_req(req); +} + +static void io_free_req_work(struct io_kiocb *req, bool *locked) +{ + io_free_req(req); +} + +struct req_batch { + struct task_struct *task; + int task_refs; + int ctx_refs; +}; + +static inline void io_init_req_batch(struct req_batch *rb) +{ + rb->task_refs = 0; + rb->ctx_refs = 0; + rb->task = NULL; +} + +static void io_req_free_batch_finish(struct io_ring_ctx *ctx, + struct req_batch *rb) +{ + if (rb->ctx_refs) + percpu_ref_put_many(&ctx->refs, rb->ctx_refs); + if (rb->task) + io_put_task(rb->task, rb->task_refs); +} + +static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, + struct io_submit_state *state) +{ + io_queue_next(req); + io_dismantle_req(req); + + if (req->task != rb->task) { + if (rb->task) + io_put_task(rb->task, rb->task_refs); + rb->task = req->task; + rb->task_refs = 0; + } + rb->task_refs++; + rb->ctx_refs++; + + if (state->free_reqs != ARRAY_SIZE(state->reqs)) + state->reqs[state->free_reqs++] = req; + else + list_add(&req->inflight_entry, &state->free_list); +} + +static void io_submit_flush_completions(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state = &ctx->submit_state; + int i, nr = state->compl_nr; + struct req_batch rb; + + spin_lock(&ctx->completion_lock); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; + + __io_fill_cqe(ctx, req->user_data, req->result, + req->compl.cflags); + } + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + + io_init_req_batch(&rb); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; + + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); + } + + io_req_free_batch_finish(ctx, &rb); + state->compl_nr = 0; +} + +/* + * Drop reference to request, return next in chain (if there is one) if this + * was the last reference to this request. + */ +static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) +{ + struct io_kiocb *nxt = NULL; + + if (req_ref_put_and_test(req)) { + nxt = io_req_find_next(req); + __io_free_req(req); + } + return nxt; +} + +static inline void io_put_req(struct io_kiocb *req) +{ + if (req_ref_put_and_test(req)) + io_free_req(req); +} + +static inline void io_put_req_deferred(struct io_kiocb *req) +{ + if (req_ref_put_and_test(req)) { + req->io_task_work.func = io_free_req_work; + io_req_task_work_add(req); + } +} + +static unsigned io_cqring_events(struct io_ring_ctx *ctx) +{ + /* See comment at the top of this file */ + smp_rmb(); + return __io_cqring_events(ctx); +} + +static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* make sure SQ entry isn't read before tail */ + return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; +} + +static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf) +{ + unsigned int cflags; + + cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT; + cflags |= IORING_CQE_F_BUFFER; + req->flags &= ~REQ_F_BUFFER_SELECTED; + kfree(kbuf); + return cflags; +} + +static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) +{ + struct io_buffer *kbuf; + + if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + return 0; + kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; + return io_put_kbuf(req, kbuf); +} + +static inline bool io_run_task_work(void) +{ + /* + * PF_IO_WORKER never returns to userspace, so check here if we have + * notify work that needs processing. + */ + if (current->flags & PF_IO_WORKER && + test_thread_flag(TIF_NOTIFY_RESUME)) { + __set_current_state(TASK_RUNNING); + tracehook_notify_resume(NULL); + } + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { + __set_current_state(TASK_RUNNING); + tracehook_notify_signal(); + return true; + } + + return false; +} + +/* + * Find and free completed poll iocbs + */ +static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, + struct list_head *done) +{ + struct req_batch rb; + struct io_kiocb *req; + + /* order with ->result store in io_complete_rw_iopoll() */ + smp_rmb(); + + io_init_req_batch(&rb); + while (!list_empty(done)) { + struct io_uring_cqe *cqe; + unsigned cflags; + + req = list_first_entry(done, struct io_kiocb, inflight_entry); + list_del(&req->inflight_entry); + cflags = io_put_rw_kbuf(req); + (*nr_events)++; + + cqe = io_get_cqe(ctx); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, cflags); + } else { + spin_lock(&ctx->completion_lock); + io_cqring_event_overflow(ctx, req->user_data, + req->result, cflags); + spin_unlock(&ctx->completion_lock); + } + + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); + } + + if (io_commit_needs_flush(ctx)) { + spin_lock(&ctx->completion_lock); + __io_commit_cqring_flush(ctx); + spin_unlock(&ctx->completion_lock); + } + __io_commit_cqring(ctx); + io_cqring_ev_posted_iopoll(ctx); + io_req_free_batch_finish(ctx, &rb); +} + +static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, + long min) +{ + struct io_kiocb *req, *tmp; + LIST_HEAD(done); + bool spin; + + /* + * Only spin for completions if we don't have multiple devices hanging + * off our complete list, and we're under the requested amount. + */ + spin = !ctx->poll_multi_queue && *nr_events < min; + + list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { + struct kiocb *kiocb = &req->rw.kiocb; + int ret; + + /* + * Move completed and retryable entries to our local lists. + * If we find a request that requires polling, break out + * and complete those lists first, if we have entries there. + */ + if (READ_ONCE(req->iopoll_completed)) { + list_move_tail(&req->inflight_entry, &done); + continue; + } + if (!list_empty(&done)) + break; + + ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); + if (unlikely(ret < 0)) + return ret; + else if (ret) + spin = false; + + /* iopoll may have completed current req */ + if (READ_ONCE(req->iopoll_completed)) + list_move_tail(&req->inflight_entry, &done); + } + + if (!list_empty(&done)) + io_iopoll_complete(ctx, nr_events, &done); + + return 0; +} + +/* + * We can't just wait for polled events to come to us, we have to actively + * find and complete them. + */ +static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_IOPOLL)) + return; + + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->iopoll_list)) { + unsigned int nr_events = 0; + + io_do_iopoll(ctx, &nr_events, 0); + + /* let it sleep and repeat later if can't complete a request */ + if (nr_events == 0) + break; + /* + * Ensure we allow local-to-the-cpu processing to take place, + * in this case we need to ensure that we reap all events. + * Also let task_work, etc. to progress by releasing the mutex + */ + if (need_resched()) { + mutex_unlock(&ctx->uring_lock); + cond_resched(); + mutex_lock(&ctx->uring_lock); + } + } + mutex_unlock(&ctx->uring_lock); +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, long min) +{ + unsigned int nr_events = 0; + int ret = 0; + + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); + /* + * Don't enter poll loop if we already have events pending. + * If we do, we can potentially be spinning for commands that + * already triggered a CQE (eg in error). + */ + if (test_bit(0, &ctx->check_cq_overflow)) + __io_cqring_overflow_flush(ctx, false); + if (io_cqring_events(ctx)) + goto out; + do { + /* + * If a submit got punted to a workqueue, we can have the + * application entering polling for a command before it gets + * issued. That app will hold the uring_lock for the duration + * of the poll right here, so we need to take a breather every + * now and then to ensure that the issue has a chance to add + * the poll to the issued list. Otherwise we can spin here + * forever, while the workqueue is stuck trying to acquire the + * very same mutex. + */ + if (list_empty(&ctx->iopoll_list)) { + u32 tail = ctx->cached_cq_tail; + + mutex_unlock(&ctx->uring_lock); + io_run_task_work(); + mutex_lock(&ctx->uring_lock); + + /* some requests don't go through iopoll_list */ + if (tail != ctx->cached_cq_tail || + list_empty(&ctx->iopoll_list)) + break; + } + ret = io_do_iopoll(ctx, &nr_events, min); + + if (task_sigpending(current)) { + ret = -EINTR; + goto out; + } + } while (!ret && nr_events < min && !need_resched()); +out: + mutex_unlock(&ctx->uring_lock); + return ret; +} + +static void kiocb_end_write(struct io_kiocb *req) +{ + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + if (req->flags & REQ_F_ISREG) { + struct super_block *sb = file_inode(req->file)->i_sb; + + __sb_writers_acquired(sb, SB_FREEZE_WRITE); + sb_end_write(sb); + } +} + +#ifdef CONFIG_BLOCK +static bool io_resubmit_prep(struct io_kiocb *req) +{ + struct io_async_rw *rw = req->async_data; + + if (!rw) + return !io_req_prep_async(req); + iov_iter_restore(&rw->iter, &rw->iter_state); + return true; +} + +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + umode_t mode = file_inode(req->file)->i_mode; + struct io_ring_ctx *ctx = req->ctx; + + if (!S_ISBLK(mode) && !S_ISREG(mode)) + return false; + if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && + !(ctx->flags & IORING_SETUP_IOPOLL))) + return false; + /* + * If ref is dying, we might be running poll reap from the exit work. + * Don't attempt to reissue from that path, just let it fail with + * -EAGAIN. + */ + if (percpu_ref_is_dying(&ctx->refs)) + return false; + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; + return true; +} +#else +static bool io_resubmit_prep(struct io_kiocb *req) +{ + return false; +} +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + return false; +} +#endif + +/* + * Trigger the notifications after having done some IO, and finish the write + * accounting, if any. + */ +static void io_req_io_end(struct io_kiocb *req) +{ + struct io_rw *rw = &req->rw; + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } +} + +static bool __io_complete_rw_common(struct io_kiocb *req, long res) +{ + if (res != req->result) { + if ((res == -EAGAIN || res == -EOPNOTSUPP) && + io_rw_should_reissue(req)) { + /* + * Reissue will start accounting again, finish the + * current cycle. + */ + io_req_io_end(req); + req->flags |= REQ_F_REISSUE; + return true; + } + req_set_fail(req); + req->result = res; + } + return false; +} + +static inline int io_fixup_rw_res(struct io_kiocb *req, long res) +{ + struct io_async_rw *io = req->async_data; + + /* add previously done IO, if any */ + if (io && io->bytes_done > 0) { + if (res < 0) + res = io->bytes_done; + else + res += io->bytes_done; + } + return res; +} + +static void io_req_task_complete(struct io_kiocb *req, bool *locked) +{ + unsigned int cflags = io_put_rw_kbuf(req); + int res = req->result; + + if (*locked) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + io_req_complete_state(req, res, cflags); + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + } else { + io_req_complete_post(req, res, cflags); + } +} + +static void io_req_rw_complete(struct io_kiocb *req, bool *locked) +{ + io_req_io_end(req); + io_req_task_complete(req, locked); +} + +static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); + + if (__io_complete_rw_common(req, res)) + return; + req->result = io_fixup_rw_res(req, res); + req->io_task_work.func = io_req_rw_complete; + io_req_task_work_add(req); +} + +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); + + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); + if (unlikely(res != req->result)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return; + } + } + + WRITE_ONCE(req->result, res); + /* order with io_iopoll_complete() checking ->result */ + smp_wmb(); + WRITE_ONCE(req->iopoll_completed, 1); +} + +/* + * After the iocb has been issued, it's safe to be found on the poll list. + * Adding the kiocb to the list AFTER submission ensures that we don't + * find it from a io_do_iopoll() thread before the issuer is done + * accessing the kiocb cookie. + */ +static void io_iopoll_req_issued(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + const bool in_async = io_wq_current_is_worker(); + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (unlikely(in_async)) + mutex_lock(&ctx->uring_lock); + + /* + * Track whether we have multiple files in our lists. This will impact + * how we do polling eventually, not spinning if we're on potentially + * different devices. + */ + if (list_empty(&ctx->iopoll_list)) { + ctx->poll_multi_queue = false; + } else if (!ctx->poll_multi_queue) { + struct io_kiocb *list_req; + unsigned int queue_num0, queue_num1; + + list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, + inflight_entry); + + if (list_req->file != req->file) { + ctx->poll_multi_queue = true; + } else { + queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie); + queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie); + if (queue_num0 != queue_num1) + ctx->poll_multi_queue = true; + } + } + + /* + * For fast devices, IO may have already completed. If it has, add + * it to the front so we find it first. + */ + if (READ_ONCE(req->iopoll_completed)) + list_add(&req->inflight_entry, &ctx->iopoll_list); + else + list_add_tail(&req->inflight_entry, &ctx->iopoll_list); + + if (unlikely(in_async)) { + /* + * If IORING_SETUP_SQPOLL is enabled, sqes are either handle + * in sq thread task context or in io worker task context. If + * current task context is sq thread, we don't need to check + * whether should wake up sq thread. + */ + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + + mutex_unlock(&ctx->uring_lock); + } +} + +static bool io_bdev_nowait(struct block_device *bdev) +{ + return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); +} + +/* + * If we tracked the file through the SCM inflight mechanism, we could support + * any file. For now, just ensure that anything potentially problematic is done + * inline. + */ +static bool __io_file_supports_nowait(struct file *file, int rw) +{ + umode_t mode = file_inode(file)->i_mode; + + if (S_ISBLK(mode)) { + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) + return true; + return false; + } + if (S_ISSOCK(mode)) + return true; + if (S_ISREG(mode)) { + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + file->f_op != &io_uring_fops) + return true; + return false; + } + + /* any ->read/write should understand O_NONBLOCK */ + if (file->f_flags & O_NONBLOCK) + return true; + + if (!(file->f_mode & FMODE_NOWAIT)) + return false; + + if (rw == READ) + return file->f_op->read_iter != NULL; + + return file->f_op->write_iter != NULL; +} + +static bool io_file_supports_nowait(struct io_kiocb *req, int rw) +{ + if (rw == READ && (req->flags & REQ_F_NOWAIT_READ)) + return true; + else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE)) + return true; + + return __io_file_supports_nowait(req->file, rw); +} + +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + int rw) +{ + struct io_ring_ctx *ctx = req->ctx; + struct kiocb *kiocb = &req->rw.kiocb; + struct file *file = req->file; + unsigned ioprio; + int ret; + + if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode)) + req->flags |= REQ_F_ISREG; + + kiocb->ki_pos = READ_ONCE(sqe->off); + kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); + kiocb->ki_flags = iocb_flags(kiocb->ki_filp); + ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) + req->flags |= REQ_F_NOWAIT; + + ioprio = READ_ONCE(sqe->ioprio); + if (ioprio) { + ret = ioprio_check_cap(ioprio); + if (ret) + return ret; + + kiocb->ki_ioprio = ioprio; + } else + kiocb->ki_ioprio = get_current_ioprio(); + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || + !kiocb->ki_filp->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->ki_flags |= IOCB_HIPRI; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + /* used for fixed read/write too - just read unconditionally */ + req->buf_index = READ_ONCE(sqe->buf_index); + req->imu = NULL; + + if (req->opcode == IORING_OP_READ_FIXED || + req->opcode == IORING_OP_WRITE_FIXED) { + struct io_ring_ctx *ctx = req->ctx; + u16 index; + + if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); + req->imu = ctx->user_bufs[index]; + io_req_set_rsrc_node(req); + } + + req->rw.addr = READ_ONCE(sqe->addr); + req->rw.len = READ_ONCE(sqe->len); + return 0; +} + +static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) +{ + switch (ret) { + case -EIOCBQUEUED: + break; + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * We can't just restart the syscall, since previously + * submitted sqes may already be in progress. Just fail this + * IO with EINTR. + */ + ret = -EINTR; + fallthrough; + default: + kiocb->ki_complete(kiocb, ret, 0); + } +} + +static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) +{ + struct kiocb *kiocb = &req->rw.kiocb; + + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; + } + + kiocb->ki_pos = 0; + return NULL; +} + +static void kiocb_done(struct kiocb *kiocb, ssize_t ret, + unsigned int issue_flags) +{ + 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 (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) { + if (!__io_complete_rw_common(req, ret)) { + /* + * Safe to call io_end from here as we're inline + * from the submission path. + */ + io_req_io_end(req); + __io_req_complete(req, issue_flags, + io_fixup_rw_res(req, ret), + io_put_rw_kbuf(req)); + } + } else { + io_rw_done(kiocb, ret); + } + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + if (io_resubmit_prep(req)) { + io_req_task_queue_reissue(req); + } else { + unsigned int cflags = io_put_rw_kbuf(req); + struct io_ring_ctx *ctx = req->ctx; + + ret = io_fixup_rw_res(req, ret); + req_set_fail(req); + if (!(issue_flags & IO_URING_F_NONBLOCK)) { + mutex_lock(&ctx->uring_lock); + __io_req_complete(req, issue_flags, ret, cflags); + mutex_unlock(&ctx->uring_lock); + } else { + __io_req_complete(req, issue_flags, ret, cflags); + } + } + } +} + +static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + struct io_mapped_ubuf *imu) +{ + size_t len = req->rw.len; + u64 buf_end, buf_addr = req->rw.addr; + size_t offset; + + if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) + return -EFAULT; + /* not inside the mapped region */ + if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) + return -EFAULT; + + /* + * May not be a start of buffer, set size appropriately + * and advance us to the beginning. + */ + offset = buf_addr - imu->ubuf; + iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset < bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= bvec->bv_len + offset; + iter->iov_offset = offset & ~PAGE_MASK; + } + } + + return 0; +} + +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +{ + if (WARN_ON_ONCE(!req->imu)) + return -EFAULT; + return __io_import_fixed(req, rw, iter, req->imu); +} + +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 = xa_load(&req->ctx->io_buffers, 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; + xa_erase(&req->ctx->io_buffers, 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; + u16 bgid; + + kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; + bgid = req->buf_index; + 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) { + struct io_buffer *kbuf; + + kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; + iov[0].iov_base = u64_to_user_ptr(kbuf->addr); + iov[0].iov_len = kbuf->len; + return 0; + } + 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 int io_import_iovec(int rw, struct io_kiocb *req, 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; + u8 opcode = req->opcode; + ssize_t ret; + + if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { + *iovec = NULL; + return io_import_fixed(req, rw, iter); + } + + /* buffer index only valid with fixed read/write, or buffer select */ + if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)) + return -EINVAL; + + if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { + if (req->flags & REQ_F_BUFFER_SELECT) { + buf = io_rw_buffer_select(req, &sqe_len, needs_lock); + if (IS_ERR(buf)) + return PTR_ERR(buf); + req->rw.len = sqe_len; + } + + ret = import_single_range(rw, buf, sqe_len, *iovec, iter); + *iovec = NULL; + return ret; + } + + if (req->flags & REQ_F_BUFFER_SELECT) { + ret = io_iov_buffer_select(req, *iovec, needs_lock); + if (!ret) + iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); + *iovec = NULL; + return ret; + } + + return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter, + req->ctx->compat); +} + +static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) +{ + return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; +} + +/* + * For files that don't have ->read_iter() and ->write_iter(), handle them + * by looping over ->read() or ->write() manually. + */ +static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct file *file = req->file; + ssize_t ret = 0; + loff_t *ppos; + + /* + * Don't support polled IO through this interface, and we can't + * support non-blocking either. For the latter, this just causes + * the kiocb to be handled from an async context. + */ + if (kiocb->ki_flags & IOCB_HIPRI) + return -EOPNOTSUPP; + if (kiocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + + ppos = io_kiocb_ppos(kiocb); + + while (iov_iter_count(iter)) { + struct iovec iovec; + ssize_t nr; + + if (!iov_iter_is_bvec(iter)) { + iovec = iov_iter_iovec(iter); + } else { + iovec.iov_base = u64_to_user_ptr(req->rw.addr); + iovec.iov_len = req->rw.len; + } + + if (rw == READ) { + nr = file->f_op->read(file, iovec.iov_base, + iovec.iov_len, ppos); + } else { + nr = file->f_op->write(file, iovec.iov_base, + iovec.iov_len, ppos); + } + + if (nr < 0) { + if (!ret) + ret = nr; + break; + } + ret += nr; + if (!iov_iter_is_bvec(iter)) { + iov_iter_advance(iter, nr); + } else { + req->rw.addr += nr; + req->rw.len -= nr; + if (!req->rw.len) + break; + } + if (nr != iovec.iov_len) + break; + } + + return ret; +} + +static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, struct iov_iter *iter) +{ + struct io_async_rw *rw = req->async_data; + + memcpy(&rw->iter, iter, sizeof(*iter)); + rw->free_iovec = iovec; + rw->bytes_done = 0; + /* can only be fixed buffers, no need to do anything */ + if (iov_iter_is_bvec(iter)) + return; + if (!iovec) { + unsigned iov_off = 0; + + rw->iter.iov = rw->fast_iov; + if (iter->iov != fast_iov) { + iov_off = iter->iov - fast_iov; + rw->iter.iov += iov_off; + } + if (rw->fast_iov != fast_iov) + memcpy(rw->fast_iov + iov_off, fast_iov + iov_off, + sizeof(struct iovec) * iter->nr_segs); + } else { + req->flags |= REQ_F_NEED_CLEANUP; + } +} + +static inline int io_alloc_async_data(struct io_kiocb *req) +{ + WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); + req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); + return req->async_data == NULL; +} + +static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, + const struct iovec *fast_iov, + struct iov_iter *iter, bool force) +{ + if (!force && !io_op_defs[req->opcode].needs_async_setup) + return 0; + if (!req->async_data) { + struct io_async_rw *iorw; + + if (io_alloc_async_data(req)) { + kfree(iovec); + return -ENOMEM; + } + + io_req_map_rw(req, iovec, fast_iov, iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->iter, &iorw->iter_state); + } + return 0; +} + +static inline int io_rw_prep_async(struct io_kiocb *req, int rw) +{ + struct io_async_rw *iorw = req->async_data; + struct iovec *iov = iorw->fast_iov; + int ret; + + iorw->bytes_done = 0; + iorw->free_iovec = NULL; + + ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); + if (unlikely(ret < 0)) + return ret; + + if (iov) { + iorw->free_iovec = iov; + req->flags |= REQ_F_NEED_CLEANUP; + } + iov_iter_save_state(&iorw->iter, &iorw->iter_state); + return 0; +} + +static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (unlikely(!