struct work_struct exit_work;
struct list_head tctx_list;
struct completion ref_comp;
+ u32 iowq_limits[2];
+ bool iowq_limits_set;
};
};
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;
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 io_unprep_linked_timeout(struct io_kiocb *req)
-{
- req->flags &= ~REQ_F_LINK_TIMEOUT;
-}
-
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
if (req->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = req->ctx;
- spin_lock(&ctx->completion_lock);
+ spin_lock_irq(&ctx->timeout_lock);
io_for_each_link(cur, req)
io_prep_async_work(cur);
- spin_unlock(&ctx->completion_lock);
+ spin_unlock_irq(&ctx->timeout_lock);
} else {
io_for_each_link(cur, req)
io_prep_async_work(cur);
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,
long res, unsigned int cflags)
{
}
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)
req->flags |= REQ_F_ISREG;
kiocb->ki_pos = READ_ONCE(sqe->off);
- if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) {
- req->flags |= REQ_F_CUR_POS;
- kiocb->ki_pos = file->f_pos;
+ if (kiocb->ki_pos == -1) {
+ if (!(file->f_mode & FMODE_STREAM)) {
+ req->flags |= REQ_F_CUR_POS;
+ kiocb->ki_pos = file->f_pos;
+ } else {
+ kiocb->ki_pos = 0;
+ }
}
kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
kfree(nxt);
if (++i == nbufs)
return i;
+ cond_resched();
}
i++;
kfree(buf);
} else {
list_add_tail(&buf->list, &(*head)->list);
}
+ cond_resched();
}
return i ? i : -ENOMEM;
list = &ctx->cancel_hash[i];
hlist_for_each_entry_safe(req, tmp, list, hash_node) {
- if (io_match_task(req, tsk, cancel_all))
+ if (io_match_task_safe(req, tsk, cancel_all))
posted += io_poll_remove_one(req);
}
}
* update those. For multishot, if we're racing with completion, just
* let completion re-add it.
*/
+ io_poll_remove_double(preq);
completing = !__io_poll_remove_one(preq, &preq->poll, false);
if (completing && (preq->poll.events & EPOLLONESHOT)) {
ret = -EALREADY;
}
/* 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 */
static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
{
struct io_kiocb *prev = req->timeout.prev;
- int ret;
+ int ret = -ENOENT;
if (prev) {
- ret = io_try_cancel_userdata(req, prev->user_data);
+ 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 {
switch (io_arm_poll_handler(req)) {
case IO_APOLL_READY:
if (linked_timeout)
- io_unprep_linked_timeout(req);
+ io_queue_linked_timeout(linked_timeout);
goto issue_sqe;
case IO_APOLL_ABORTED:
/*
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- signed long *timeout)
+ ktime_t timeout)
{
int ret;
if (test_bit(0, &ctx->check_cq_overflow))
return 1;
- *timeout = schedule_timeout(*timeout);
- return !*timeout ? -ETIME : 1;
+ if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ return -ETIME;
+ return 1;
}
/*
{
struct io_wait_queue iowq;
struct io_rings *rings = ctx->rings;
- signed long timeout = MAX_SCHEDULE_TIMEOUT;
+ ktime_t timeout = KTIME_MAX;
int ret;
do {
if (get_timespec64(&ts, uts))
return -EFAULT;
- timeout = timespec64_to_jiffies(&ts);
+ timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
}
if (sig) {
}
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
finish_wait(&ctx->cq_wait, &iowq.wq);
cond_resched();
} while (ret > 0);
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);
spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags);
if (first_add)
- mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ);
+ mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay);
}
static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
ret = wait_for_completion_interruptible(&data->done);
if (!ret) {
mutex_lock(&ctx->uring_lock);
- break;
+ 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);
static void *io_mem_alloc(size_t size)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP |
- __GFP_NORETRY | __GFP_ACCOUNT;
+ gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
- return (void *) __get_free_pages(gfp_flags, get_order(size));
+ return (void *) __get_free_pages(gfp, get_order(size));
}
static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries,
struct io_buffer *buf;
unsigned long index;
- xa_for_each(&ctx->io_buffers, index, buf) {
+ xa_for_each(&ctx->io_buffers, index, buf)
__io_remove_buffers(ctx, buf, index, -1U);
- cond_resched();
- }
}
static void io_req_cache_free(struct list_head *list)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct io_task_cancel *cancel = data;
- bool ret;
-
- if (!cancel->all && (req->flags & REQ_F_LINK_TIMEOUT)) {
- struct io_ring_ctx *ctx = req->ctx;
- /* protect against races with linked timeouts */
- spin_lock(&ctx->completion_lock);
- ret = io_match_task(req, cancel->task, cancel->all);
- spin_unlock(&ctx->completion_lock);
- } else {
- ret = io_match_task(req, cancel->task, cancel->all);
- }
- return ret;
+ return io_match_task_safe(req, cancel->task, cancel->all);
}
static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
spin_lock(&ctx->completion_lock);
list_for_each_entry_reverse(de, &ctx->defer_list, list) {
- if (io_match_task(de->req, task, cancel_all)) {
+ if (io_match_task_safe(de->req, task, cancel_all)) {
list_cut_position(&list, &ctx->defer_list, &de->list);
break;
}
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);
return percpu_counter_sum(&tctx->inflight);
}
-static 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);
- }
-}
-
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
+ * 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)
{
cancel_all);
}
- prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+ 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
schedule();
finish_wait(&tctx->wait, &wait);
} while (1);
- atomic_dec(&tctx->in_idle);
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);
}
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];
tctx = current->io_uring;
}
- ret = -EINVAL;
- if (!tctx || !tctx->io_wq)
- goto err;
+ BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
- ret = io_wq_max_workers(tctx->io_wq, new_count);
- if (ret)
- goto err;
+ 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);
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) {
projects / mirror_ubuntu-jammy-kernel.git / blobdiff