(req->file->f_mode & FMODE_READ))) + return -EBADF; + return io_prep_rw(req, sqe, READ); +} + +/* + * This is our waitqueue callback handler, registered through lock_page_async() + * when we initially tried to do the IO with the iocb armed our waitqueue. + * This gets called when the page is unlocked, and we generally expect that to + * happen when the page IO is completed and the page is now uptodate. This will + * queue a task_work based retry of the operation, attempting to copy the data + * again. If the latter fails because the page was NOT uptodate, then we will + * do a thread based blocking retry of the operation. That's the unexpected + * slow path. + */ +static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, + int sync, void *arg) +{ + struct wait_page_queue *wpq; + struct io_kiocb *req = wait->private; + struct wait_page_key *key = arg; + + wpq = container_of(wait, struct wait_page_queue, wait); + + if (!wake_page_match(wpq, key)) + return 0; + + req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; + list_del_init(&wait->entry); + io_req_task_queue(req); + return 1; +} + +/* + * This controls whether a given IO request should be armed for async page + * based retry. If we return false here, the request is handed to the async + * worker threads for retry. If we're doing buffered reads on a regular file, + * we prepare a private wait_page_queue entry and retry the operation. This + * will either succeed because the page is now uptodate and unlocked, or it + * will register a callback when the page is unlocked at IO completion. Through + * that callback, io_uring uses task_work to setup a retry of the operation. + * That retry will attempt the buffered read again. The retry will generally + * succeed, or in rare cases where it fails, we then fall back to using the + * async worker threads for a blocking retry. + */ +static bool io_rw_should_retry(struct io_kiocb *req) +{ + struct io_async_rw *rw = req->async_data; + struct wait_page_queue *wait = &rw->wpq; + struct kiocb *kiocb = &req->rw.kiocb; + + /* never retry for NOWAIT, we just complete with -EAGAIN */ + if (req->flags & REQ_F_NOWAIT) + return false; + + /* Only for buffered IO */ + if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) + return false; + + /* + * just use poll if we can, and don't attempt if the fs doesn't + * support callback based unlocks + */ + if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) + return false; + + wait->wait.func = io_async_buf_func; + wait->wait.private = req; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_flags &= ~IOCB_NOWAIT; + kiocb->ki_waitq = wait; + return true; +} + +static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) +{ + if (req->file->f_op->read_iter) + return call_read_iter(req->file, &req->rw.kiocb, iter); + else if (req->file->f_op->read) + return loop_rw_iter(READ, req, iter); + else + return -EINVAL; +} + +static bool need_read_all(struct io_kiocb *req) +{ + return req->flags & REQ_F_ISREG || + S_ISBLK(file_inode(req->file)->i_mode); +} + +static int io_read(struct io_kiocb *req, unsigned int issue_flags) +{ + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct kiocb *kiocb = &req->rw.kiocb; + struct iov_iter __iter, *iter = &__iter; + struct io_async_rw *rw = req->async_data; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; + loff_t *ppos; + + if (rw) { + iter = &rw->iter; + state = &rw->iter_state; + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); + + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + kiocb->ki_flags &= ~IOCB_NOWAIT; + else + kiocb->ki_flags |= IOCB_NOWAIT; + + /* If the file doesn't support async, just async punt */ + if (force_nonblock && !io_file_supports_nowait(req, READ)) { + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + return ret ?: -EAGAIN; + } + + ppos = io_kiocb_update_pos(req); + + ret = rw_verify_area(READ, req->file, ppos, req->result); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } + + ret = io_iter_do_read(req, iter); + + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { + req->flags &= ~REQ_F_REISSUE; + /* IOPOLL retry should happen for io-wq threads */ + if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) + goto done; + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (req->flags & REQ_F_NOWAIT) + goto done; + ret = 0; + } else if (ret == -EIOCBQUEUED) { + goto out_free; + } else if (ret <= 0 || ret == req->result || !force_nonblock || + (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { + /* read all, failed, already did sync or don't want to retry */ + goto done; + } + + /* + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. + */ + iov_iter_restore(iter, state); + + ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + if (ret2) + return ret2; + + iovec = NULL; + rw = req->async_data; + /* + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. + */ + if (iter != &rw->iter) { + iter = &rw->iter; + state = &rw->iter_state; + } + + do { + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(iter, ret); + if (!iov_iter_count(iter)) + break; + rw->bytes_done += ret; + iov_iter_save_state(iter, state); + + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { + kiocb->ki_flags &= ~IOCB_WAITQ; + return -EAGAIN; + } + + req->result = iov_iter_count(iter); + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If + * we get -EIOCBQUEUED, then we'll get a notification when the + * desired page gets unlocked. We can also get a partial read + * here, and if we do, then just retry at the new offset. + */ + ret = io_iter_do_read(req, iter); + if (ret == -EIOCBQUEUED) + return 0; + /* we got some bytes, but not all. retry. */ + kiocb->ki_flags &= ~IOCB_WAITQ; + iov_iter_restore(iter, state); + } while (ret > 0); +done: + kiocb_done(kiocb, ret, issue_flags); +out_free: + /* it's faster to check here then delegate to kfree */ + if (iovec) + kfree(iovec); + return 0; +} + +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; + return io_prep_rw(req, sqe, WRITE); +} + +static int io_write(struct io_kiocb *req, unsigned int issue_flags) +{ + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct kiocb *kiocb = &req->rw.kiocb; + struct iov_iter __iter, *iter = &__iter; + struct io_async_rw *rw = req->async_data; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; + loff_t *ppos; + + if (rw) { + iter = &rw->iter; + state = &rw->iter_state; + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); + + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + kiocb->ki_flags &= ~IOCB_NOWAIT; + else + kiocb->ki_flags |= IOCB_NOWAIT; + + /* If the file doesn't support async, just async punt */ + if (force_nonblock && !io_file_supports_nowait(req, WRITE)) + goto copy_iov; + + /* file path doesn't support NOWAIT for non-direct_IO */ + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && + (req->flags & REQ_F_ISREG)) + goto copy_iov; + + ppos = io_kiocb_update_pos(req); + + ret = rw_verify_area(WRITE, req->file, ppos, req->result); + if (unlikely(ret)) + goto out_free; + + /* + * Open-code file_start_write here to grab freeze protection, + * which will be released by another thread in + * io_complete_rw(). Fool lockdep by telling it the lock got + * released so that it doesn't complain about the held lock when + * we return to userspace. + */ + if (req->flags & REQ_F_ISREG) { + sb_start_write(file_inode(req->file)->i_sb); + __sb_writers_release(file_inode(req->file)->i_sb, + SB_FREEZE_WRITE); + } + kiocb->ki_flags |= IOCB_WRITE; + + if (req->file->f_op->write_iter) + ret2 = call_write_iter(req->file, kiocb, iter); + else if (req->file->f_op->write) + ret2 = loop_rw_iter(WRITE, req, iter); + else + ret2 = -EINVAL; + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + ret2 = -EAGAIN; + } + + /* + * 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; + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) + goto done; + if (!force_nonblock || ret2 != -EAGAIN) { + /* IOPOLL retry should happen for io-wq threads */ + if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) + goto copy_iov; +done: + kiocb_done(kiocb, ret2, issue_flags); + } else { +copy_iov: + iov_iter_restore(iter, state); + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); + if (!ret) { + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); + return -EAGAIN; + } + return ret; + } +out_free: + /* it's reportedly faster than delegating the null check to kfree() */ + if (iovec) + kfree(iovec); + return ret; +} + +static int io_renameat_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_rename *ren = &req->rename; + const char __user *oldf, *newf; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ren->old_dfd = READ_ONCE(sqe->fd); + oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ren->new_dfd = READ_ONCE(sqe->len); + ren->flags = READ_ONCE(sqe->rename_flags); + + ren->oldpath = getname(oldf); + if (IS_ERR(ren->oldpath)) + return PTR_ERR(ren->oldpath); + + ren->newpath = getname(newf); + if (IS_ERR(ren->newpath)) { + putname(ren->oldpath); + return PTR_ERR(ren->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rename *ren = &req->rename; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, + ren->newpath, ren->flags); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_unlinkat_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_unlink *un = &req->unlink; + const char __user *fname; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + un->dfd = READ_ONCE(sqe->fd); + + un->flags = READ_ONCE(sqe->unlink_flags); + if (un->flags & ~AT_REMOVEDIR) + return -EINVAL; + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + un->filename = getname(fname); + if (IS_ERR(un->filename)) + return PTR_ERR(un->filename); + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_unlink *un = &req->unlink; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (un->flags & AT_REMOVEDIR) + ret = do_rmdir(un->dfd, un->filename); + else + ret = do_unlinkat(un->dfd, un->filename); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_shutdown_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_NET) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || + sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + req->shutdown.how = READ_ONCE(sqe->len); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_NET) + struct socket *sock; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + ret = __sys_shutdown_sock(sock, req->shutdown.how); + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +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; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + sp->len = READ_ONCE(sqe->len); + sp->flags = READ_ONCE(sqe->splice_flags); + if (unlikely(sp->flags & ~valid_flags)) + return -EINVAL; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); + return 0; +} + +static int io_tee_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off)) + return -EINVAL; + return __io_splice_prep(req, sqe); +} + +static int io_tee(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_splice *sp = &req->splice; + struct file *out = sp->file_out; + unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; + long ret = 0; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); + if (!in) { + ret = -EBADF; + goto done; + } + + if (sp->len) + ret = do_tee(in, out, sp->len, flags); + + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: + if (ret != sp->len) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_splice *sp = &req->splice; + + sp->off_in = READ_ONCE(sqe->splice_off_in); + sp->off_out = READ_ONCE(sqe->off); + return __io_splice_prep(req, sqe); +} + +static int io_splice(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_splice *sp = &req->splice; + struct file *out = sp->file_out; + unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + loff_t *poff_in, *poff_out; + struct file *in; + long ret = 0; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); + if (!in) { + ret = -EBADF; + goto done; + } + + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; + poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; + + if (sp->len) + ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); + + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: + if (ret != sp->len) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +/* + * IORING_OP_NOP just posts a completion event, nothing else. + */ +static int io_nop(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + __io_req_complete(req, issue_flags, 0, 0); + return 0; +} + +static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || + sqe->splice_fd_in)) + return -EINVAL; + + req->sync.flags = READ_ONCE(sqe->fsync_flags); + if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC)) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); + return 0; +} + +static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) +{ + loff_t end = req->sync.off + req->sync.len; + int ret; + + /* fsync always requires a blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + 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(req); + io_req_complete(req, ret); + return 0; +} + +static int io_fallocate_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (sqe->ioprio || sqe->buf_index || sqe->rw_flags || + sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->addr); + req->sync.mode = READ_ONCE(sqe->len); + return 0; +} + +static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + /* fallocate always requiring blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, + req->sync.len); + if (ret < 0) + req_set_fail(req); + else + fsnotify_modify(req->file); + io_req_complete(req, ret); + return 0; +} + +static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + const char __user *fname; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->buf_index)) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + /* open.how should be already initialised */ + if (!(req->open.how.flags & O_PATH) && force_o_largefile()) + req->open.how.flags |= O_LARGEFILE; + + req->open.dfd = READ_ONCE(sqe->fd); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + req->open.filename = getname(fname); + if (IS_ERR(req->open.filename)) { + ret = PTR_ERR(req->open.filename); + req->open.filename = NULL; + return ret; + } + + req->open.file_slot = READ_ONCE(sqe->file_index); + if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC)) + return -EINVAL; + + req->open.nofile = rlimit(RLIMIT_NOFILE); + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + u64 mode = READ_ONCE(sqe->len); + u64 flags = READ_ONCE(sqe->open_flags); + + req->open.how = build_open_how(flags, mode); + return __io_openat_prep(req, sqe); +} + +static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct open_how __user *how; + size_t len; + int ret; + + how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + len = READ_ONCE(sqe->len); + if (len < OPEN_HOW_SIZE_VER0) + return -EINVAL; + + ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how, + len); + if (ret) + return ret; + + return __io_openat_prep(req, sqe); +} + +static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) +{ + struct open_flags op; + struct file *file; + bool resolve_nonblock, nonblock_set; + bool fixed = !!req->open.file_slot; + int ret; + + ret = build_open_flags(&req->open.how, &op); + if (ret) + goto err; + nonblock_set = op.open_flag & O_NONBLOCK; + resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; + if (issue_flags & IO_URING_F_NONBLOCK) { + /* + * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, + * it'll always -EAGAIN. Note that we test for __O_TMPFILE + * because O_TMPFILE includes O_DIRECTORY, which isn't a flag + * we need to force async for. + */ + if (req->open.how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) + return -EAGAIN; + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } + + if (!fixed) { + ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); + if (ret < 0) + goto err; + } + + file = do_filp_open(req->open.dfd, req->open.filename, &op); + if (IS_ERR(file)) { + /* + * We could hang on to this 'fd' on retrying, but seems like + * marginal gain for something that is now known to be a slower + * path. So just put it, and we'll get a new one when we retry. + */ + if (!fixed) + put_unused_fd(ret); + + ret = PTR_ERR(file); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if (ret == -EAGAIN && + (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) + return -EAGAIN; + goto err; + } + + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + fsnotify_open(file); + + if (!fixed) + fd_install(ret, file); + else + ret = io_install_fixed_file(req, file, issue_flags, + req->open.file_slot - 1); +err: + putname(req->open.filename); + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_openat(struct io_kiocb *req, unsigned int issue_flags) +{ + return io_openat2(req, issue_flags); +} + +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 || + sqe->splice_fd_in) + 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; + cond_resched(); + } + i++; + kfree(buf); + xa_erase(&ctx->io_buffers, bgid); + + return i; +} + +static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_provide_buf *p = &req->pbuf; + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer *head; + int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + io_ring_submit_lock(ctx, !force_nonblock); + + lockdep_assert_held(&ctx->uring_lock); + + ret = -ENOENT; + head = xa_load(&ctx->io_buffers, p->bgid); + if (head) + ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); + if (ret < 0) + req_set_fail(req); + + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); + return 0; +} + +static int io_provide_buffers_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + unsigned long size, tmp_check; + struct io_provide_buf *p = &req->pbuf; + u64 tmp; + + if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + 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 (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, + &size)) + return -EOVERFLOW; + if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) + return -EOVERFLOW; + + size = (unsigned long)p->len * p->nbufs; + if (!access_ok(u64_to_user_ptr(p->addr), size)) + 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_ACCOUNT); + if (!buf) + break; + + buf->addr = addr; + buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); + buf->bid = bid; + addr += pbuf->len; + bid++; + if (!*head) { + INIT_LIST_HEAD(&buf->list); + *head = buf; + } else { + list_add_tail(&buf->list, &(*head)->list); + } + cond_resched(); + } + + return i ? i : -ENOMEM; +} + +static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_provide_buf *p = &req->pbuf; + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer *head, *list; + int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + io_ring_submit_lock(ctx, !force_nonblock); + + lockdep_assert_held(&ctx->uring_lock); + + list = head = xa_load(&ctx->io_buffers, p->bgid); + + ret = io_add_buffers(p, &head); + if (ret >= 0 && !list) { + ret = xa_insert(&ctx->io_buffers, p->bgid, head, + GFP_KERNEL_ACCOUNT); + if (ret < 0) + __io_remove_buffers(ctx, head, p->bgid, -1U); + } + if (ret < 0) + req_set_fail(req); + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); + return 0; +} + +static int io_epoll_ctl_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_EPOLL) + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + req->epoll.epfd = READ_ONCE(sqe->fd); + req->epoll.op = READ_ONCE(sqe->len); + req->epoll.fd = READ_ONCE(sqe->off); + + if (ep_op_has_event(req->epoll.op)) { + struct epoll_event __user *ev; + + ev = u64_to_user_ptr(READ_ONCE(sqe->addr)); + if (copy_from_user(&req->epoll.event, ev, sizeof(*ev))) + return -EFAULT; + } + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_EPOLL) + struct io_epoll *ie = &req->epoll; + int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + + if (ret < 0) + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + req->madvise.addr = READ_ONCE(sqe->addr); + req->madvise.len = READ_ONCE(sqe->len); + req->madvise.advice = READ_ONCE(sqe->fadvise_advice); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + struct io_madvise *ma = &req->madvise; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + req->fadvise.offset = READ_ONCE(sqe->off); + req->fadvise.len = READ_ONCE(sqe->len); + req->fadvise.advice = READ_ONCE(sqe->fadvise_advice); + return 0; +} + +static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_fadvise *fa = &req->fadvise; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) { + switch (fa->advice) { + case POSIX_FADV_NORMAL: + case POSIX_FADV_RANDOM: + case POSIX_FADV_SEQUENTIAL: + break; + default: + return -EAGAIN; + } + } + + ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); + if (ret < 0) + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (req->flags & REQ_F_FIXED_FILE) + return -EBADF; + + req->statx.dfd = READ_ONCE(sqe->fd); + req->statx.mask = READ_ONCE(sqe->len); + req->statx.filename = u64_to_user_ptr(READ_ONCE(sqe->addr)); + req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + req->statx.flags = READ_ONCE(sqe->statx_flags); + + return 0; +} + +static int io_statx(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_statx *ctx = &req->statx; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, + ctx->buffer); + + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || + sqe->rw_flags || sqe->buf_index) + return -EINVAL; + if (req->flags & REQ_F_FIXED_FILE) + return -EBADF; + + req->close.fd = READ_ONCE(sqe->fd); + req->close.file_slot = READ_ONCE(sqe->file_index); + if (req->close.file_slot && req->close.fd) + return -EINVAL; + + return 0; +} + +static int io_close(struct io_kiocb *req, unsigned int issue_flags) +{ + struct files_struct *files = current->files; + struct io_close *close = &req->close; + struct fdtable *fdt; + struct file *file = NULL; + int ret = -EBADF; + + if (req->close.file_slot) { + ret = io_close_fixed(req, issue_flags); + goto err; + } + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + if (close->fd >= fdt->max_fds) { + spin_unlock(&files->file_lock); + goto err; + } + file = fdt->fd[close->fd]; + if (!file || file->f_op == &io_uring_fops) { + spin_unlock(&files->file_lock); + file = NULL; + goto err; + } + + /* if the file has a flush method, be safe and punt to async */ + if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { + spin_unlock(&files->file_lock); + return -EAGAIN; + } + + ret = __close_fd_get_file(close->fd, &file); + spin_unlock(&files->file_lock); + if (ret < 0) { + if (ret == -ENOENT) + ret = -EBADF; + goto err; + } + + /* No ->flush() or already async, safely close from here */ + ret = filp_close(file, current->files); +err: + if (ret < 0) + req_set_fail(req); + if (file) + fput(file); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || + sqe->splice_fd_in)) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); + req->sync.flags = READ_ONCE(sqe->sync_range_flags); + return 0; +} + +static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + /* sync_file_range always requires a blocking context */ + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = sync_file_range(req->file, req->sync.off, req->sync.len, + req->sync.flags); + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +#if defined(CONFIG_NET) +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + +static int io_setup_async_msg(struct io_kiocb *req, + struct io_async_msghdr *kmsg) +{ + struct io_async_msghdr *async_msg = req->async_data; + + if (async_msg) + return -EAGAIN; + if (io_alloc_async_data(req)) { + kfree(kmsg->free_iov); + return -ENOMEM; + } + async_msg = req->async_data; + req->flags |= REQ_F_NEED_CLEANUP; + memcpy(async_msg, kmsg, sizeof(*kmsg)); + if (async_msg->msg.msg_name) + async_msg->msg.msg_name = &async_msg->addr; + /* if were using fast_iov, set it to the new one */ + if (!kmsg->free_iov) { + size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov; + async_msg->msg.msg_iter.iov = &async_msg->fast_iov[fast_idx]; + } + + return -EAGAIN; +} + +static int io_sendmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = &req->sr_msg; + int ret; + + iomsg->msg.msg_name = &iomsg->addr; + iomsg->free_iov = iomsg->fast_iov; + ret = sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, + req->sr_msg.msg_flags, &iomsg->free_iov); + /* save msg_control as sys_sendmsg() overwrites it */ + sr->msg_control = iomsg->msg.msg_control; + return ret; +} + +static int io_sendmsg_prep_async(struct io_kiocb *req) +{ + int ret; + + ret = io_sendmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + sr->done_io = 0; + return 0; +} + +static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; + struct socket *sock; + unsigned flags; + int min_ret = 0; + int ret; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + kmsg = req->async_data; + if (!kmsg) { + ret = io_sendmsg_copy_hdr(req, &iomsg); + if (ret) + return ret; + kmsg = &iomsg; + } else { + kmsg->msg.msg_control = sr->msg_control; + } + + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); + + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } + req_set_fail(req); + } + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_send(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_sr_msg *sr = &req->sr_msg; + struct msghdr msg; + struct iovec iov; + struct socket *sock; + unsigned flags; + int min_ret = 0; + int ret; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter); + if (unlikely(ret)) + return ret; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + msg.msg_flags = flags; + ret = sock_sendmsg(sock, &msg); + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } + req_set_fail(req); + } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int __io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = &req->sr_msg; + struct iovec __user *uiov; + size_t iov_len; + int ret; + + ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg, + &iomsg->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(iomsg->fast_iov, uiov, sizeof(*uiov))) + return -EFAULT; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; + } else { + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, + &iomsg->free_iov, &iomsg->msg.msg_iter, + false); + if (ret > 0) + ret = 0; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + struct io_sr_msg *sr = &req->sr_msg; + struct compat_iovec __user *uiov; + compat_uptr_t ptr; + compat_size_t len; + int ret; + + ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->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 = clen; + iomsg->free_iov = NULL; + } else { + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(READ, (struct iovec __user *)uiov, len, + UIO_FASTIOV, &iomsg->free_iov, + &iomsg->msg.msg_iter, true); + if (ret < 0) + return ret; + } + + return 0; +} +#endif + +static int io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) +{ + iomsg->msg.msg_name = &iomsg->addr; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + return __io_compat_recvmsg_copy_hdr(req, iomsg); +#endif + + return __io_recvmsg_copy_hdr(req, iomsg); +} + +static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req, + bool needs_lock) +{ + struct io_sr_msg *sr = &req->sr_msg; + struct io_buffer *kbuf; + + 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; + return kbuf; +} + +static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req) +{ + return io_put_kbuf(req, req->sr_msg.kbuf); +} + +static int io_recvmsg_prep_async(struct io_kiocb *req) +{ + int ret; + + ret = io_recvmsg_copy_hdr(req, req->async_data); + if (!ret) + req->flags |= REQ_F_NEED_CLEANUP; + return ret; +} + +static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->bgid = READ_ONCE(sqe->buf_group); + sr->msg_flags = READ_ONCE(sqe->msg_flags); + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + sr->done_io = 0; + return 0; +} + +static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; + struct socket *sock; + struct io_buffer *kbuf; + unsigned flags; + int min_ret = 0; + int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + kmsg = req->async_data; + if (!kmsg) { + ret = io_recvmsg_copy_hdr(req, &iomsg); + if (ret) + return ret; + kmsg = &iomsg; + } + + if (req->flags & REQ_F_BUFFER_SELECT) { + kbuf = io_recv_buffer_select(req, !force_nonblock); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); + kmsg->fast_iov[0].iov_len = req->sr_msg.len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, + 1, req->sr_msg.len); + } + + flags = req->sr_msg.msg_flags; + if (force_nonblock) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + + ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, + kmsg->uaddr, flags); + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + kmsg->msg.msg_controllen = 0; + kmsg->msg.msg_control = NULL; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } + + if (req->flags & REQ_F_BUFFER_SELECTED) + cflags = io_put_recv_kbuf(req); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + __io_req_complete(req, issue_flags, ret, cflags); + return 0; +} + +static int io_recv(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_buffer *kbuf; + struct io_sr_msg *sr = &req->sr_msg; + struct msghdr msg; + void __user *buf = sr->buf; + struct socket *sock; + struct iovec iov; + unsigned flags; + int min_ret = 0; + int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + if (req->flags & REQ_F_BUFFER_SELECT) { + kbuf = io_recv_buffer_select(req, !force_nonblock); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + buf = u64_to_user_ptr(kbuf->addr); + } + + ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter); + if (unlikely(ret)) + goto out_free; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + msg.msg_iocb = NULL; + msg.msg_flags = 0; + + flags = req->sr_msg.msg_flags; + if (force_nonblock) + flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + ret = sock_recvmsg(sock, &msg, flags); + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { +out_free: + req_set_fail(req); + } + if (req->flags & REQ_F_BUFFER_SELECTED) + cflags = io_put_recv_kbuf(req); + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; + __io_req_complete(req, issue_flags, ret, cflags); + return 0; +} + +static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_accept *accept = &req->accept; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->len || sqe->buf_index) + return -EINVAL; + + accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + accept->flags = READ_ONCE(sqe->accept_flags); + accept->nofile = rlimit(RLIMIT_NOFILE); + + accept->file_slot = READ_ONCE(sqe->file_index); + if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) + accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + return 0; +} + +static int io_accept(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_accept *accept = &req->accept; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; + bool fixed = !!accept->file_slot; + struct file *file; + int ret, fd; + + if (!fixed) { + fd = __get_unused_fd_flags(accept->flags, accept->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, + accept->flags); + + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + /* safe to retry */ + req->flags |= REQ_F_PARTIAL_IO; + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_install_fixed_file(req, file, issue_flags, + accept->file_slot - 1); + } + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_connect_prep_async(struct io_kiocb *req) +{ + struct io_async_connect *io = req->async_data; + struct io_connect *conn = &req->connect; + + return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); +} + +static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_connect *conn = &req->connect; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || + sqe->splice_fd_in) + return -EINVAL; + + conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + conn->addr_len = READ_ONCE(sqe->addr2); + return 0; +} + +static int io_connect(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_async_connect __io, *io; + unsigned file_flags; + int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + + if (req->async_data) { + io = req->async_data; + } else { + ret = move_addr_to_kernel(req->connect.addr, + req->connect.addr_len, + &__io.address); + if (ret) + goto out; + io = &__io; + } + + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_connect_file(req->file, &io->address, + req->connect.addr_len, file_flags); + if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { + if (req->async_data) + return -EAGAIN; + if (io_alloc_async_data(req)) { + ret = -ENOMEM; + goto out; + } + memcpy(req->async_data, &__io, sizeof(__io)); + return -EAGAIN; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; +out: + if (ret < 0) + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} +#else /* !CONFIG_NET */ +#define IO_NETOP_FN(op) \ +static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \ +{ \ + return -EOPNOTSUPP; \ +} + +#define IO_NETOP_PREP(op) \ +IO_NETOP_FN(op) \ +static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \ +{ \ + return -EOPNOTSUPP; \ +} \ + +#define IO_NETOP_PREP_ASYNC(op) \ +IO_NETOP_PREP(op) \ +static int io_##op##_prep_async(struct io_kiocb *req) \ +{ \ + return -EOPNOTSUPP; \ +} + +IO_NETOP_PREP_ASYNC(sendmsg); +IO_NETOP_PREP_ASYNC(recvmsg); +IO_NETOP_PREP_ASYNC(connect); +IO_NETOP_PREP(accept); +IO_NETOP_FN(send); +IO_NETOP_FN(recv); +#endif /* CONFIG_NET */ + +struct io_poll_table { + struct poll_table_struct pt; + struct io_kiocb *req; + int nr_entries; + int error; +}; + +#define IO_POLL_CANCEL_FLAG BIT(31) +#define IO_POLL_RETRY_FLAG BIT(30) +#define IO_POLL_REF_MASK GENMASK(29, 0) + +/* + * We usually have 1-2 refs taken, 128 is more than enough and we want to + * maximise the margin between this amount and the moment when it overflows. + */ +#define IO_POLL_REF_BIAS 128 + +static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) +{ + int v; + + /* + * poll_refs are already elevated and we don't have much hope for + * grabbing the ownership. Instead of incrementing set a retry flag + * to notify the loop that there might have been some change. + */ + v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); + if (v & IO_POLL_REF_MASK) + return false; + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} + +/* + * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can + * bump it and acquire ownership. It's disallowed to modify requests while not + * owning it, that prevents from races for enqueueing task_work's and b/w + * arming poll and wakeups. + */ +static inline bool io_poll_get_ownership(struct io_kiocb *req) +{ + if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) + return io_poll_get_ownership_slowpath(req); + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} + +static void io_poll_mark_cancelled(struct io_kiocb *req) +{ + atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); +} + +static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) +{ + /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ + if (req->opcode == IORING_OP_POLL_ADD) + return req->async_data; + return req->apoll->double_poll; +} + +static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) +{ + if (req->opcode == IORING_OP_POLL_ADD) + return &req->poll; + return &req->apoll->poll; +} + +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 void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, + wait_queue_func_t wake_func) +{ + poll->head = NULL; +#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) + /* mask in events that we always want/need */ + poll->events = events | IO_POLL_UNMASK; + INIT_LIST_HEAD(&poll->wait.entry); + init_waitqueue_func_entry(&poll->wait, wake_func); +} + +static inline void io_poll_remove_entry(struct io_poll_iocb *poll) +{ + struct wait_queue_head *head = smp_load_acquire(&poll->head); + + if (head) { + spin_lock_irq(&head->lock); + list_del_init(&poll->wait.entry); + poll->head = NULL; + spin_unlock_irq(&head->lock); + } +} + +static void io_poll_remove_entries(struct io_kiocb *req) +{ + struct io_poll_iocb *poll = io_poll_get_single(req); + struct io_poll_iocb *poll_double = io_poll_get_double(req); + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + io_poll_remove_entry(poll); + if (poll_double) + io_poll_remove_entry(poll_double); + rcu_read_unlock(); +} + +/* + * All poll tw should go through this. Checks for poll events, manages + * references, does rewait, etc. + * + * Returns a negative error on failure. >0 when no action require, which is + * either spurious wakeup or multishot CQE is served. 0 when it's done with + * the request, then the mask is stored in req->result. + */ +static int io_poll_check_events(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_iocb *poll = io_poll_get_single(req); + int v; + + /* req->task == current here, checking PF_EXITING is safe */ + if (unlikely(req->task->flags & PF_EXITING)) + io_poll_mark_cancelled(req); + + do { + v = atomic_read(&req->poll_refs); + + /* tw handler should be the owner, and so have some references */ + if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) + return 0; + if (v & IO_POLL_CANCEL_FLAG) + return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->result = 0; + if (v & IO_POLL_RETRY_FLAG) { + req->result = 0; + /* + * We won't find new events that came in between + * vfs_poll and the ref put unless we clear the + * flag in advance. + */ + atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); + v &= ~IO_POLL_RETRY_FLAG; + } + + if (!req->result) { + struct poll_table_struct pt = { ._key = poll->events }; + + req->result = vfs_poll(req->file, &pt) & poll->events; + } + + /* multishot, just fill an CQE and proceed */ + if (req->result && !(poll->events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & poll->events); + bool filled; + + spin_lock(&ctx->completion_lock); + filled = io_fill_cqe_aux(ctx, req->user_data, mask, + IORING_CQE_F_MORE); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (unlikely(!filled)) + return -ECANCELED; + io_cqring_ev_posted(ctx); + } else if (req->result) { + return 0; + } + + /* force the next iteration to vfs_poll() */ + req->result = 0; + + /* + * Release all references, retry if someone tried to restart + * task_work while we were executing it. + */ + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & + IO_POLL_REF_MASK); + + return 1; +} + +static void io_poll_task_func(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = io_poll_check_events(req); + if (ret > 0) + return; + + if (!ret) { + req->result = mangle_poll(req->result & req->poll.events); + } else { + req->result = ret; + req_set_fail(req); + } + + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); + io_req_complete_post(req, req->result, 0); +} + +static void io_apoll_task_func(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = io_poll_check_events(req); + if (ret > 0) + return; + + io_tw_lock(req->ctx, locked); + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); + + if (!ret) + io_req_task_submit(req, locked); + else + io_req_complete_failed(req, ret); +} + +static void __io_poll_execute(struct io_kiocb *req, int mask) +{ + req->result = mask; + if (req->opcode == IORING_OP_POLL_ADD) + req->io_task_work.func = io_poll_task_func; + else + req->io_task_work.func = io_apoll_task_func; + + trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); + io_req_task_work_add(req); +} + +static inline void io_poll_execute(struct io_kiocb *req, int res) +{ + if (io_poll_get_ownership(req)) + __io_poll_execute(req, res); +} + +static void io_poll_cancel_req(struct io_kiocb *req) +{ + io_poll_mark_cancelled(req); + /* kick tw, which should complete the request */ + io_poll_execute(req, 0); +} + +static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) +{ + struct io_kiocb *req = wait->private; + struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, + wait); + __poll_t mask = key_to_poll(key); + + if (unlikely(mask & POLLFREE)) { + io_poll_mark_cancelled(req); + /* we have to kick tw in case it's not already */ + io_poll_execute(req, 0); + + /* + * If the waitqueue is being freed early but someone is already + * holds ownership over it, we have to tear down the request as + * best we can. That means immediately removing the request from + * its waitqueue and preventing all further accesses to the + * waitqueue via the request. + */ + list_del_init(&poll->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&poll->head, NULL); + return 1; + } + + /* for instances that support it check for an event match first */ + if (mask && !(mask & poll->events)) + return 0; + + if (io_poll_get_ownership(req)) { + /* + * If we trigger a multishot poll off our own wakeup path, + * disable multishot as there is a circular dependency between + * CQ posting and triggering the event. + */ + if (mask & EPOLL_URING_WAKE) + poll->events |= EPOLLONESHOT; + + __io_poll_execute(req, mask); + } + return 1; +} + +static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, + struct wait_queue_head *head, + struct io_poll_iocb **poll_ptr) +{ + struct io_kiocb *req = pt->req; + + /* + * The file being polled uses multiple waitqueues for poll handling + * (e.g. one for read, one for write). Setup a separate io_poll_iocb + * if this happens. + */ + if (unlikely(pt->nr_entries)) { + struct io_poll_iocb *first = poll; + + /* double add on the same waitqueue head, ignore */ + if (first->head == head) + return; + /* already have a 2nd entry, fail a third attempt */ + if (*poll_ptr) { + if ((*poll_ptr)->head == head) + return; + pt->error = -EINVAL; + return; + } + + poll = kmalloc(sizeof(*poll), GFP_ATOMIC); + if (!poll) { + pt->error = -ENOMEM; + return; + } + io_init_poll_iocb(poll, first->events, first->wait.func); + *poll_ptr = poll; + } + + pt->nr_entries++; + poll->head = head; + poll->wait.private = req; + + if (poll->events & EPOLLEXCLUSIVE) + add_wait_queue_exclusive(head, &poll->wait); + else + add_wait_queue(head, &poll->wait); +} + +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); + + __io_queue_proc(&pt->req->poll, pt, head, + (struct io_poll_iocb **) &pt->req->async_data); +} + +static int __io_arm_poll_handler(struct io_kiocb *req, + struct io_poll_iocb *poll, + struct io_poll_table *ipt, __poll_t mask) +{ + struct io_ring_ctx *ctx = req->ctx; + + INIT_HLIST_NODE(&req->hash_node); + io_init_poll_iocb(poll, mask, io_poll_wake); + poll->file = req->file; + poll->wait.private = req; + + ipt->pt._key = mask; + ipt->req = req; + ipt->error = 0; + ipt->nr_entries = 0; + + /* + * Take the ownership to delay any tw execution up until we're done + * with poll arming. see io_poll_get_ownership(). + */ + atomic_set(&req->poll_refs, 1); + mask = vfs_poll(req->file, &ipt->pt) & poll->events; + + if (mask && (poll->events & EPOLLONESHOT)) { + io_poll_remove_entries(req); + /* no one else has access to the req, forget about the ref */ + return mask; + } + if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { + io_poll_remove_entries(req); + if (!ipt->error) + ipt->error = -EINVAL; + return 0; + } + + spin_lock(&ctx->completion_lock); + io_poll_req_insert(req); + spin_unlock(&ctx->completion_lock); + + if (mask) { + /* can't multishot if failed, just queue the event we've got */ + if (unlikely(ipt->error || !ipt->nr_entries)) { + poll->events |= EPOLLONESHOT; + ipt->error = 0; + } + __io_poll_execute(req, mask); + return 0; + } + + /* + * Try to release ownership. If we see a change of state, e.g. + * poll was waken up, queue up a tw, it'll deal with it. + */ + if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) + __io_poll_execute(req, 0); + return 0; +} + +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); + struct async_poll *apoll = pt->req->apoll; + + __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); +} + +enum { + IO_APOLL_OK, + IO_APOLL_ABORTED, + IO_APOLL_READY +}; + +/* + * We can't reliably detect loops in repeated poll triggers and issue + * subsequently failing. But rather than fail these immediately, allow a + * certain amount of retries before we give up. Given that this condition + * should _rarely_ trigger even once, we should be fine with a larger value. + */ +#define APOLL_MAX_RETRY 128 + +static int 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 = EPOLLONESHOT | POLLERR | POLLPRI; + int ret; + + if (!req->file || !file_can_poll(req->file)) + return IO_APOLL_ABORTED; + if (!def->pollin && !def->pollout) + return IO_APOLL_ABORTED; + + if (def->pollin) { + mask |= POLLIN | POLLRDNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + } else { + mask |= POLLOUT | POLLWRNORM; + } + + if (req->flags & REQ_F_POLLED) { + apoll = req->apoll; + kfree(apoll->double_poll); + if (unlikely(!--apoll->poll.retries)) { + apoll->double_poll = NULL; + return IO_APOLL_ABORTED; + } + } else { + apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (unlikely(!apoll)) + return IO_APOLL_ABORTED; + apoll->poll.retries = APOLL_MAX_RETRY; + } + apoll->double_poll = NULL; + req->apoll = apoll; + req->flags |= REQ_F_POLLED; + ipt.pt._qproc = io_async_queue_proc; + + ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); + if (ret || ipt.error) + return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; + + trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data, + mask, apoll->poll.events); + return IO_APOLL_OK; +} + +/* + * Returns true if we found and killed one or more poll requests + */ +static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + bool found = false; + int i; + + spin_lock(&ctx->completion_lock); + for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { + struct hlist_head *list; + + list = &ctx->cancel_hash[i]; + hlist_for_each_entry_safe(req, tmp, list, hash_node) { + if (io_match_task_safe(req, tsk, cancel_all)) { + hlist_del_init(&req->hash_node); + io_poll_cancel_req(req); + found = true; + } + } + } + spin_unlock(&ctx->completion_lock); + return found; +} + +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) +{ + struct hlist_head *list; + struct io_kiocb *req; + + 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) + continue; + if (poll_only && req->opcode != IORING_OP_POLL_ADD) + continue; + return req; + } + return NULL; +} + +static bool io_poll_disarm(struct io_kiocb *req) + __must_hold(&ctx->completion_lock) +{ + if (!io_poll_get_ownership(req)) + return false; + io_poll_remove_entries(req); + hash_del(&req->hash_node); + return true; +} + +static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); + + if (!req) + return -ENOENT; + io_poll_cancel_req(req); + return 0; +} + +static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, + unsigned int flags) +{ + u32 events; + + events = READ_ONCE(sqe->poll32_events); +#ifdef __BIG_ENDIAN + events = swahw32(events); +#endif + if (!(flags & IORING_POLL_ADD_MULTI)) + events |= EPOLLONESHOT; + return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); +} + +static int io_poll_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_poll_update *upd = &req->poll_update; + u32 flags; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | + IORING_POLL_ADD_MULTI)) + return -EINVAL; + /* meaningless without update */ + if (flags == IORING_POLL_ADD_MULTI) + return -EINVAL; + + upd->old_user_data = READ_ONCE(sqe->addr); + upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; + upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; + + upd->new_user_data = READ_ONCE(sqe->off); + if (!upd->update_user_data && upd->new_user_data) + return -EINVAL; + if (upd->update_events) + upd->events = io_poll_parse_events(sqe, flags); + else if (sqe->poll32_events) + return -EINVAL; + + return 0; +} + +static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_poll_iocb *poll = &req->poll; + u32 flags; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~IORING_POLL_ADD_MULTI) + return -EINVAL; + + io_req_set_refcount(req); + poll->events = io_poll_parse_events(sqe, flags); + return 0; +} + +static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_poll_iocb *poll = &req->poll; + struct io_poll_table ipt; + int ret; + + ipt.pt._qproc = io_poll_queue_proc; + + ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events); + if (!ret && ipt.error) + req_set_fail(req); + ret = ret ?: ipt.error; + if (ret) + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *preq; + int ret2, ret = 0; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + + spin_lock(&ctx->completion_lock); + preq = io_poll_find(ctx, req->poll_update.old_user_data, true); + if (!preq || !io_poll_disarm(preq)) { + spin_unlock(&ctx->completion_lock); + ret = preq ? -EALREADY : -ENOENT; + goto out; + } + spin_unlock(&ctx->completion_lock); + + if (req->poll_update.update_events || req->poll_update.update_user_data) { + /* only mask one event flags, keep behavior flags */ + if (req->poll_update.update_events) { + preq->poll.events &= ~0xffff; + preq->poll.events |= req->poll_update.events & 0xffff; + preq->poll.events |= IO_POLL_UNMASK; + } + if (req->poll_update.update_user_data) + preq->user_data = req->poll_update.new_user_data; + + ret2 = io_poll_add(preq, issue_flags); + /* successfully updated, don't complete poll request */ + if (!ret2) + goto out; + } + req_set_fail(preq); + io_req_complete(preq, -ECANCELED); +out: + if (ret < 0) + req_set_fail(req); + /* complete update request, we're done with it */ + io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return 0; +} + +static void io_req_task_timeout(struct io_kiocb *req, bool *locked) +{ + req_set_fail(req); + io_req_complete_post(req, -ETIME, 0); +} + +static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) +{ + struct io_timeout_data *data = container_of(timer, + struct io_timeout_data, timer); + struct io_kiocb *req = data->req; + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->timeout_lock, flags); + list_del_init(&req->timeout.list); + atomic_set(&req->ctx->cq_timeouts, + atomic_read(&req->ctx->cq_timeouts) + 1); + spin_unlock_irqrestore(&ctx->timeout_lock, flags); + + req->io_task_work.func = io_req_task_timeout; + io_req_task_work_add(req); + return HRTIMER_NORESTART; +} + +static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, + __u64 user_data) + __must_hold(&ctx->timeout_lock) +{ + struct io_timeout_data *io; + struct io_kiocb *req; + bool found = false; + + list_for_each_entry(req, &ctx->timeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) + break; + } + if (!found) + return ERR_PTR(-ENOENT); + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return ERR_PTR(-EALREADY); + list_del_init(&req->timeout.list); + return req; +} + +static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) + __must_hold(&ctx->completion_lock) + __must_hold(&ctx->timeout_lock) +{ + struct io_kiocb *req = io_timeout_extract(ctx, user_data); + + if (IS_ERR(req)) + return PTR_ERR(req); + + req_set_fail(req); + io_fill_cqe_req(req, -ECANCELED, 0); + io_put_req_deferred(req); + return 0; +} + +static clockid_t io_timeout_get_clock(struct io_timeout_data *data) +{ + switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + +static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_timeout_data *io; + struct io_kiocb *req; + bool found = false; + + list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) + break; + } + if (!found) + return -ENOENT; + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return -EALREADY; + hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); + io->timer.function = io_link_timeout_fn; + hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_timeout_data *data; + + if (IS_ERR(req)) + return PTR_ERR(req); + + req->timeout.off = 0; /* noseq */ + data = req->async_data; + list_add_tail(&req->timeout.list, &ctx->timeout_list); + hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +static int io_timeout_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_timeout_rem *tr = &req->timeout_rem; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) + return -EINVAL; + + tr->ltimeout = false; + tr->addr = READ_ONCE(sqe->addr); + tr->flags = READ_ONCE(sqe->timeout_flags); + if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { + if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) + tr->ltimeout = true; + if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) + return -EINVAL; + if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) + return -EFAULT; + } else if (tr->flags) { + /* timeout removal doesn't support flags */ + return -EINVAL; + } + + return 0; +} + +static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) +{ + return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS + : HRTIMER_MODE_REL; +} + +/* + * Remove or update an existing timeout command + */ +static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_timeout_rem *tr = &req->timeout_rem; + struct io_ring_ctx *ctx = req->ctx; + int ret; + + if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, tr->addr); + spin_unlock_irq(&ctx->timeout_lock); + spin_unlock(&ctx->completion_lock); + } else { + enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); + + spin_lock_irq(&ctx->timeout_lock); + if (tr->ltimeout) + ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); + else + ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); + spin_unlock_irq(&ctx->timeout_lock); + } + + if (ret < 0) + req_set_fail(req); + io_req_complete_post(req, ret, 0); + return 0; +} + +static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool is_timeout_link) +{ + struct io_timeout_data *data; + unsigned flags; + u32 off = READ_ONCE(sqe->off); + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || + sqe->splice_fd_in) + return -EINVAL; + if (off && is_timeout_link) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + return -EINVAL; + /* more than one clock specified is invalid, obviously */ + if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + + INIT_LIST_HEAD(&req->timeout.list); + req->timeout.off = off; + if (unlikely(off && !req->ctx->off_timeout_used)) + req->ctx->off_timeout_used = true; + + if (!req->async_data && io_alloc_async_data(req)) + return -ENOMEM; + + data = req->async_data; + data->req = req; + data->flags = flags; + + if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) + return -EFAULT; + + INIT_LIST_HEAD(&req->timeout.list); + data->mode = io_translate_timeout_mode(flags); + hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); + + if (is_timeout_link) { + struct io_submit_link *link = &req->ctx->submit_state.link; + + if (!link->head) + return -EINVAL; + if (link->last->opcode == IORING_OP_LINK_TIMEOUT) + return -EINVAL; + req->timeout.head = link->last; + link->last->flags |= REQ_F_ARM_LTIMEOUT; + } + return 0; +} + +static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_timeout_data *data = req->async_data; + struct list_head *entry; + u32 tail, off = req->timeout.off; + + spin_lock_irq(&ctx->timeout_lock); + + /* + * sqe->off holds how many events that need to occur for this + * timeout event to be satisfied. If it isn't set, then this is + * a pure timeout request, sequence isn't used. + */ + if (io_is_timeout_noseq(req)) { + entry = ctx->timeout_list.prev; + goto add; + } + + tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + req->timeout.target_seq = tail + off; + + /* Update the last seq here in case io_flush_timeouts() hasn't. + * This is safe because ->completion_lock is held, and submissions + * and completions are never mixed in the same ->completion_lock section. + */ + ctx->cq_last_tm_flush = tail; + + /* + * Insertion sort, ensuring the first entry in the list is always + * the one we need first. + */ + list_for_each_prev(entry, &ctx->timeout_list) { + struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, + timeout.list); + + if (io_is_timeout_noseq(nxt)) + continue; + /* nxt.seq is behind @tail, otherwise would've been completed */ + if (off >= nxt->timeout.target_seq - tail) + break; + } +add: + list_add(&req->timeout.list, entry); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); + spin_unlock_irq(&ctx->timeout_lock); + return 0; +} + +struct io_cancel_data { + struct io_ring_ctx *ctx; + u64 user_data; +}; + +static bool io_cancel_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_cancel_data *cd = data; + + return req->ctx == cd->ctx && req->user_data == cd->user_data; +} + +static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, + struct io_ring_ctx *ctx) +{ + struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; + enum io_wq_cancel cancel_ret; + int ret = 0; + + if (!tctx || !tctx->io_wq) + return -ENOENT; + + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); + switch (cancel_ret) { + case IO_WQ_CANCEL_OK: + ret = 0; + break; + case IO_WQ_CANCEL_RUNNING: + ret = -EALREADY; + break; + case IO_WQ_CANCEL_NOTFOUND: + ret = -ENOENT; + break; + } + + return ret; +} + +static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); + + ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); + if (ret != -ENOENT) + return ret; + + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, sqe_addr); + spin_unlock_irq(&ctx->timeout_lock); + if (ret != -ENOENT) + goto out; + ret = io_poll_cancel(ctx, sqe_addr, false); +out: + spin_unlock(&ctx->completion_lock); + return ret; +} + +static int io_async_cancel_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags || + sqe->splice_fd_in) + return -EINVAL; + + req->cancel.addr = READ_ONCE(sqe->addr); + return 0; +} + +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + u64 sqe_addr = req->cancel.addr; + struct io_tctx_node *node; + int ret; + + ret = io_try_cancel_userdata(req, sqe_addr); + if (ret != -ENOENT) + goto done; + + /* slow path, try all io-wq's */ + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENOENT; + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); + if (ret != -ENOENT) + break; + } + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); +done: + if (ret < 0) + req_set_fail(req); + io_req_complete_post(req, ret, 0); + return 0; +} + +static int io_rsrc_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + req->rsrc_update.offset = READ_ONCE(sqe->off); + req->rsrc_update.nr_args = READ_ONCE(sqe->len); + if (!req->rsrc_update.nr_args) + return -EINVAL; + req->rsrc_update.arg = READ_ONCE(sqe->addr); + return 0; +} + +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_rsrc_update2 up; + int ret; + + up.offset = req->rsrc_update.offset; + up.data = req->rsrc_update.arg; + up.nr = 0; + up.tags = 0; + up.resv = 0; + up.resv2 = 0; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, + &up, req->rsrc_update.nr_args); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + + if (ret < 0) + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + +static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + switch (req->opcode) { + case IORING_OP_NOP: + return 0; + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_READ: + return io_read_prep(req, sqe); + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + case IORING_OP_WRITE: + return io_write_prep(req, sqe); + case IORING_OP_POLL_ADD: + return io_poll_add_prep(req, sqe); + case IORING_OP_POLL_REMOVE: + return io_poll_update_prep(req, sqe); + case IORING_OP_FSYNC: + return io_fsync_prep(req, sqe); + case IORING_OP_SYNC_FILE_RANGE: + return io_sfr_prep(req, sqe); + case IORING_OP_SENDMSG: + case IORING_OP_SEND: + return io_sendmsg_prep(req, sqe); + case IORING_OP_RECVMSG: + case IORING_OP_RECV: + return io_recvmsg_prep(req, sqe); + case IORING_OP_CONNECT: + return io_connect_prep(req, sqe); + case IORING_OP_TIMEOUT: + return io_timeout_prep(req, sqe, false); + case IORING_OP_TIMEOUT_REMOVE: + return io_timeout_remove_prep(req, sqe); + case IORING_OP_ASYNC_CANCEL: + return io_async_cancel_prep(req, sqe); + case IORING_OP_LINK_TIMEOUT: + return io_timeout_prep(req, sqe, true); + case IORING_OP_ACCEPT: + return io_accept_prep(req, sqe); + case IORING_OP_FALLOCATE: + return io_fallocate_prep(req, sqe); + case IORING_OP_OPENAT: + return io_openat_prep(req, sqe); + case IORING_OP_CLOSE: + return io_close_prep(req, sqe); + case IORING_OP_FILES_UPDATE: + return io_rsrc_update_prep(req, sqe); + case IORING_OP_STATX: + return io_statx_prep(req, sqe); + case IORING_OP_FADVISE: + return io_fadvise_prep(req, sqe); + case IORING_OP_MADVISE: + return io_madvise_prep(req, sqe); + case IORING_OP_OPENAT2: + return io_openat2_prep(req, sqe); + case IORING_OP_EPOLL_CTL: + return io_epoll_ctl_prep(req, sqe); + case IORING_OP_SPLICE: + return io_splice_prep(req, sqe); + case IORING_OP_PROVIDE_BUFFERS: + return io_provide_buffers_prep(req, sqe); + case IORING_OP_REMOVE_BUFFERS: + return io_remove_buffers_prep(req, sqe); + case IORING_OP_TEE: + return io_tee_prep(req, sqe); + case IORING_OP_SHUTDOWN: + return io_shutdown_prep(req, sqe); + case IORING_OP_RENAMEAT: + return io_renameat_prep(req, sqe); + case IORING_OP_UNLINKAT: + return io_unlinkat_prep(req, sqe); + } + + printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", + req->opcode); + return -EINVAL; +} + +static int io_req_prep_async(struct io_kiocb *req) +{ + if (!io_op_defs[req->opcode].needs_async_setup) + return 0; + if (WARN_ON_ONCE(req->async_data)) + return -EFAULT; + if (io_alloc_async_data(req)) + return -EAGAIN; + + switch (req->opcode) { + case IORING_OP_READV: + return io_rw_prep_async(req, READ); + case IORING_OP_WRITEV: + return io_rw_prep_async(req, WRITE); + case IORING_OP_SENDMSG: + return io_sendmsg_prep_async(req); + case IORING_OP_RECVMSG: + return io_recvmsg_prep_async(req); + case IORING_OP_CONNECT: + return io_connect_prep_async(req); + } + printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", + req->opcode); + return -EFAULT; +} + +static u32 io_get_sequence(struct io_kiocb *req) +{ + u32 seq = req->ctx->cached_sq_head; + + /* need original cached_sq_head, but it was increased for each req */ + io_for_each_link(req, req) + seq--; + return seq; +} + +static bool io_drain_req(struct io_kiocb *req) +{ + struct io_kiocb *pos; + struct io_ring_ctx *ctx = req->ctx; + struct io_defer_entry *de; + int ret; + u32 seq; + + if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); + return true; + } + + /* + * If we need to drain a request in the middle of a link, drain the + * head request and the next request/link after the current link. + * Considering sequential execution of links, IOSQE_IO_DRAIN will be + * maintained for every request of our link. + */ + if (ctx->drain_next) { + req->flags |= REQ_F_IO_DRAIN; + ctx->drain_next = false; + } + /* not interested in head, start from the first linked */ + io_for_each_link(pos, req->link) { + if (pos->flags & REQ_F_IO_DRAIN) { + ctx->drain_next = true; + req->flags |= REQ_F_IO_DRAIN; + break; + } + } + + /* Still need defer if there is pending req in defer list. */ + spin_lock(&ctx->completion_lock); + if (likely(list_empty_careful(&ctx->defer_list) && + !(req->flags & REQ_F_IO_DRAIN))) { + spin_unlock(&ctx->completion_lock); + ctx->drain_active = false; + return false; + } + spin_unlock(&ctx->completion_lock); + + seq = io_get_sequence(req); + /* Still a chance to pass the sequence check */ + if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) + return false; + + ret = io_req_prep_async(req); + if (ret) + goto fail; + io_prep_async_link(req); + de = kmalloc(sizeof(*de), GFP_KERNEL); + if (!de) { + ret = -ENOMEM; +fail: + io_req_complete_failed(req, ret); + return true; + } + + spin_lock(&ctx->completion_lock); + if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { + spin_unlock(&ctx->completion_lock); + kfree(de); + io_queue_async_work(req, NULL); + return true; + } + + trace_io_uring_defer(ctx, req, req->user_data); + de->req = req; + de->seq = seq; + list_add_tail(&de->list, &ctx->defer_list); + spin_unlock(&ctx->completion_lock); + return true; +} + +static void io_clean_op(struct io_kiocb *req) +{ + if (req->flags & REQ_F_BUFFER_SELECTED) { + switch (req->opcode) { + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_READ: + kfree((void *)(unsigned long)req->rw.addr); + break; + case IORING_OP_RECVMSG: + case IORING_OP_RECV: + kfree(req->sr_msg.kbuf); + break; + } + } + + if (req->flags & REQ_F_NEED_CLEANUP) { + switch (req->opcode) { + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_READ: + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + case IORING_OP_WRITE: { + struct io_async_rw *io = req->async_data; + + kfree(io->free_iovec); + break; + } + case IORING_OP_RECVMSG: + case IORING_OP_SENDMSG: { + struct io_async_msghdr *io = req->async_data; + + kfree(io->free_iov); + break; + } + case IORING_OP_OPENAT: + case IORING_OP_OPENAT2: + if (req->open.filename) + putname(req->open.filename); + break; + case IORING_OP_RENAMEAT: + putname(req->rename.oldpath); + putname(req->rename.newpath); + break; + case IORING_OP_UNLINKAT: + putname(req->unlink.filename); + break; + } + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + kfree(req->apoll->double_poll); + kfree(req->apoll); + req->apoll = NULL; + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_uring_task *tctx = req->task->io_uring; + + atomic_dec(&tctx->inflight_tracked); + } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + + req->flags &= ~IO_REQ_CLEAN_FLAGS; +} + +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + const struct cred *creds = NULL; + int ret; + + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); + + switch (req->opcode) { + case IORING_OP_NOP: + ret = io_nop(req, issue_flags); + break; + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_READ: + ret = io_read(req, issue_flags); + break; + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + case IORING_OP_WRITE: + ret = io_write(req, issue_flags); + break; + case IORING_OP_FSYNC: + ret = io_fsync(req, issue_flags); + break; + case IORING_OP_POLL_ADD: + ret = io_poll_add(req, issue_flags); + break; + case IORING_OP_POLL_REMOVE: + ret = io_poll_update(req, issue_flags); + break; + case IORING_OP_SYNC_FILE_RANGE: + ret = io_sync_file_range(req, issue_flags); + break; + case IORING_OP_SENDMSG: + ret = io_sendmsg(req, issue_flags); + break; + case IORING_OP_SEND: + ret = io_send(req, issue_flags); + break; + case IORING_OP_RECVMSG: + ret = io_recvmsg(req, issue_flags); + break; + case IORING_OP_RECV: + ret = io_recv(req, issue_flags); + break; + case IORING_OP_TIMEOUT: + ret = io_timeout(req, issue_flags); + break; + case IORING_OP_TIMEOUT_REMOVE: + ret = io_timeout_remove(req, issue_flags); + break; + case IORING_OP_ACCEPT: + ret = io_accept(req, issue_flags); + break; + case IORING_OP_CONNECT: + ret = io_connect(req, issue_flags); + break; + case IORING_OP_ASYNC_CANCEL: + ret = io_async_cancel(req, issue_flags); + break; + case IORING_OP_FALLOCATE: + ret = io_fallocate(req, issue_flags); + break; + case IORING_OP_OPENAT: + ret = io_openat(req, issue_flags); + break; + case IORING_OP_CLOSE: + ret = io_close(req, issue_flags); + break; + case IORING_OP_FILES_UPDATE: + ret = io_files_update(req, issue_flags); + break; + case IORING_OP_STATX: + ret = io_statx(req, issue_flags); + break; + case IORING_OP_FADVISE: + ret = io_fadvise(req, issue_flags); + break; + case IORING_OP_MADVISE: + ret = io_madvise(req, issue_flags); + break; + case IORING_OP_OPENAT2: + ret = io_openat2(req, issue_flags); + break; + case IORING_OP_EPOLL_CTL: + ret = io_epoll_ctl(req, issue_flags); + break; + case IORING_OP_SPLICE: + ret = io_splice(req, issue_flags); + break; + case IORING_OP_PROVIDE_BUFFERS: + ret = io_provide_buffers(req, issue_flags); + break; + case IORING_OP_REMOVE_BUFFERS: + ret = io_remove_buffers(req, issue_flags); + break; + case IORING_OP_TEE: + ret = io_tee(req, issue_flags); + break; + case IORING_OP_SHUTDOWN: + ret = io_shutdown(req, issue_flags); + break; + case IORING_OP_RENAMEAT: + ret = io_renameat(req, issue_flags); + break; + case IORING_OP_UNLINKAT: + ret = io_unlinkat(req, issue_flags); + break; + default: + ret = -EINVAL; + break; + } + + if (creds) + revert_creds(creds); + if (ret) + return ret; + /* If the op doesn't have a file, we're not polling for it */ + if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) + io_iopoll_req_issued(req); + + return 0; +} + +static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + req = io_put_req_find_next(req); + return req ? &req->work : NULL; +} + +static void io_wq_submit_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_kiocb *timeout; + int ret = 0; + + /* one will be dropped by ->io_free_work() after returning to io-wq */ + if (!(req->flags & REQ_F_REFCOUNT)) + __io_req_set_refcount(req, 2); + else + req_ref_get(req); + + timeout = io_prep_linked_timeout(req); + if (timeout) + io_queue_linked_timeout(timeout); + + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ + if (work->flags & IO_WQ_WORK_CANCEL) + ret = -ECANCELED; + + if (!ret) { + do { + ret = io_issue_sqe(req, 0); + /* + * We can get EAGAIN for polled IO even though we're + * forcing a sync submission from here, since we can't + * wait for request slots on the block side. + */ + if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL)) + break; + if (io_wq_worker_stopped()) + break; + /* + * If REQ_F_NOWAIT is set, then don't wait or retry with + * poll. -EAGAIN is final for that case. + */ + if (req->flags & REQ_F_NOWAIT) + break; + + cond_resched(); + } while (1); + } + + /* avoid locking problems by failing it from a clean context */ + if (ret) + io_req_task_queue_fail(req, ret); +} + +static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table, + unsigned i) +{ + return &table->files[i]; +} + +static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, + int index) +{ + struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index); + + return (struct file *) (slot->file_ptr & FFS_MASK); +} + +static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) +{ + unsigned long file_ptr = (unsigned long) file; + + if (__io_file_supports_nowait(file, READ)) + file_ptr |= FFS_ASYNC_READ; + if (__io_file_supports_nowait(file, WRITE)) + file_ptr |= FFS_ASYNC_WRITE; + if (S_ISREG(file_inode(file)->i_mode)) + file_ptr |= FFS_ISREG; + file_slot->file_ptr = file_ptr; +} + +static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd, + unsigned int issue_flags) +{ + struct file *file = NULL; + unsigned long file_ptr; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) + goto out; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + file_ptr &= ~FFS_MASK; + /* mask in overlapping REQ_F and FFS bits */ + req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); + io_req_set_rsrc_node(req); +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return file; +} + +static struct file *io_file_get_normal(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd) +{ + struct file *file = fget(fd); + + trace_io_uring_file_get(ctx, fd); + + /* we don't allow fixed io_uring files */ + if (file && unlikely(file->f_op == &io_uring_fops)) + io_req_track_inflight(req); + return file; +} + +static inline struct file *io_file_get(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags) +{ + if (fixed) + return io_file_get_fixed(ctx, req, fd, issue_flags); + else + return io_file_get_normal(ctx, req, fd); +} + +static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) +{ + struct io_kiocb *prev = req->timeout.prev; + int ret = -ENOENT; + + if (prev) { + if (!(req->task->flags & PF_EXITING)) + ret = io_try_cancel_userdata(req, prev->user_data); + io_req_complete_post(req, ret ?: -ETIME, 0); + io_put_req(prev); + } else { + io_req_complete_post(req, -ETIME, 0); + } +} + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) +{ + struct io_timeout_data *data = container_of(timer, + struct io_timeout_data, timer); + struct io_kiocb *prev, *req = data->req; + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->timeout_lock, flags); + prev = req->timeout.head; + req->timeout.head = NULL; + + /* + * We don't expect the list to be empty, that will only happen if we + * race with the completion of the linked work. + */ + if (prev) { + io_remove_next_linked(prev); + if (!req_ref_inc_not_zero(prev)) + prev = NULL; + } + list_del(&req->timeout.list); + req->timeout.prev = prev; + spin_unlock_irqrestore(&ctx->timeout_lock, flags); + + req->io_task_work.func = io_req_task_link_timeout; + io_req_task_work_add(req); + return HRTIMER_NORESTART; +} + +static void io_queue_linked_timeout(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + /* + * If the back reference is NULL, then our linked request finished + * before we got a chance to setup the timer + */ + if (req->timeout.head) { + struct io_timeout_data *data = req->async_data; + + data->timer.function = io_link_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), + data->mode); + list_add_tail(&req->timeout.list, &ctx->ltimeout_list); + } + spin_unlock_irq(&ctx->timeout_lock); + /* drop submission reference */ + io_put_req(req); +} + +static void __io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + struct io_kiocb *linked_timeout; + int ret; + +issue_sqe: + ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + + /* + * We async punt it if the file wasn't marked NOWAIT, or if the file + * doesn't support non-blocking read/write attempts + */ + if (likely(!ret)) { + if (req->flags & REQ_F_COMPLETE_INLINE) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + return; + } + + linked_timeout = io_prep_linked_timeout(req); + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { + linked_timeout = io_prep_linked_timeout(req); + + switch (io_arm_poll_handler(req)) { + case IO_APOLL_READY: + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + goto issue_sqe; + case IO_APOLL_ABORTED: + /* + * Queued up for async execution, worker will release + * submit reference when the iocb is actually submitted. + */ + io_queue_async_work(req, NULL); + break; + } + + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + } else { + io_req_complete_failed(req, ret); + } +} + +static inline void io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + if (unlikely(req->ctx->drain_active) && io_drain_req(req)) + return; + + if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) { + __io_queue_sqe(req); + } else if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); + } else { + int ret = io_req_prep_async(req); + + if (unlikely(ret)) + io_req_complete_failed(req, ret); + else + io_queue_async_work(req, NULL); + } +} + +/* + * Check SQE restrictions (opcode and flags). + * + * Returns 'true' if SQE is allowed, 'false' otherwise. + */ +static inline bool io_check_restriction(struct io_ring_ctx *ctx, + struct io_kiocb *req, + unsigned int sqe_flags) +{ + if (likely(!ctx->restricted)) + return true; + + if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) + return false; + + if ((sqe_flags & ctx->restrictions.sqe_flags_required) != + ctx->restrictions.sqe_flags_required) + return false; + + if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | + ctx->restrictions.sqe_flags_required)) + return false; + + return true; +} + +static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state; + unsigned int sqe_flags; + int personality, ret = 0; + + /* req is partially pre-initialised, see io_preinit_req() */ + req->opcode = READ_ONCE(sqe->opcode); + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags = sqe_flags = READ_ONCE(sqe->flags); + req->user_data = READ_ONCE(sqe->user_data); + req->file = NULL; + req->fixed_rsrc_refs = NULL; + req->task = current; + + /* enforce forwards compatibility on users */ + if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) + return -EINVAL; + if (unlikely(req->opcode >= IORING_OP_LAST)) + return -EINVAL; + if (!io_check_restriction(ctx, req, sqe_flags)) + return -EACCES; + + if ((sqe_flags & IOSQE_BUFFER_SELECT) && + !io_op_defs[req->opcode].buffer_select) + return -EOPNOTSUPP; + if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) + ctx->drain_active = true; + + personality = READ_ONCE(sqe->personality); + if (personality) { + req->creds = xa_load(&ctx->personalities, personality); + if (!req->creds) + return -EINVAL; + get_cred(req->creds); + req->flags |= REQ_F_CREDS; + } + state = &ctx->submit_state; + + /* + * Plug now if we have more than 1 IO left after this, and the target + * is potentially a read/write to block based storage. + */ + if (!state->plug_started && state->ios_left > 1 && + io_op_defs[req->opcode].plug) { + blk_start_plug(&state->plug); + state->plug_started = true; + } + + if (io_op_defs[req->opcode].needs_file) { + req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), + (sqe_flags & IOSQE_FIXED_FILE), + IO_URING_F_NONBLOCK); + if (unlikely(!req->file)) + ret = -EBADF; + } + + state->ios_left--; + return ret; +} + +static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_link *link = &ctx->submit_state.link; + int ret; + + ret = io_init_req(ctx, req, sqe); + if (unlikely(ret)) { +fail_req: + /* fail even hard links since we don't submit */ + if (link->head) { + /* + * we can judge a link req is failed or cancelled by if + * REQ_F_FAIL is set, but the head is an exception since + * it may be set REQ_F_FAIL because of other req's failure + * so let's leverage req->result to distinguish if a head + * is set REQ_F_FAIL because of its failure or other req's + * failure so that we can set the correct ret code for it. + * init result here to avoid affecting the normal path. + */ + if (!(link->head->flags & REQ_F_FAIL)) + req_fail_link_node(link->head, -ECANCELED); + } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { + /* + * the current req is a normal req, we should return + * error and thus break the submittion loop. + */ + io_req_complete_failed(req, ret); + return ret; + } + req_fail_link_node(req, ret); + } else { + ret = io_req_prep(req, sqe); + if (unlikely(ret)) + goto fail_req; + } + + /* don't need @sqe from now on */ + trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data, + req->flags, true, + ctx->flags & IORING_SETUP_SQPOLL); + + /* + * If we already have a head request, queue this one for async + * submittal once the head completes. If we don't have a head but + * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be + * submitted sync once the chain is complete. If none of those + * conditions are true (normal request), then just queue it. + */ + if (link->head) { + struct io_kiocb *head = link->head; + + if (!(req->flags & REQ_F_FAIL)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) { + req_fail_link_node(req, ret); + if (!(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + } + } + trace_io_uring_link(ctx, req, head); + link->last->link = req; + link->last = req; + + /* last request of a link, enqueue the link */ + if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { + link->head = NULL; + io_queue_sqe(head); + } + } else { + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + link->head = req; + link->last = req; + } else { + io_queue_sqe(req); + } + } + + return 0; +} + +/* + * Batched submission is done, ensure local IO is flushed out. + */ +static void io_submit_state_end(struct io_submit_state *state, + struct io_ring_ctx *ctx) +{ + if (state->link.head) + io_queue_sqe(state->link.head); + if (state->compl_nr) + io_submit_flush_completions(ctx); + if (state->plug_started) + blk_finish_plug(&state->plug); +} + +/* + * Start submission side cache. + */ +static void io_submit_state_start(struct io_submit_state *state, + unsigned int max_ios) +{ + state->plug_started = false; + state->ios_left = max_ios; + /* set only head, no need to init link_last in advance */ + state->link.head = NULL; +} + +static void io_commit_sqring(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* + * Ensure any loads from the SQEs are done at this point, + * since once we write the new head, the application could + * write new data to them. + */ + smp_store_release(&rings->sq.head, ctx->cached_sq_head); +} + +/* + * Fetch an sqe, if one is available. Note this returns a pointer to memory + * that is mapped by userspace. This means that care needs to be taken to + * ensure that reads are stable, as we cannot rely on userspace always + * being a good citizen. If members of the sqe are validated and then later + * used, it's important that those reads are done through READ_ONCE() to + * prevent a re-load down the line. + */ +static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) +{ + unsigned head, mask = ctx->sq_entries - 1; + unsigned sq_idx = ctx->cached_sq_head++ & mask; + + /* + * The cached sq head (or cq tail) serves two purposes: + * + * 1) allows us to batch the cost of updating the user visible + * head updates. + * 2) allows the kernel side to track the head on its own, even + * though the application is the one updating it. + */ + head = READ_ONCE(ctx->sq_array[sq_idx]); + if (likely(head < ctx->sq_entries)) + return &ctx->sq_sqes[head]; + + /* drop invalid entries */ + ctx->cq_extra--; + WRITE_ONCE(ctx->rings->sq_dropped, + READ_ONCE(ctx->rings->sq_dropped) + 1); + return NULL; +} + +static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) + __must_hold(&ctx->uring_lock) +{ + int submitted = 0; + + /* make sure SQ entry isn't read before tail */ + nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); + if (!percpu_ref_tryget_many(&ctx->refs, nr)) + return -EAGAIN; + io_get_task_refs(nr); + + io_submit_state_start(&ctx->submit_state, nr); + while (submitted < nr) { + const struct io_uring_sqe *sqe; + struct io_kiocb *req; + + req = io_alloc_req(ctx); + if (unlikely(!req)) { + if (!submitted) + submitted = -EAGAIN; + break; + } + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + list_add(&req->inflight_entry, &ctx->submit_state.free_list); + break; + } + /* will complete beyond this point, count as submitted */ + submitted++; + if (io_submit_sqe(ctx, req, sqe)) + break; + } + + if (unlikely(submitted != nr)) { + int ref_used = (submitted == -EAGAIN) ? 0 : submitted; + int unused = nr - ref_used; + + current->io_uring->cached_refs += unused; + percpu_ref_put_many(&ctx->refs, unused); + } + + io_submit_state_end(&ctx->submit_state, ctx); + /* Commit SQ ring head once we've consumed and submitted all SQEs */ + io_commit_sqring(ctx); + + return submitted; +} + +static inline bool io_sqd_events_pending(struct io_sq_data *sqd) +{ + return READ_ONCE(sqd->state); +} + +static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) +{ + /* Tell userspace we may need a wakeup call */ + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); +} + +static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) +{ + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); +} + +static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) +{ + unsigned int to_submit; + int ret = 0; + + to_submit = io_sqring_entries(ctx); + /* if we're handling multiple rings, cap submit size for fairness */ + if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) + to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; + + if (!list_empty(&ctx->iopoll_list) || to_submit) { + unsigned nr_events = 0; + const struct cred *creds = NULL; + + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); + + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->iopoll_list)) + io_do_iopoll(ctx, &nr_events, 0); + + /* + * Don't submit if refs are dying, good for io_uring_register(), + * but also it is relied upon by io_ring_exit_work() + */ + if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && + !(ctx->flags & IORING_SETUP_R_DISABLED)) + ret = io_submit_sqes(ctx, to_submit); + mutex_unlock(&ctx->uring_lock); + + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) + wake_up(&ctx->sqo_sq_wait); + if (creds) + revert_creds(creds); + } + + return ret; +} + +static void io_sqd_update_thread_idle(struct io_sq_data *sqd) +{ + struct io_ring_ctx *ctx; + unsigned sq_thread_idle = 0; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); + sqd->sq_thread_idle = sq_thread_idle; +} + +static bool io_sqd_handle_event(struct io_sq_data *sqd) +{ + bool did_sig = false; + struct ksignal ksig; + + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + mutex_unlock(&sqd->lock); + if (signal_pending(current)) + did_sig = get_signal(&ksig); + cond_resched(); + mutex_lock(&sqd->lock); + } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); +} + +static int io_sq_thread(void *data) +{ + struct io_sq_data *sqd = data; + struct io_ring_ctx *ctx; + unsigned long timeout = 0; + char buf[TASK_COMM_LEN]; + DEFINE_WAIT(wait); + + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); + set_task_comm(current, buf); + + if (sqd->sq_cpu != -1) + set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); + else + set_cpus_allowed_ptr(current, cpu_online_mask); + current->flags |= PF_NO_SETAFFINITY; + + mutex_lock(&sqd->lock); + while (1) { + bool cap_entries, sqt_spin = false; + + if (io_sqd_events_pending(sqd) || signal_pending(current)) { + if (io_sqd_handle_event(sqd)) + break; + timeout = jiffies + sqd->sq_thread_idle; + } + + cap_entries = !list_is_singular(&sqd->ctx_list); + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + int ret = __io_sq_thread(ctx, cap_entries); + + if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) + sqt_spin = true; + } + if (io_run_task_work()) + sqt_spin = true; + + if (sqt_spin || !time_after(jiffies, timeout)) { + cond_resched(); + if (sqt_spin) + timeout = jiffies + sqd->sq_thread_idle; + continue; + } + + prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); + if (!io_sqd_events_pending(sqd) && !current->task_works) { + bool needs_sched = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + io_ring_set_wakeup_flag(ctx); + + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !list_empty_careful(&ctx->iopoll_list)) { + needs_sched = false; + break; + } + if (io_sqring_entries(ctx)) { + needs_sched = false; + break; + } + } + + if (needs_sched) { + mutex_unlock(&sqd->lock); + schedule(); + mutex_lock(&sqd->lock); + } + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_ring_clear_wakeup_flag(ctx); + } + + finish_wait(&sqd->wait, &wait); + timeout = jiffies + sqd->sq_thread_idle; + } + + io_uring_cancel_generic(true, sqd); + sqd->thread = NULL; + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_ring_set_wakeup_flag(ctx); + io_run_task_work(); + mutex_unlock(&sqd->lock); + + complete(&sqd->exited); + do_exit(0); +} + +struct io_wait_queue { + struct wait_queue_entry wq; + struct io_ring_ctx *ctx; + unsigned cq_tail; + unsigned nr_timeouts; +}; + +static inline bool io_should_wake(struct io_wait_queue *iowq) +{ + struct io_ring_ctx *ctx = iowq->ctx; + int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; + + /* + * Wake up if we have enough events, or if a timeout occurred since we + * started waiting. For timeouts, we always want to return to userspace, + * regardless of event count. + */ + return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; +} + +static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, + int wake_flags, void *key) +{ + struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, + wq); + + /* + * Cannot safely flush overflowed CQEs from here, ensure we wake up + * the task, and the next invocation will do it. + */ + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) + return autoremove_wake_function(curr, mode, wake_flags, key); + return -1; +} + +static int io_run_task_work_sig(void) +{ + if (io_run_task_work()) + return 1; + if (!signal_pending(current)) + return 0; + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + return -ERESTARTSYS; + return -EINTR; +} + +static bool current_pending_io(void) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx) + return false; + return percpu_counter_read_positive(&tctx->inflight); +} + +/* when returns >0, the caller should retry */ +static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + ktime_t *timeout) +{ + int io_wait, ret; + + /* make sure we run task_work before checking for signals */ + ret = io_run_task_work_sig(); + if (ret || io_should_wake(iowq)) + return ret; + /* let the caller flush overflows, retry */ + if (test_bit(0, &ctx->check_cq_overflow)) + return 1; + + /* + * Mark us as being in io_wait if we have pending requests, so cpufreq + * can take into account that the task is waiting for IO - turns out + * to be important for low QD IO. + */ + io_wait = current->in_iowait; + if (current_pending_io()) + current->in_iowait = 1; + ret = 1; + if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) + ret = -ETIME; + current->in_iowait = io_wait; + return ret; +} + +/* + * Wait until events become available, if we don't already have some. The + * application must reap them itself, as they reside on the shared cq ring. + */ +static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, + const sigset_t __user *sig, size_t sigsz, + struct __kernel_timespec __user *uts) +{ + struct io_wait_queue iowq; + struct io_rings *rings = ctx->rings; + ktime_t timeout = KTIME_MAX; + int ret; + + do { + io_cqring_overflow_flush(ctx); + if (io_cqring_events(ctx) >= min_events) + return 0; + if (!io_run_task_work()) + break; + } while (1); + + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + + if (sig) { +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + sigsz); + else +#endif + ret = set_user_sigmask(sig, sigsz); + + if (ret) + return ret; + } + + init_waitqueue_func_entry(&iowq.wq, io_wake_function); + iowq.wq.private = current; + INIT_LIST_HEAD(&iowq.wq.entry); + iowq.ctx = ctx; + iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; + + trace_io_uring_cqring_wait(ctx, min_events); + do { + /* if we can't even flush overflow, don't wait for more */ + if (!io_cqring_overflow_flush(ctx)) { + ret = -EBUSY; + break; + } + prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, + TASK_INTERRUPTIBLE); + ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); + finish_wait(&ctx->cq_wait, &iowq.wq); + cond_resched(); + } while (ret > 0); + + restore_saved_sigmask_unless(ret == -EINTR); + + return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; +} + +static void io_free_page_table(void **table, size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + + for (i = 0; i < nr_tables; i++) + kfree(table[i]); + kfree(table); +} + +static void **io_alloc_page_table(size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + size_t init_size = size; + void **table; + + table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); + if (!table) + return NULL; + + for (i = 0; i < nr_tables; i++) { + unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + + table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); + if (!table[i]) { + io_free_page_table(table, init_size); + return NULL; + } + size -= this_size; + } + return table; +} + +static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) +{ + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); +} + +static void io_rsrc_node_ref_zero(struct percpu_ref *ref) +{ + struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); + struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; + bool first_add = false; + unsigned long delay = HZ; + + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); + node->done = true; + + /* if we are mid-quiesce then do not delay */ + if (node->rsrc_data->quiesce) + delay = 0; + + while (!list_empty(&ctx->rsrc_ref_list)) { + node = list_first_entry(&ctx->rsrc_ref_list, + struct io_rsrc_node, node); + /* recycle ref nodes in order */ + if (!node->done) + break; + list_del(&node->node); + first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); + } + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); + + if (first_add) + mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); +} + +static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) +{ + struct io_rsrc_node *ref_node; + + ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); + if (!ref_node) + return NULL; + + if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, + 0, GFP_KERNEL)) { + kfree(ref_node); + return NULL; + } + INIT_LIST_HEAD(&ref_node->node); + INIT_LIST_HEAD(&ref_node->rsrc_list); + ref_node->done = false; + return ref_node; +} + +static void io_rsrc_node_switch(struct io_ring_ctx *ctx, + struct io_rsrc_data *data_to_kill) +{ + WARN_ON_ONCE(!ctx->rsrc_backup_node); + WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); + + if (data_to_kill) { + struct io_rsrc_node *rsrc_node = ctx->rsrc_node; + + rsrc_node->rsrc_data = data_to_kill; + spin_lock_irq(&ctx->rsrc_ref_lock); + list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); + spin_unlock_irq(&ctx->rsrc_ref_lock); + + atomic_inc(&data_to_kill->refs); + percpu_ref_kill(&rsrc_node->refs); + ctx->rsrc_node = NULL; + } + + if (!ctx->rsrc_node) { + ctx->rsrc_node = ctx->rsrc_backup_node; + ctx->rsrc_backup_node = NULL; + } +} + +static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) +{ + if (ctx->rsrc_backup_node) + return 0; + ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx); + return ctx->rsrc_backup_node ? 0 : -ENOMEM; +} + +static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx) +{ + int ret; + + /* As we may drop ->uring_lock, other task may have started quiesce */ + if (data->quiesce) + return -ENXIO; + + data->quiesce = true; + do { + ret = io_rsrc_node_switch_start(ctx); + if (ret) + break; + io_rsrc_node_switch(ctx, data); + + /* kill initial ref, already quiesced if zero */ + if (atomic_dec_and_test(&data->refs)) + break; + mutex_unlock(&ctx->uring_lock); + flush_delayed_work(&ctx->rsrc_put_work); + ret = wait_for_completion_interruptible(&data->done); + if (!ret) { + mutex_lock(&ctx->uring_lock); + if (atomic_read(&data->refs) > 0) { + /* + * it has been revived by another thread while + * we were unlocked + */ + mutex_unlock(&ctx->uring_lock); + } else { + break; + } + } + + atomic_inc(&data->refs); + /* wait for all works potentially completing data->done */ + flush_delayed_work(&ctx->rsrc_put_work); + reinit_completion(&data->done); + + ret = io_run_task_work_sig(); + mutex_lock(&ctx->uring_lock); + } while (ret >= 0); + data->quiesce = false; + + return ret; +} + +static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) +{ + unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; + unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; + + return &data->tags[table_idx][off]; +} + +static void io_rsrc_data_free(struct io_rsrc_data *data) +{ + size_t size = data->nr * sizeof(data->tags[0][0]); + + if (data->tags) + io_free_page_table((void **)data->tags, size); + kfree(data); +} + +static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, + u64 __user *utags, unsigned nr, + struct io_rsrc_data **pdata) +{ + struct io_rsrc_data *data; + int ret = -ENOMEM; + unsigned i; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); + if (!data->tags) { + kfree(data); + return -ENOMEM; + } + + data->nr = nr; + data->ctx = ctx; + data->do_put = do_put; + if (utags) { + ret = -EFAULT; + for (i = 0; i < nr; i++) { + u64 *tag_slot = io_get_tag_slot(data, i); + + if (copy_from_user(tag_slot, &utags[i], + sizeof(*tag_slot))) + goto fail; + } + } + + atomic_set(&data->refs, 1); + init_completion(&data->done); + *pdata = data; + return 0; +fail: + io_rsrc_data_free(data); + return ret; +} + +static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) +{ + table->files = kvcalloc(nr_files, sizeof(table->files[0]), + GFP_KERNEL_ACCOUNT); + return !!table->files; +} + +static void io_free_file_tables(struct io_file_table *table) +{ + kvfree(table->files); + table->files = NULL; +} + +static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) { + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff *skb; + + while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) + kfree_skb(skb); + } +#else + int i; + + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file; + + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } +#endif + io_free_file_tables(&ctx->file_table); + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + ctx->nr_user_files = 0; +} + +static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_files; + int ret; + + if (!ctx->file_data) + return -ENXIO; + + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ + ctx->nr_user_files = 0; + ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); + ctx->nr_user_files = nr; + if (!ret) + __io_sqe_files_unregister(ctx); + return ret; +} + +static void io_sq_thread_unpark(struct io_sq_data *sqd) + __releases(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + /* + * Do the dance but not conditional clear_bit() because it'd race with + * other threads incrementing park_pending and setting the bit. + */ + clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + if (atomic_dec_return(&sqd->park_pending)) + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_unlock(&sqd->lock); +} + +static void io_sq_thread_park(struct io_sq_data *sqd) + __acquires(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + atomic_inc(&sqd->park_pending); + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); +} + +static void io_sq_thread_stop(struct io_sq_data *sqd) +{ + WARN_ON_ONCE(sqd->thread == current); + WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); + + set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); + mutex_unlock(&sqd->lock); + wait_for_completion(&sqd->exited); +} + +static void io_put_sq_data(struct io_sq_data *sqd) +{ + if (refcount_dec_and_test(&sqd->refs)) { + WARN_ON_ONCE(atomic_read(&sqd->park_pending)); + + io_sq_thread_stop(sqd); + kfree(sqd); + } +} + +static void io_sq_thread_finish(struct io_ring_ctx *ctx) +{ + struct io_sq_data *sqd = ctx->sq_data; + + if (sqd) { + io_sq_thread_park(sqd); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(sqd); + io_sq_thread_unpark(sqd); + + io_put_sq_data(sqd); + ctx->sq_data = NULL; + } +} + +static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) +{ + struct io_ring_ctx *ctx_attach; + struct io_sq_data *sqd; + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return ERR_PTR(-ENXIO); + if (f.file->f_op != &io_uring_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + ctx_attach = f.file->private_data; + sqd = ctx_attach->sq_data; + if (!sqd) { + fdput(f); + return ERR_PTR(-EINVAL); + } + if (sqd->task_tgid != current->tgid) { + fdput(f); + return ERR_PTR(-EPERM); + } + + refcount_inc(&sqd->refs); + fdput(f); + return sqd; +} + +static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, + bool *attached) +{ + struct io_sq_data *sqd; + + *attached = false; + if (p->flags & IORING_SETUP_ATTACH_WQ) { + sqd = io_attach_sq_data(p); + if (!IS_ERR(sqd)) { + *attached = true; + return sqd; + } + /* fall through for EPERM case, setup new sqd/task */ + if (PTR_ERR(sqd) != -EPERM) + return sqd; + } + + sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); + if (!sqd) + return ERR_PTR(-ENOMEM); + + atomic_set(&sqd->park_pending, 0); + refcount_set(&sqd->refs, 1); + INIT_LIST_HEAD(&sqd->ctx_list); + mutex_init(&sqd->lock); + init_waitqueue_head(&sqd->wait); + init_completion(&sqd->exited); + return sqd; +} + +#if defined(CONFIG_UNIX) +/* + * Ensure the UNIX gc is aware of our file set, so we are certain that + * the io_uring can be safely unregistered on process exit, even if we have + * loops in the file referencing. + */ +static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) +{ + struct sock *sk = ctx->ring_sock->sk; + struct scm_fp_list *fpl; + struct sk_buff *skb; + int i, nr_files; + + fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); + if (!fpl) + return -ENOMEM; + + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) { + kfree(fpl); + return -ENOMEM; + } + + skb->sk = sk; + skb->scm_io_uring = 1; + + nr_files = 0; + fpl->user = get_uid(current_user()); + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (!file) + continue; + fpl->fp[nr_files] = get_file(file); + unix_inflight(fpl->user, fpl->fp[nr_files]); + nr_files++; + } + + if (nr_files) { + fpl->max = SCM_MAX_FD; + fpl->count = nr_files; + UNIXCB(skb).fp = fpl; + skb->destructor = unix_destruct_scm; + refcount_add(skb->truesize, &sk->sk_wmem_alloc); + skb_queue_head(&sk->sk_receive_queue, skb); + + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (file) + fput(file); + } + } else { + kfree_skb(skb); + free_uid(fpl->user); + kfree(fpl); + } + + return 0; +} + +/* + * If UNIX sockets are enabled, fd passing can cause a reference cycle which + * causes regular reference counting to break down. We rely on the UNIX + * garbage collection to take care of this problem for us. + */ +static int io_sqe_files_scm(struct io_ring_ctx *ctx) +{ + unsigned left, total; + int ret = 0; + + total = 0; + left = ctx->nr_user_files; + while (left) { + unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); + + ret = __io_sqe_files_scm(ctx, this_files, total); + if (ret) + break; + left -= this_files; + total += this_files; + } + + if (!ret) + return 0; + + while (total < ctx->nr_user_files) { + struct file *file = io_file_from_index(ctx, total); + + if (file) + fput(file); + total++; + } + + return ret; +} +#else +static int io_sqe_files_scm(struct io_ring_ctx *ctx) +{ + return 0; +} +#endif + +static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) +{ + struct file *file = prsrc->file; +#if defined(CONFIG_UNIX) + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head list, *head = &sock->sk_receive_queue; + struct sk_buff *skb; + int i; + + __skb_queue_head_init(&list); + + /* + * Find the skb that holds this file in its SCM_RIGHTS. When found, + * remove this entry and rearrange the file array. + */ + skb = skb_dequeue(head); + while (skb) { + struct scm_fp_list *fp; + + fp = UNIXCB(skb).fp; + for (i = 0; i < fp->count; i++) { + int left; + + if (fp->fp[i] != file) + continue; + + unix_notinflight(fp->user, fp->fp[i]); + left = fp->count - 1 - i; + if (left) { + memmove(&fp->fp[i], &fp->fp[i + 1], + left * sizeof(struct file *)); + } + fp->count--; + if (!fp->count) { + kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_tail(&list, skb); + } + fput(file); + file = NULL; + break; + } + + if (!file) + break; + + __skb_queue_tail(&list, skb); + + skb = skb_dequeue(head); + } + + if (skb_peek(&list)) { + spin_lock_irq(&head->lock); + while ((skb = __skb_dequeue(&list)) != NULL) + __skb_queue_tail(head, skb); + spin_unlock_irq(&head->lock); + } +#else + fput(file); +#endif +} + +static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) +{ + struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; + + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + + if (prsrc->tag) { + bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; + + io_ring_submit_lock(ctx, lock_ring); + spin_lock(&ctx->completion_lock); + io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + io_ring_submit_unlock(ctx, lock_ring); + } + + rsrc_data->do_put(ctx, prsrc); + kfree(prsrc); + } + + io_rsrc_node_destroy(ref_node); + if (atomic_dec_and_test(&rsrc_data->refs)) + complete(&rsrc_data->done); +} + +static void io_rsrc_put_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx; + struct llist_node *node; + + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); + + while (node) { + struct io_rsrc_node *ref_node; + struct llist_node *next = node->next; + + ref_node = llist_entry(node, struct io_rsrc_node, llist); + __io_rsrc_put_work(ref_node); + node = next; + } +} + +static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args, u64 __user *tags) +{ + __s32 __user *fds = (__s32 __user *) arg; + struct file *file; + int fd, ret; + unsigned i; + + if (ctx->file_data) + return -EBUSY; + if (!nr_args) + return -EINVAL; + if (nr_args > IORING_MAX_FIXED_FILES) + return -EMFILE; + if (nr_args > rlimit(RLIMIT_NOFILE)) + return -EMFILE; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, + &ctx->file_data); + if (ret) + return ret; + + ret = -ENOMEM; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) + goto out_free; + + for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { + if (copy_from_user(&fd, &fds[i], sizeof(fd))) { + ret = -EFAULT; + goto out_fput; + } + /* allow sparse sets */ + if (fd == -1) { + ret = -EINVAL; + if (unlikely(*io_get_tag_slot(ctx->file_data, i))) + goto out_fput; + continue; + } + + file = fget(fd); + ret = -EBADF; + if (unlikely(!file)) + goto out_fput; + + /* + * Don't allow io_uring instances to be registered. If UNIX + * isn't enabled, then this causes a reference cycle and this + * instance can never get freed. If UNIX is enabled we'll + * handle it just fine, but there's still no point in allowing + * a ring fd as it doesn't support regular read/write anyway. + */ + if (file->f_op == &io_uring_fops) { + fput(file); + goto out_fput; + } + io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); + } + + ret = io_sqe_files_scm(ctx); + if (ret) { + __io_sqe_files_unregister(ctx); + return ret; + } + + io_rsrc_node_switch(ctx, NULL); + return ret; +out_fput: + for (i = 0; i < ctx->nr_user_files; i++) { + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } + io_free_file_tables(&ctx->file_table); + ctx->nr_user_files = 0; +out_free: + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + return ret; +} + +static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) +{ + u64 *tag_slot = io_get_tag_slot(data, idx); + struct io_rsrc_put *prsrc; + + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) + return -ENOMEM; + + prsrc->tag = *tag_slot; + *tag_slot = 0; + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); + return 0; +} + +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index) +{ + struct io_ring_ctx *ctx = req->ctx; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_switch = false; + struct io_fixed_file *file_slot; + int ret = -EBADF; + + io_ring_submit_lock(ctx, !force_nonblock); + if (file->f_op == &io_uring_fops) + goto err; + ret = -ENXIO; + if (!ctx->file_data) + goto err; + ret = -EINVAL; + if (slot_index >= ctx->nr_user_files) + goto err; + + slot_index = array_index_nospec(slot_index, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + needs_switch = true; + } + + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + ret = 0; +err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); + io_ring_submit_unlock(ctx, !force_nonblock); + if (ret) + fput(file); + return ret; +} + +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) +{ + unsigned int offset = req->close.file_slot - 1; + struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *file_slot; + struct file *file; + int ret; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENXIO; + if (unlikely(!ctx->file_data)) + goto out; + ret = -EINVAL; + if (offset >= ctx->nr_user_files) + goto out; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto out; + + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); + ret = -EBADF; + if (!file_slot->file_ptr) + goto out; + + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); + if (ret) + goto out; + + file_slot->file_ptr = 0; + io_rsrc_node_switch(ctx, ctx->file_data); + ret = 0; +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return ret; +} + +static int __io_sqe_files_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + __s32 __user *fds = u64_to_user_ptr(up->data); + struct io_rsrc_data *data = ctx->file_data; + struct io_fixed_file *file_slot; + struct file *file; + int fd, i, err = 0; + unsigned int done; + bool needs_switch = false; + + if (!ctx->file_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_files) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + u64 tag = 0; + + if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || + copy_from_user(&fd, &fds[done], sizeof(fd))) { + err = -EFAULT; + break; + } + if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { + err = -EINVAL; + break; + } + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + + i = array_index_nospec(up->offset + done, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, i); + + if (file_slot->file_ptr) { + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); + if (err) + break; + file_slot->file_ptr = 0; + needs_switch = true; + } + if (fd != -1) { + file = fget(fd); + if (!file) { + err = -EBADF; + break; + } + /* + * Don't allow io_uring instances to be registered. If + * UNIX isn't enabled, then this causes a reference + * cycle and this instance can never get freed. If UNIX + * is enabled we'll handle it just fine, but there's + * still no point in allowing a ring fd as it doesn't + * support regular read/write anyway. + */ + if (file->f_op == &io_uring_fops) { + fput(file); + err = -EBADF; + break; + } + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); + } + } + + if (needs_switch) + io_rsrc_node_switch(ctx, data); + return done ? done : err; +} + +static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, + struct task_struct *task) +{ + struct io_wq_hash *hash; + struct io_wq_data data; + unsigned int concurrency; + + mutex_lock(&ctx->uring_lock); + hash = ctx->hash_map; + if (!hash) { + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) { + mutex_unlock(&ctx->uring_lock); + return ERR_PTR(-ENOMEM); + } + refcount_set(&hash->refs, 1); + init_waitqueue_head(&hash->wait); + ctx->hash_map = hash; + } + mutex_unlock(&ctx->uring_lock); + + data.hash = hash; + data.task = task; + data.free_work = io_wq_free_work; + data.do_work = io_wq_submit_work; + + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + + return io_wq_create(concurrency, &data); +} + +static int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx; + int ret; + + tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); + if (unlikely(!tctx)) + return -ENOMEM; + + ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL); + if (unlikely(ret)) { + kfree(tctx); + return ret; + } + + tctx->io_wq = io_init_wq_offload(ctx, task); + if (IS_ERR(tctx->io_wq)) { + ret = PTR_ERR(tctx->io_wq); + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + return ret; + } + + xa_init(&tctx->xa); + init_waitqueue_head(&tctx->wait); + atomic_set(&tctx->in_idle, 0); + atomic_set(&tctx->inflight_tracked, 0); + task->io_uring = tctx; + spin_lock_init(&tctx->task_lock); + INIT_WQ_LIST(&tctx->task_list); + init_task_work(&tctx->task_work, tctx_task_work); + return 0; +} + +void __io_uring_free(struct task_struct *tsk) +{ + struct io_uring_task *tctx = tsk->io_uring; + + WARN_ON_ONCE(!xa_empty(&tctx->xa)); + WARN_ON_ONCE(tctx->io_wq); + WARN_ON_ONCE(tctx->cached_refs); + + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + tsk->io_uring = NULL; +} + +static int io_sq_offload_create(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + int ret; + + /* Retain compatibility with failing for an invalid attach attempt */ + if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == + IORING_SETUP_ATTACH_WQ) { + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return -ENXIO; + if (f.file->f_op != &io_uring_fops) { + fdput(f); + return -EINVAL; + } + fdput(f); + } + if (ctx->flags & IORING_SETUP_SQPOLL) { + struct task_struct *tsk; + struct io_sq_data *sqd; + bool attached; + + sqd = io_get_sq_data(p, &attached); + if (IS_ERR(sqd)) { + ret = PTR_ERR(sqd); + goto err; + } + + ctx->sq_creds = get_current_cred(); + ctx->sq_data = sqd; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; + + io_sq_thread_park(sqd); + list_add(&ctx->sqd_list, &sqd->ctx_list); + io_sqd_update_thread_idle(sqd); + /* don't attach to a dying SQPOLL thread, would be racy */ + ret = (attached && !sqd->thread) ? -ENXIO : 0; + io_sq_thread_unpark(sqd); + + if (ret < 0) + goto err; + if (attached) + return 0; + + if (p->flags & IORING_SETUP_SQ_AFF) { + int cpu = p->sq_thread_cpu; + + ret = -EINVAL; + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + goto err_sqpoll; + sqd->sq_cpu = cpu; + } else { + sqd->sq_cpu = -1; + } + + sqd->task_pid = current->pid; + sqd->task_tgid = current->tgid; + tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); + if (IS_ERR(tsk)) { + ret = PTR_ERR(tsk); + goto err_sqpoll; + } + + sqd->thread = tsk; + ret = io_uring_alloc_task_context(tsk, ctx); + wake_up_new_task(tsk); + if (ret) + goto err; + } else if (p->flags & IORING_SETUP_SQ_AFF) { + /* Can't have SQ_AFF without SQPOLL */ + ret = -EINVAL; + goto err; + } + + return 0; +err_sqpoll: + complete(&ctx->sq_data->exited); +err: + io_sq_thread_finish(ctx); + return ret; +} + +static inline void __io_unaccount_mem(struct user_struct *user, + unsigned long nr_pages) +{ + atomic_long_sub(nr_pages, &user->locked_vm); +} + +static inline int __io_account_mem(struct user_struct *user, + unsigned long nr_pages) +{ + unsigned long page_limit, cur_pages, new_pages; + + /* Don't allow more pages than we can safely lock */ + page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + + do { + cur_pages = atomic_long_read(&user->locked_vm); + new_pages = cur_pages + nr_pages; + if (new_pages > page_limit) + return -ENOMEM; + } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, + new_pages) != cur_pages); + + return 0; +} + +static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) +{ + if (ctx->user) + __io_unaccount_mem(ctx->user, nr_pages); + + if (ctx->mm_account) + atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); +} + +static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) +{ + int ret; + + if (ctx->user) { + ret = __io_account_mem(ctx->user, nr_pages); + if (ret) + return ret; + } + + if (ctx->mm_account) + atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); + + return 0; +} + +static void io_mem_free(void *ptr) +{ + struct page *page; + + if (!ptr) + return; + + page = virt_to_head_page(ptr); + if (put_page_testzero(page)) + free_compound_page(page); +} + +static void *io_mem_alloc(size_t size) +{ + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; + + return (void *) __get_free_pages(gfp, get_order(size)); +} + +static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, + size_t *sq_offset) +{ + struct io_rings *rings; + size_t off, sq_array_size; + + off = struct_size(rings, cqes, cq_entries); + if (off == SIZE_MAX) + return SIZE_MAX; + +#ifdef CONFIG_SMP + off = ALIGN(off, SMP_CACHE_BYTES); + if (off == 0) + return SIZE_MAX; +#endif + + if (sq_offset) + *sq_offset = off; + + sq_array_size = array_size(sizeof(u32), sq_entries); + if (sq_array_size == SIZE_MAX) + return SIZE_MAX; + + if (check_add_overflow(off, sq_array_size, &off)) + return SIZE_MAX; + + return off; +} + +static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) +{ + struct io_mapped_ubuf *imu = *slot; + unsigned int i; + + if (imu != ctx->dummy_ubuf) { + for (i = 0; i < imu->nr_bvecs; i++) + unpin_user_page(imu->bvec[i].bv_page); + if (imu->acct_pages) + io_unaccount_mem(ctx, imu->acct_pages); + kvfree(imu); + } + *slot = NULL; +} + +static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) +{ + io_buffer_unmap(ctx, &prsrc->buf); + prsrc->buf = NULL; +} + +static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned int i; + + for (i = 0; i < ctx->nr_user_bufs; i++) + io_buffer_unmap(ctx, &ctx->user_bufs[i]); + kfree(ctx->user_bufs); + io_rsrc_data_free(ctx->buf_data); + ctx->user_bufs = NULL; + ctx->buf_data = NULL; + ctx->nr_user_bufs = 0; +} + +static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_bufs; + int ret; + + if (!ctx->buf_data) + return -ENXIO; + + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ + ctx->nr_user_bufs = 0; + ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); + ctx->nr_user_bufs = nr; + if (!ret) + __io_sqe_buffers_unregister(ctx); + return ret; +} + +static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, + void __user *arg, unsigned index) +{ + struct iovec __user *src; + +#ifdef CONFIG_COMPAT + if (ctx->compat) { + struct compat_iovec __user *ciovs; + struct compat_iovec ciov; + + ciovs = (struct compat_iovec __user *) arg; + if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) + return -EFAULT; + + dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); + dst->iov_len = ciov.iov_len; + return 0; + } +#endif + src = (struct iovec __user *) arg; + if (copy_from_user(dst, &src[index], sizeof(*dst))) + return -EFAULT; + return 0; +} + +/* + * Not super efficient, but this is just a registration time. And we do cache + * the last compound head, so generally we'll only do a full search if we don't + * match that one. + * + * We check if the given compound head page has already been accounted, to + * avoid double accounting it. This allows us to account the full size of the + * page, not just the constituent pages of a huge page. + */ +static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, + int nr_pages, struct page *hpage) +{ + int i, j; + + /* check current page array */ + for (i = 0; i < nr_pages; i++) { + if (!PageCompound(pages[i])) + continue; + if (compound_head(pages[i]) == hpage) + return true; + } + + /* check previously registered pages */ + for (i = 0; i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *imu = ctx->user_bufs[i]; + + for (j = 0; j < imu->nr_bvecs; j++) { + if (!PageCompound(imu->bvec[j].bv_page)) + continue; + if (compound_head(imu->bvec[j].bv_page) == hpage) + return true; + } + } + + return false; +} + +static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, + int nr_pages, struct io_mapped_ubuf *imu, + struct page **last_hpage) +{ + int i, ret; + + imu->acct_pages = 0; + for (i = 0; i < nr_pages; i++) { + if (!PageCompound(pages[i])) { + imu->acct_pages++; + } else { + struct page *hpage; + + hpage = compound_head(pages[i]); + if (hpage == *last_hpage) + continue; + *last_hpage = hpage; + if (headpage_already_acct(ctx, pages, i, hpage)) + continue; + imu->acct_pages += page_size(hpage) >> PAGE_SHIFT; + } + } + + if (!imu->acct_pages) + return 0; + + ret = io_account_mem(ctx, imu->acct_pages); + if (ret) + imu->acct_pages = 0; + return ret; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) +{ + struct io_mapped_ubuf *imu = NULL; + struct vm_area_struct **vmas = NULL; + struct page **pages = NULL; + unsigned long off, start, end, ubuf; + size_t size; + int ret, pret, nr_pages, i; + + if (!iov->iov_base) { + *pimu = ctx->dummy_ubuf; + return 0; + } + + ubuf = (unsigned long) iov->iov_base; + end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + *pimu = NULL; + ret = -ENOMEM; + + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto done; + + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + goto done; + + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = 0; + mmap_read_lock(current->mm); + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); + if (pret == nr_pages) { + struct file *file = vmas[0]->vm_file; + + /* don't support file backed memory */ + for (i = 0; i < nr_pages; i++) { + if (vmas[i]->vm_file != file) { + ret = -EINVAL; + break; + } + if (!file) + continue; + if (!vma_is_shmem(vmas[i]) && !is_file_hugepages(file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + mmap_read_unlock(current->mm); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) + unpin_user_pages(pages, pret); + goto done; + } + + ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + if (ret) { + unpin_user_pages(pages, pret); + goto done; + } + + off = ubuf & ~PAGE_MASK; + size = iov->iov_len; + for (i = 0; i < nr_pages; i++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[i].bv_page = pages[i]; + imu->bvec[i].bv_len = vec_len; + imu->bvec[i].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->ubuf_end = ubuf + iov->iov_len; + imu->nr_bvecs = nr_pages; + *pimu = imu; + ret = 0; +done: + if (ret) + kvfree(imu); + kvfree(pages); + kvfree(vmas); + return ret; +} + +static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) +{ + ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); + return ctx->user_bufs ? 0 : -ENOMEM; +} + +static int io_buffer_validate(struct iovec *iov) +{ + unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); + + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + if (!iov->iov_base) + return iov->iov_len ? -EFAULT : 0; + if (!iov->iov_len) + return -EFAULT; + + /* arbitrary limit, but we need something */ + if (iov->iov_len > SZ_1G) + return -EFAULT; + + if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) + return -EOVERFLOW; + + return 0; +} + +static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args, u64 __user *tags) +{ + struct page *last_hpage = NULL; + struct io_rsrc_data *data; + int i, ret; + struct iovec iov; + + if (ctx->user_bufs) + return -EBUSY; + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) + return -EINVAL; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); + if (ret) + return ret; + ret = io_buffers_map_alloc(ctx, nr_args); + if (ret) { + io_rsrc_data_free(data); + return ret; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + if (!iov.iov_base && *io_get_tag_slot(data, i)) { + ret = -EINVAL; + break; + } + + ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], + &last_hpage); + if (ret) + break; + } + + WARN_ON_ONCE(ctx->buf_data); + + ctx->buf_data = data; + if (ret) + __io_sqe_buffers_unregister(ctx); + else + io_rsrc_node_switch(ctx, NULL); + return ret; +} + +static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned int nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); + struct page *last_hpage = NULL; + bool needs_switch = false; + __u32 done; + int i, err; + + if (!ctx->buf_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_bufs) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + struct io_mapped_ubuf *imu; + int offset = up->offset + done; + u64 tag = 0; + + err = io_copy_iov(ctx, &iov, iovs, done); + if (err) + break; + if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { + err = -EFAULT; + break; + } + err = io_buffer_validate(&iov); + if (err) + break; + if (!iov.iov_base && tag) { + err = -EINVAL; + break; + } + err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); + if (err) + break; + + i = array_index_nospec(offset, ctx->nr_user_bufs); + if (ctx->user_bufs[i] != ctx->dummy_ubuf) { + err = io_queue_rsrc_removal(ctx->buf_data, i, + ctx->rsrc_node, ctx->user_bufs[i]); + if (unlikely(err)) { + io_buffer_unmap(ctx, &imu); + break; + } + ctx->user_bufs[i] = NULL; + needs_switch = true; + } + + ctx->user_bufs[i] = imu; + *io_get_tag_slot(ctx->buf_data, offset) = tag; + } + + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->buf_data); + return done ? done : err; +} + +static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) +{ + __s32 __user *fds = arg; + int fd; + + if (ctx->cq_ev_fd) + return -EBUSY; + + if (copy_from_user(&fd, fds, sizeof(*fds))) + return -EFAULT; + + ctx->cq_ev_fd = eventfd_ctx_fdget(fd); + if (IS_ERR(ctx->cq_ev_fd)) { + int ret = PTR_ERR(ctx->cq_ev_fd); + + ctx->cq_ev_fd = NULL; + return ret; + } + + return 0; +} + +static int io_eventfd_unregister(struct io_ring_ctx *ctx) +{ + if (ctx->cq_ev_fd) { + eventfd_ctx_put(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; + return 0; + } + + return -ENXIO; +} + +static void io_destroy_buffers(struct io_ring_ctx *ctx) +{ + struct io_buffer *buf; + unsigned long index; + + xa_for_each(&ctx->io_buffers, index, buf) + __io_remove_buffers(ctx, buf, index, -1U); +} + +static void io_req_cache_free(struct list_head *list) +{ + struct io_kiocb *req, *nxt; + + list_for_each_entry_safe(req, nxt, list, inflight_entry) { + list_del(&req->inflight_entry); + kmem_cache_free(req_cachep, req); + } +} + +static void io_req_caches_free(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + + mutex_lock(&ctx->uring_lock); + + if (state->free_reqs) { + kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); + state->free_reqs = 0; + } + + io_flush_cached_locked_reqs(ctx, state); + io_req_cache_free(&state->free_list); + mutex_unlock(&ctx->uring_lock); +} + +static void io_wait_rsrc_data(struct io_rsrc_data *data) +{ + if (data && !atomic_dec_and_test(&data->refs)) + wait_for_completion(&data->done); +} + +static void io_ring_ctx_free(struct io_ring_ctx *ctx) +{ + io_sq_thread_finish(ctx); + + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + + mutex_lock(&ctx->uring_lock); + if (ctx->buf_data) + __io_sqe_buffers_unregister(ctx); + if (ctx->file_data) + __io_sqe_files_unregister(ctx); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); + mutex_unlock(&ctx->uring_lock); + io_eventfd_unregister(ctx); + io_destroy_buffers(ctx); + if (ctx->sq_creds) + put_cred(ctx->sq_creds); + + /* there are no registered resources left, nobody uses it */ + if (ctx->rsrc_node) + io_rsrc_node_destroy(ctx->rsrc_node); + if (ctx->rsrc_backup_node) + io_rsrc_node_destroy(ctx->rsrc_backup_node); + flush_delayed_work(&ctx->rsrc_put_work); + + WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); + WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); + +#if defined(CONFIG_UNIX) + if (ctx->ring_sock) { + ctx->ring_sock->file = NULL; /* so that iput() is called */ + sock_release(ctx->ring_sock); + } +#endif + WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); + + if (ctx->mm_account) { + mmdrop(ctx->mm_account); + ctx->mm_account = NULL; + } + + io_mem_free(ctx->rings); + io_mem_free(ctx->sq_sqes); + + percpu_ref_exit(&ctx->refs); + free_uid(ctx->user); + io_req_caches_free(ctx); + if (ctx->hash_map) + io_wq_put_hash(ctx->hash_map); + kfree(ctx->cancel_hash); + kfree(ctx->dummy_ubuf); + kfree(ctx); +} + +static __poll_t io_uring_poll(struct file *file, poll_table *wait) +{ + struct io_ring_ctx *ctx = file->private_data; + __poll_t mask = 0; + + poll_wait(file, &ctx->poll_wait, wait); + /* + * synchronizes with barrier from wq_has_sleeper call in + * io_commit_cqring + */ + smp_rmb(); + if (!io_sqring_full(ctx)) + mask |= EPOLLOUT | EPOLLWRNORM; + + /* + * Don't flush cqring overflow list here, just do a simple check. + * Otherwise there could possible be ABBA deadlock: + * CPU0 CPU1 + * ---- ---- + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * + * Users may get EPOLLIN meanwhile seeing nothing in cqring, this + * pushs them to do the flush. + */ + if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) +{ + const struct cred *creds; + + creds = xa_erase(&ctx->personalities, id); + if (creds) { + put_cred(creds); + return 0; + } + + return -EINVAL; +} + +struct io_tctx_exit { + struct callback_head task_work; + struct completion completion; + struct io_ring_ctx *ctx; +}; + +static void io_tctx_exit_cb(struct callback_head *cb) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_exit *work; + + work = container_of(cb, struct io_tctx_exit, task_work); + /* + * When @in_idle, we're in cancellation and it's racy to remove the + * node. It'll be removed by the end of cancellation, just ignore it. + * tctx can be NULL if the queueing of this task_work raced with + * work cancelation off the exec path. + */ + if (tctx && !atomic_read(&tctx->in_idle)) + io_uring_del_tctx_node((unsigned long)work->ctx); + complete(&work->completion); +} + +static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->ctx == data; +} + +static void io_ring_exit_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); + unsigned long timeout = jiffies + HZ * 60 * 5; + unsigned long interval = HZ / 20; + struct io_tctx_exit exit; + struct io_tctx_node *node; + int ret; + + /* + * If we're doing polled IO and end up having requests being + * submitted async (out-of-line), then completions can come in while + * we're waiting for refs to drop. We need to reap these manually, + * as nobody else will be looking for them. + */ + do { + io_uring_try_cancel_requests(ctx, NULL, true); + if (ctx->sq_data) { + struct io_sq_data *sqd = ctx->sq_data; + struct task_struct *tsk; + + io_sq_thread_park(sqd); + tsk = sqd->thread; + if (tsk && tsk->io_uring && tsk->io_uring->io_wq) + io_wq_cancel_cb(tsk->io_uring->io_wq, + io_cancel_ctx_cb, ctx, true); + io_sq_thread_unpark(sqd); + } + + if (WARN_ON_ONCE(time_after(jiffies, timeout))) { + /* there is little hope left, don't run it too often */ + interval = HZ * 60; + } + /* + * This is really an uninterruptible wait, as it has to be + * complete. But it's also run from a kworker, which doesn't + * take signals, so it's fine to make it interruptible. This + * avoids scenarios where we knowingly can wait much longer + * on completions, for example if someone does a SIGSTOP on + * a task that needs to finish task_work to make this loop + * complete. That's a synthetic situation that should not + * cause a stuck task backtrace, and hence a potential panic + * on stuck tasks if that is enabled. + */ + } while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval)); + + init_completion(&exit.completion); + init_task_work(&exit.task_work, io_tctx_exit_cb); + exit.ctx = ctx; + /* + * Some may use context even when all refs and requests have been put, + * and they are free to do so while still holding uring_lock or + * completion_lock, see io_req_task_submit(). Apart from other work, + * this lock/unlock section also waits them to finish. + */ + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->tctx_list)) { + WARN_ON_ONCE(time_after(jiffies, timeout)); + + node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, + ctx_node); + /* don't spin on a single task if cancellation failed */ + list_rotate_left(&ctx->tctx_list); + ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); + if (WARN_ON_ONCE(ret)) + continue; + wake_up_process(node->task); + + mutex_unlock(&ctx->uring_lock); + /* + * See comment above for + * wait_for_completion_interruptible_timeout() on why this + * wait is marked as interruptible. + */ + wait_for_completion_interruptible(&exit.completion); + mutex_lock(&ctx->uring_lock); + } + mutex_unlock(&ctx->uring_lock); + spin_lock(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + + io_ring_ctx_free(ctx); +} + +/* Returns true if we found and killed one or more timeouts */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) +{ + struct io_kiocb *req, *tmp; + int canceled = 0; + + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + if (io_match_task(req, tsk, cancel_all)) { + io_kill_timeout(req, -ECANCELED); + canceled++; + } + } + spin_unlock_irq(&ctx->timeout_lock); + if (canceled != 0) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (canceled != 0) + io_cqring_ev_posted(ctx); + return canceled != 0; +} + +static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) +{ + unsigned long index; + struct creds *creds; + + mutex_lock(&ctx->uring_lock); + percpu_ref_kill(&ctx->refs); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); + xa_for_each(&ctx->personalities, index, creds) + io_unregister_personality(ctx, index); + mutex_unlock(&ctx->uring_lock); + + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); + + /* if we failed setting up the ctx, we might not have any rings */ + io_iopoll_try_reap_events(ctx); + + /* drop cached put refs after potentially doing completions */ + if (current->io_uring) + io_uring_drop_tctx_refs(current); + + INIT_WORK(&ctx->exit_work, io_ring_exit_work); + /* + * Use system_unbound_wq to avoid spawning tons of event kworkers + * if we're exiting a ton of rings at the same time. It just adds + * noise and overhead, there's no discernable change in runtime + * over using system_wq. + */ + queue_work(system_unbound_wq, &ctx->exit_work); +} + +static int io_uring_release(struct inode *inode, struct file *file) +{ + struct io_ring_ctx *ctx = file->private_data; + + file->private_data = NULL; + io_ring_ctx_wait_and_kill(ctx); + return 0; +} + +struct io_task_cancel { + struct task_struct *task; + bool all; +}; + +static bool io_cancel_task_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_task_cancel *cancel = data; + + return io_match_task_safe(req, cancel->task, cancel->all); +} + +static bool io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, bool cancel_all) +{ + struct io_defer_entry *de; + LIST_HEAD(list); + + spin_lock(&ctx->completion_lock); + list_for_each_entry_reverse(de, &ctx->defer_list, list) { + if (io_match_task_safe(de->req, task, cancel_all)) { + list_cut_position(&list, &ctx->defer_list, &de->list); + break; + } + } + spin_unlock(&ctx->completion_lock); + if (list_empty(&list)) + return false; + + while (!list_empty(&list)) { + de = list_first_entry(&list, struct io_defer_entry, list); + list_del_init(&de->list); + io_req_complete_failed(de->req, -ECANCELED); + kfree(de); + } + return true; +} + +static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) +{ + struct io_tctx_node *node; + enum io_wq_cancel cret; + bool ret = false; + + mutex_lock(&ctx->uring_lock); + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + /* + * io_wq will stay alive while we hold uring_lock, because it's + * killed after ctx nodes, which requires to take the lock. + */ + if (!tctx || !tctx->io_wq) + continue; + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } + mutex_unlock(&ctx->uring_lock); + + return ret; +} + +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) +{ + struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; + struct io_uring_task *tctx = task ? task->io_uring : NULL; + + while (1) { + enum io_wq_cancel cret; + bool ret = false; + + if (!task) { + ret |= io_uring_try_cancel_iowq(ctx); + } else if (tctx && tctx->io_wq) { + /* + * Cancels requests of all rings, not only @ctx, but + * it's fine as the task is in exit/exec. + */ + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } + + /* SQPOLL thread does its own polling */ + if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || + (ctx->sq_data && ctx->sq_data->thread == current)) { + while (!list_empty_careful(&ctx->iopoll_list)) { + io_iopoll_try_reap_events(ctx); + ret = true; + cond_resched(); + } + } + + ret |= io_cancel_defer_files(ctx, task, cancel_all); + ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_kill_timeouts(ctx, task, cancel_all); + if (task) + ret |= io_run_task_work(); + if (!ret) + break; + cond_resched(); + } +} + +static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; + int ret; + + if (unlikely(!tctx)) { + ret = io_uring_alloc_task_context(current, ctx); + if (unlikely(ret)) + return ret; + + tctx = current->io_uring; + if (ctx->iowq_limits_set) { + unsigned int limits[2] = { ctx->iowq_limits[0], + ctx->iowq_limits[1], }; + + ret = io_wq_max_workers(tctx->io_wq, limits); + if (ret) + return ret; + } + } + if (!xa_load(&tctx->xa, (unsigned long)ctx)) { + node = kmalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + node->ctx = ctx; + node->task = current; + + ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, + node, GFP_KERNEL)); + if (ret) { + kfree(node); + return ret; + } + + mutex_lock(&ctx->uring_lock); + list_add(&node->ctx_node, &ctx->tctx_list); + mutex_unlock(&ctx->uring_lock); + } + tctx->last = ctx; + return 0; +} + +/* + * Note that this task has used io_uring. We use it for cancelation purposes. + */ +static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (likely(tctx && tctx->last == ctx)) + return 0; + return __io_uring_add_tctx_node(ctx); +} + +/* + * Remove this io_uring_file -> task mapping. + */ +static void io_uring_del_tctx_node(unsigned long index) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; + + if (!tctx) + return; + node = xa_erase(&tctx->xa, index); + if (!node) + return; + + WARN_ON_ONCE(current != node->task); + WARN_ON_ONCE(list_empty(&node->ctx_node)); + + mutex_lock(&node->ctx->uring_lock); + list_del(&node->ctx_node); + mutex_unlock(&node->ctx->uring_lock); + + if (tctx->last == node->ctx) + tctx->last = NULL; + kfree(node); +} + +static void io_uring_clean_tctx(struct io_uring_task *tctx) +{ + struct io_wq *wq = tctx->io_wq; + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + io_uring_del_tctx_node(index); + cond_resched(); + } + if (wq) { + /* + * Must be after io_uring_del_task_file() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + io_wq_put_and_exit(wq); + tctx->io_wq = NULL; + } +} + +static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) +{ + if (tracked) + return atomic_read(&tctx->inflight_tracked); + return percpu_counter_sum(&tctx->inflight); +} + +/* + * Find any io_uring ctx that this task has registered or done IO on, and cancel + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. + */ +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_ring_ctx *ctx; + s64 inflight; + DEFINE_WAIT(wait); + + WARN_ON_ONCE(sqd && sqd->thread != current); + + if (!current->io_uring) + return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); + + atomic_inc(&tctx->in_idle); + do { + io_uring_drop_tctx_refs(current); + /* read completions before cancelations */ + inflight = tctx_inflight(tctx, !cancel_all); + if (!inflight) + break; + + if (!sqd) { + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + /* sqpoll task will cancel all its requests */ + if (node->ctx->sq_data) + continue; + io_uring_try_cancel_requests(node->ctx, current, + cancel_all); + } + } else { + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_uring_try_cancel_requests(ctx, current, + cancel_all); + } + + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); + io_uring_drop_tctx_refs(current); + + /* + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). + */ + if (inflight == tctx_inflight(tctx, !cancel_all)) + schedule(); + finish_wait(&tctx->wait, &wait); + } while (1); + + io_uring_clean_tctx(tctx); + if (cancel_all) { + /* + * We shouldn't run task_works after cancel, so just leave + * ->in_idle set for normal exit. + */ + atomic_dec(&tctx->in_idle); + /* for exec all current's requests should be gone, kill tctx */ + __io_uring_free(current); + } +} + +void __io_uring_cancel(bool cancel_all) +{ + io_uring_cancel_generic(cancel_all, NULL); +} + +static void *io_uring_validate_mmap_request(struct file *file, + loff_t pgoff, size_t sz) +{ + struct io_ring_ctx *ctx = file->private_data; + loff_t offset = pgoff << PAGE_SHIFT; + struct page *page; + void *ptr; + + switch (offset) { + case IORING_OFF_SQ_RING: + case IORING_OFF_CQ_RING: + ptr = ctx->rings; + break; + case IORING_OFF_SQES: + ptr = ctx->sq_sqes; + break; + default: + return ERR_PTR(-EINVAL); + } + + page = virt_to_head_page(ptr); + if (sz > page_size(page)) + return ERR_PTR(-EINVAL); + + return ptr; +} + +#ifdef CONFIG_MMU + +static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +{ + size_t sz = vma->vm_end - vma->vm_start; + unsigned long pfn; + void *ptr; + + ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + pfn = virt_to_phys(ptr) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); +} + +#else /* !CONFIG_MMU */ + +static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL; +} + +static unsigned int io_uring_nommu_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE; +} + +static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + void *ptr; + + ptr = io_uring_validate_mmap_request(file, pgoff, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + return (unsigned long) ptr; +} + +#endif /* !CONFIG_MMU */ + +static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) +{ + DEFINE_WAIT(wait); + + do { + if (!io_sqring_full(ctx)) + break; + prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); + + if (!io_sqring_full(ctx)) + break; + schedule(); + } while (!signal_pending(current)); + + finish_wait(&ctx->sqo_sq_wait, &wait); + return 0; +} + +static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, + struct __kernel_timespec __user **ts, + const sigset_t __user **sig) +{ + struct io_uring_getevents_arg arg; + + /* + * If EXT_ARG isn't set, then we have no timespec and the argp pointer + * is just a pointer to the sigset_t. + */ + if (!(flags & IORING_ENTER_EXT_ARG)) { + *sig = (const sigset_t __user *) argp; + *ts = NULL; + return 0; + } + + /* + * EXT_ARG is set - ensure we agree on the size of it and copy in our + * timespec and sigset_t pointers if good. + */ + if (*argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + if (arg.pad) + return -EINVAL; + *sig = u64_to_user_ptr(arg.sigmask); + *argsz = arg.sigmask_sz; + *ts = u64_to_user_ptr(arg.ts); + return 0; +} + +SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, + u32, min_complete, u32, flags, const void __user *, argp, + size_t, argsz) +{ + struct io_ring_ctx *ctx; + int submitted = 0; + struct fd f; + long ret; + + io_run_task_work(); + + if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | + IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))) + return -EINVAL; + + f = fdget(fd); + if (unlikely(!f.file)) + return -EBADF; + + ret = -EOPNOTSUPP; + if (unlikely(f.file->f_op != &io_uring_fops)) + goto out_fput; + + ret = -ENXIO; + ctx = f.file->private_data; + if (unlikely(!percpu_ref_tryget(&ctx->refs))) + goto out_fput; + + ret = -EBADFD; + if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) + goto out; + + /* + * For SQ polling, the thread will do all submissions and completions. + * Just return the requested submit count, and wake the thread if + * we were asked to. + */ + ret = 0; + if (ctx->flags & IORING_SETUP_SQPOLL) { + io_cqring_overflow_flush(ctx); + + if (unlikely(ctx->sq_data->thread == NULL)) { + ret = -EOWNERDEAD; + goto out; + } + if (flags & IORING_ENTER_SQ_WAKEUP) + wake_up(&ctx->sq_data->wait); + if (flags & IORING_ENTER_SQ_WAIT) { + ret = io_sqpoll_wait_sq(ctx); + if (ret) + goto out; + } + submitted = to_submit; + } else if (to_submit) { + ret = io_uring_add_tctx_node(ctx); + if (unlikely(ret)) + goto out; + mutex_lock(&ctx->uring_lock); + submitted = io_submit_sqes(ctx, to_submit); + mutex_unlock(&ctx->uring_lock); + + if (submitted != to_submit) + goto out; + } + if (flags & IORING_ENTER_GETEVENTS) { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (unlikely(ret)) + goto out; + + min_complete = min(min_complete, ctx->cq_entries); + + /* + * 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, min_complete); + } else { + ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); + } + } + +out: + percpu_ref_put(&ctx->refs); +out_fput: + fdput(f); + return submitted ? submitted : ret; +} + +#ifdef CONFIG_PROC_FS +static int io_uring_show_cred(struct seq_file *m, unsigned int id, + const struct cred *cred) +{ + struct user_namespace *uns = seq_user_ns(m); + struct group_info *gi; + kernel_cap_t cap; + unsigned __capi; + int g; + + seq_printf(m, "%5d\n", id); + seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); + seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); + seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); + seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); + seq_puts(m, "\n\tGroups:\t"); + gi = cred->group_info; + for (g = 0; g < gi->ngroups; g++) { + seq_put_decimal_ull(m, g ? " " : "", + from_kgid_munged(uns, gi->gid[g])); + } + seq_puts(m, "\n\tCapEff:\t"); + cap = cred->cap_effective; + CAP_FOR_EACH_U32(__capi) + seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); + seq_putc(m, '\n'); + return 0; +} + +static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) +{ + int sq_pid = -1, sq_cpu = -1; + bool has_lock; + int i; + + /* + * Avoid ABBA deadlock between the seq lock and the io_uring mutex, + * since fdinfo case grabs it in the opposite direction of normal use + * cases. If we fail to get the lock, we just don't iterate any + * structures that could be going away outside the io_uring mutex. + */ + has_lock = mutex_trylock(&ctx->uring_lock); + + if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { + struct io_sq_data *sq = ctx->sq_data; + + if (mutex_trylock(&sq->lock)) { + if (sq->thread) { + sq_pid = task_pid_nr(sq->thread); + sq_cpu = task_cpu(sq->thread); + } + mutex_unlock(&sq->lock); + } + } + + seq_printf(m, "SqThread:\t%d\n", sq_pid); + seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); + seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); + for (i = 0; has_lock && i < ctx->nr_user_files; i++) { + struct file *f = io_file_from_index(ctx, i); + + if (f) + seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); + else + seq_printf(m, "%5u: <none>\n", i); + } + seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); + for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *buf = ctx->user_bufs[i]; + unsigned int len = buf->ubuf_end - buf->ubuf; + + seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); + } + if (has_lock && !xa_empty(&ctx->personalities)) { + unsigned long index; + const struct cred *cred; + + seq_printf(m, "Personalities:\n"); + xa_for_each(&ctx->personalities, index, cred) + io_uring_show_cred(m, index, cred); + } + seq_printf(m, "PollList:\n"); + spin_lock(&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(&ctx->completion_lock); + if (has_lock) + mutex_unlock(&ctx->uring_lock); +} + +static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct io_ring_ctx *ctx = f->private_data; + + if (percpu_ref_tryget(&ctx->refs)) { + __io_uring_show_fdinfo(ctx, m); + percpu_ref_put(&ctx->refs); + } +} +#endif + +static const struct file_operations io_uring_fops = { + .release = io_uring_release, + .mmap = io_uring_mmap, +#ifndef CONFIG_MMU + .get_unmapped_area = io_uring_nommu_get_unmapped_area, + .mmap_capabilities = io_uring_nommu_mmap_capabilities, +#endif + .poll = io_uring_poll, +#ifdef CONFIG_PROC_FS + .show_fdinfo = io_uring_show_fdinfo, +#endif +}; + +static int io_allocate_scq_urings(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + struct io_rings *rings; + size_t size, sq_array_offset; + + /* make sure these are sane, as we already accounted them */ + ctx->sq_entries = p->sq_entries; + ctx->cq_entries = p->cq_entries; + + size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); + if (size == SIZE_MAX) + return -EOVERFLOW; + + rings = io_mem_alloc(size); + if (!rings) + return -ENOMEM; + + ctx->rings = rings; + ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); + rings->sq_ring_mask = p->sq_entries - 1; + rings->cq_ring_mask = p->cq_entries - 1; + rings->sq_ring_entries = p->sq_entries; + rings->cq_ring_entries = p->cq_entries; + + size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); + if (size == SIZE_MAX) { + io_mem_free(ctx->rings); + ctx->rings = NULL; + return -EOVERFLOW; + } + + ctx->sq_sqes = io_mem_alloc(size); + if (!ctx->sq_sqes) { + io_mem_free(ctx->rings); + ctx->rings = NULL; + return -ENOMEM; + } + + return 0; +} + +static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) +{ + int ret, fd; + + fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + + ret = io_uring_add_tctx_node(ctx); + if (ret) { + put_unused_fd(fd); + return ret; + } + fd_install(fd, file); + return fd; +} + +/* + * Allocate an anonymous fd, this is what constitutes the application + * visible backing of an io_uring instance. The application mmaps this + * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, + * we have to tie this fd to a socket for file garbage collection purposes. + */ +static struct file *io_uring_get_file(struct io_ring_ctx *ctx) +{ + struct file *file; +#if defined(CONFIG_UNIX) + int ret; + + ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, + &ctx->ring_sock); + if (ret) + return ERR_PTR(ret); +#endif + + file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, + O_RDWR | O_CLOEXEC); +#if defined(CONFIG_UNIX) + if (IS_ERR(file)) { + sock_release(ctx->ring_sock); + ctx->ring_sock = NULL; + } else { + ctx->ring_sock->file = file; + } +#endif + return file; +} + +static int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) +{ + struct io_ring_ctx *ctx; + struct file *file; + int ret; + + if (!entries) + return -EINVAL; + if (entries > IORING_MAX_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + entries = IORING_MAX_ENTRIES; + } + + /* + * Use twice as many entries for the CQ ring. It's possible for the + * application to drive a higher depth than the size of the SQ ring, + * since the sqes are only used at submission time. This allows for + * some flexibility in overcommitting a bit. If the application has + * set IORING_SETUP_CQSIZE, it will have passed in the desired number + * of CQ ring entries manually. + */ + p->sq_entries = roundup_pow_of_two(entries); + if (p->flags & IORING_SETUP_CQSIZE) { + /* + * If IORING_SETUP_CQSIZE is set, we do the same roundup + * to a power-of-two, if it isn't already. We do NOT impose + * any cq vs sq ring sizing. + */ + if (!p->cq_entries) + return -EINVAL; + if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + p->cq_entries = IORING_MAX_CQ_ENTRIES; + } + p->cq_entries = roundup_pow_of_two(p->cq_entries); + if (p->cq_entries < p->sq_entries) + return -EINVAL; + } else { + p->cq_entries = 2 * p->sq_entries; + } + + ctx = io_ring_ctx_alloc(p); + if (!ctx) + return -ENOMEM; + ctx->compat = in_compat_syscall(); + if (!ns_capable_noaudit(&init_user_ns, CAP_IPC_LOCK)) + ctx->user = get_uid(current_user()); + + /* + * This is just grabbed for accounting purposes. When a process exits, + * the mm is exited and dropped before the files, hence we need to hang + * on to this mm purely for the purposes of being able to unaccount + * memory (locked/pinned vm). It's not used for anything else. + */ + mmgrab(current->mm); + ctx->mm_account = current->mm; + + ret = io_allocate_scq_urings(ctx, p); + if (ret) + goto err; + + ret = io_sq_offload_create(ctx, p); + if (ret) + goto err; + /* always set a rsrc node */ + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + io_rsrc_node_switch(ctx, NULL); + + memset(&p->sq_off, 0, sizeof(p->sq_off)); + p->sq_off.head = offsetof(struct io_rings, sq.head); + p->sq_off.tail = offsetof(struct io_rings, sq.tail); + p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask); + p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries); + p->sq_off.flags = offsetof(struct io_rings, sq_flags); + p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); + p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; + + memset(&p->cq_off, 0, sizeof(p->cq_off)); + p->cq_off.head = offsetof(struct io_rings, cq.head); + p->cq_off.tail = offsetof(struct io_rings, cq.tail); + p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask); + p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries); + p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); + p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->cq_off.flags = offsetof(struct io_rings, cq_flags); + + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | + IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } + + file = io_uring_get_file(ctx); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err; + } + + /* + * Install ring fd as the very last thing, so we don't risk someone + * having closed it before we finish setup + */ + ret = io_uring_install_fd(ctx, file); + if (ret < 0) { + /* fput will clean it up */ + fput(file); + return ret; + } + + trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); + return ret; +err: + io_ring_ctx_wait_and_kill(ctx); + return ret; +} + +/* + * Sets up an aio uring context, and returns the fd. Applications asks for a + * ring size, we return the actual sq/cq ring sizes (among other things) in the + * params structure passed in. + */ +static long io_uring_setup(u32 entries, struct io_uring_params __user *params) +{ + struct io_uring_params p; + int i; + + if (copy_from_user(&p, params, sizeof(p))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(p.resv); i++) { + if (p.resv[i]) + return -EINVAL; + } + + if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | + IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | + IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | + IORING_SETUP_R_DISABLED)) + return -EINVAL; + + return io_uring_create(entries, &p, params); +} + +SYSCALL_DEFINE2(io_uring_setup, u32, entries, + struct io_uring_params __user *, params) +{ + return io_uring_setup(entries, params); +} + +static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) +{ + struct io_uring_probe *p; + size_t size; + int i, ret; + + size = struct_size(p, ops, nr_args); + if (size == SIZE_MAX) + return -EOVERFLOW; + p = kzalloc(size, GFP_KERNEL); + if (!p) + return -ENOMEM; + + ret = -EFAULT; + if (copy_from_user(p, arg, size)) + goto out; + ret = -EINVAL; + if (memchr_inv(p, 0, size)) + goto out; + + p->last_op = IORING_OP_LAST - 1; + if (nr_args > IORING_OP_LAST) + nr_args = IORING_OP_LAST; + + for (i = 0; i < nr_args; i++) { + p->ops[i].op = i; + if (!io_op_defs[i].not_supported) + p->ops[i].flags = IO_URING_OP_SUPPORTED; + } + p->ops_len = i; + + ret = 0; + if (copy_to_user(arg, p, size)) + ret = -EFAULT; +out: + kfree(p); + return ret; +} + +static int io_register_personality(struct io_ring_ctx *ctx) +{ + const struct cred *creds; + u32 id; + int ret; + + creds = get_current_cred(); + + ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, + XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); + if (ret < 0) { + put_cred(creds); + return ret; + } + return id; +} + +static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args) +{ + struct io_uring_restriction *res; + size_t size; + int i, ret; + + /* Restrictions allowed only if rings started disabled */ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EBADFD; + + /* We allow only a single restrictions registration */ + if (ctx->restrictions.registered) + return -EBUSY; + + if (!arg || nr_args > IORING_MAX_RESTRICTIONS) + return -EINVAL; + + size = array_size(nr_args, sizeof(*res)); + if (size == SIZE_MAX) + return -EOVERFLOW; + + res = memdup_user(arg, size); + if (IS_ERR(res)) + return PTR_ERR(res); + + ret = 0; + + for (i = 0; i < nr_args; i++) { + switch (res[i].opcode) { + case IORING_RESTRICTION_REGISTER_OP: + if (res[i].register_op >= IORING_REGISTER_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].register_op, + ctx->restrictions.register_op); + break; + case IORING_RESTRICTION_SQE_OP: + if (res[i].sqe_op >= IORING_OP_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); + break; + case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: + ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags; + break; + case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: + ctx->restrictions.sqe_flags_required = res[i].sqe_flags; + break; + default: + ret = -EINVAL; + goto out; + } + } + +out: + /* Reset all restrictions if an error happened */ + if (ret != 0) + memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); + else + ctx->restrictions.registered = true; + + kfree(res); + return ret; +} + +static int io_register_enable_rings(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EBADFD; + + if (ctx->restrictions.registered) + ctx->restricted = 1; + + ctx->flags &= ~IORING_SETUP_R_DISABLED; + if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + return 0; +} + +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + __u32 tmp; + int err; + + if (check_add_overflow(up->offset, nr_args, &tmp)) + return -EOVERFLOW; + err = io_rsrc_node_switch_start(ctx); + if (err) + return err; + + switch (type) { + case IORING_RSRC_FILE: + return __io_sqe_files_update(ctx, up, nr_args); + case IORING_RSRC_BUFFER: + return __io_sqe_buffers_update(ctx, up, nr_args); + } + return -EINVAL; +} + +static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update2 up; + + if (!nr_args) + return -EINVAL; + memset(&up, 0, sizeof(up)); + if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) + return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); +} + +static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned size, unsigned type) +{ + struct io_uring_rsrc_update2 up; + + if (size != sizeof(up)) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (!up.nr || up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, type, &up, up.nr); +} + +static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, + unsigned int size, unsigned int type) +{ + struct io_uring_rsrc_register rr; + + /* keep it extendible */ + if (size != sizeof(rr)) + return -EINVAL; + + memset(&rr, 0, sizeof(rr)); + if (copy_from_user(&rr, arg, size)) + return -EFAULT; + if (!rr.nr || rr.resv || rr.resv2) + return -EINVAL; + + switch (type) { + case IORING_RSRC_FILE: + return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + case IORING_RSRC_BUFFER: + return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + } + return -EINVAL; +} + +static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, + unsigned len) +{ + struct io_uring_task *tctx = current->io_uring; + cpumask_var_t new_mask; + int ret; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(new_mask); + if (len > cpumask_size()) + len = cpumask_size(); + +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } +#else + ret = copy_from_user(new_mask, arg, len); +#endif + + if (ret) { + free_cpumask_var(new_mask); + return -EFAULT; + } + + ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + free_cpumask_var(new_mask); + return ret; +} + +static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + return io_wq_cpu_affinity(tctx->io_wq, NULL); +} + +static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, + void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_tctx_node *node; + struct io_uring_task *tctx = NULL; + struct io_sq_data *sqd = NULL; + __u32 new_count[2]; + int i, ret; + + if (copy_from_user(new_count, arg, sizeof(new_count))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i] > INT_MAX) + return -EINVAL; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + sqd = ctx->sq_data; + if (sqd) { + /* + * Observe the correct sqd->lock -> ctx->uring_lock + * ordering. Fine to drop uring_lock here, we hold + * a ref to the ctx. + */ + refcount_inc(&sqd->refs); + mutex_unlock(&ctx->uring_lock); + mutex_lock(&sqd->lock); + mutex_lock(&ctx->uring_lock); + if (sqd->thread) + tctx = sqd->thread->io_uring; + } + } else { + tctx = current->io_uring; + } + + BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i]) + ctx->iowq_limits[i] = new_count[i]; + ctx->iowq_limits_set = true; + + ret = -EINVAL; + if (tctx && tctx->io_wq) { + ret = io_wq_max_workers(tctx->io_wq, new_count); + if (ret) + goto err; + } else { + memset(new_count, 0, sizeof(new_count)); + } + + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + + if (copy_to_user(arg, new_count, sizeof(new_count))) + return -EFAULT; + + /* that's it for SQPOLL, only the SQPOLL task creates requests */ + if (sqd) + return 0; + + /* now propagate the restriction to all registered users */ + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + if (WARN_ON_ONCE(!tctx->io_wq)) + continue; + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + new_count[i] = ctx->iowq_limits[i]; + /* ignore errors, it always returns zero anyway */ + (void)io_wq_max_workers(tctx->io_wq, new_count); + } + return 0; +err: + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + return ret; +} + +static bool io_register_op_must_quiesce(int op) +{ + switch (op) { + case IORING_REGISTER_BUFFERS: + case IORING_UNREGISTER_BUFFERS: + case IORING_REGISTER_FILES: + case IORING_UNREGISTER_FILES: + case IORING_REGISTER_FILES_UPDATE: + case IORING_REGISTER_PROBE: + case IORING_REGISTER_PERSONALITY: + case IORING_UNREGISTER_PERSONALITY: + case IORING_REGISTER_FILES2: + case IORING_REGISTER_FILES_UPDATE2: + case IORING_REGISTER_BUFFERS2: + case IORING_REGISTER_BUFFERS_UPDATE: + case IORING_REGISTER_IOWQ_AFF: + case IORING_UNREGISTER_IOWQ_AFF: + case IORING_REGISTER_IOWQ_MAX_WORKERS: + return false; + default: + return true; + } +} + +static int io_ctx_quiesce(struct io_ring_ctx *ctx) +{ + long ret; + + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab the + * uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); + do { + ret = wait_for_completion_interruptible(&ctx->ref_comp); + if (!ret) + break; + ret = io_run_task_work_sig(); + } while (ret >= 0); + mutex_lock(&ctx->uring_lock); + + if (ret) + io_refs_resurrect(&ctx->refs, &ctx->ref_comp); + return ret; +} + +static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, + void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) +{ + int ret; + + /* + * We're inside the ring mutex, if the ref is already dying, then + * someone else killed the ctx or is already going through + * io_uring_register(). + */ + if (percpu_ref_is_dying(&ctx->refs)) + return -ENXIO; + + if (ctx->restricted) { + opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); + if (!test_bit(opcode, ctx->restrictions.register_op)) + return -EACCES; + } + + if (io_register_op_must_quiesce(opcode)) { + ret = io_ctx_quiesce(ctx); + if (ret) + return ret; + } + + switch (opcode) { + case IORING_REGISTER_BUFFERS: + ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); + break; + case IORING_UNREGISTER_BUFFERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_buffers_unregister(ctx); + break; + case IORING_REGISTER_FILES: + ret = io_sqe_files_register(ctx, arg, nr_args, NULL); + break; + case IORING_UNREGISTER_FILES: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_files_unregister(ctx); + break; + case IORING_REGISTER_FILES_UPDATE: + ret = io_register_files_update(ctx, arg, nr_args); + break; + case IORING_REGISTER_EVENTFD: + case IORING_REGISTER_EVENTFD_ASYNC: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_eventfd_register(ctx, arg); + if (ret) + break; + if (opcode == IORING_REGISTER_EVENTFD_ASYNC) + ctx->eventfd_async = 1; + else + ctx->eventfd_async = 0; + break; + case IORING_UNREGISTER_EVENTFD: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_eventfd_unregister(ctx); + break; + case IORING_REGISTER_PROBE: + ret = -EINVAL; + if (!arg || nr_args > 256) + break; + ret = io_probe(ctx, arg, nr_args); + break; + case IORING_REGISTER_PERSONALITY: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_personality(ctx); + break; + case IORING_UNREGISTER_PERSONALITY: + ret = -EINVAL; + if (arg) + break; + ret = io_unregister_personality(ctx, nr_args); + break; + case IORING_REGISTER_ENABLE_RINGS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_enable_rings(ctx); + break; + case IORING_REGISTER_RESTRICTIONS: + ret = io_register_restrictions(ctx, arg, nr_args); + break; + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_IOWQ_AFF: + ret = -EINVAL; + if (!arg || !nr_args) + break; + ret = io_register_iowq_aff(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_IOWQ_AFF: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_unregister_iowq_aff(ctx); + break; + case IORING_REGISTER_IOWQ_MAX_WORKERS: + ret = -EINVAL; + if (!arg || nr_args != 2) + break; + ret = io_register_iowq_max_workers(ctx, arg); + break; + default: + ret = -EINVAL; + break; + } + + if (io_register_op_must_quiesce(opcode)) { + /* bring the ctx back to life */ + percpu_ref_reinit(&ctx->refs); + reinit_completion(&ctx->ref_comp); + } + return ret; +} + +SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, + void __user *, arg, unsigned int, nr_args) +{ + struct io_ring_ctx *ctx; + long ret = -EBADF; + struct fd f; + + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = -EOPNOTSUPP; + if (f.file->f_op != &io_uring_fops) + goto out_fput; + + ctx = f.file->private_data; + + io_run_task_work(); + + mutex_lock(&ctx->uring_lock); + ret = __io_uring_register(ctx, opcode, arg, nr_args); + mutex_unlock(&ctx->uring_lock); + trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, + ctx->cq_ev_fd != NULL, ret); +out_fput: + fdput(f); + return ret; +} + +static int __init io_uring_init(void) +{ +#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \ + BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \ + BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \ +} while (0) + +#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \ + __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename) + BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64); + BUILD_BUG_SQE_ELEM(0, __u8, opcode); + BUILD_BUG_SQE_ELEM(1, __u8, flags); + BUILD_BUG_SQE_ELEM(2, __u16, ioprio); + BUILD_BUG_SQE_ELEM(4, __s32, fd); + 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); + BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags); + BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags); + BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events); + BUILD_BUG_SQE_ELEM(28, __u32, poll32_events); + BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags); + BUILD_BUG_SQE_ELEM(28, __u32, msg_flags); + BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags); + BUILD_BUG_SQE_ELEM(28, __u32, accept_flags); + BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags); + 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(40, __u16, buf_group); + BUILD_BUG_SQE_ELEM(42, __u16, personality); + BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); + BUILD_BUG_SQE_ELEM(44, __u32, file_index); + + BUILD_BUG_ON(sizeof(struct io_uring_files_update) != + sizeof(struct io_uring_rsrc_update)); + BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > + sizeof(struct io_uring_rsrc_update2)); + + /* ->buf_index is u16 */ + BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + + /* should fit into one byte */ + BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); + + 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 | + SLAB_ACCOUNT); + return 0; +}; +__initcall(io_uring_init); |