struct io_mapped_ubuf **pimu,
struct page **last_hpage);
-#define IO_RSRC_REF_BATCH 100
-
/* only define max */
#define IORING_MAX_FIXED_FILES (1U << 20)
#define IORING_MAX_REG_BUFFERS (1U << 14)
-void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- if (ctx->rsrc_cached_refs) {
- io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs);
- ctx->rsrc_cached_refs = 0;
- }
-}
-
int __io_account_mem(struct user_struct *user, unsigned long nr_pages)
{
unsigned long page_limit, cur_pages, new_pages;
*slot = NULL;
}
-void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
- percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
-}
-
-static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
+static void io_rsrc_put_work(struct io_rsrc_data *rsrc_data,
+ struct io_rsrc_put *prsrc)
{
- 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) {
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- mutex_lock(&ctx->uring_lock);
- io_post_aux_cqe(ctx, prsrc->tag, 0, 0);
- mutex_unlock(&ctx->uring_lock);
- } else {
- io_post_aux_cqe(ctx, prsrc->tag, 0, 0);
- }
- }
-
- 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);
-}
-
-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;
- }
+ if (prsrc->tag)
+ io_post_aux_cqe(ctx, prsrc->tag, 0, 0);
+ rsrc_data->do_put(ctx, prsrc);
}
-void io_rsrc_put_tw(struct callback_head *cb)
+void io_rsrc_node_destroy(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
{
- struct io_ring_ctx *ctx = container_of(cb, struct io_ring_ctx,
- rsrc_put_tw);
-
- io_rsrc_put_work(&ctx->rsrc_put_work.work);
+ if (!io_alloc_cache_put(&ctx->rsrc_node_cache, &node->cache))
+ kfree(node);
}
-void io_wait_rsrc_data(struct io_rsrc_data *data)
+void io_rsrc_node_ref_zero(struct io_rsrc_node *node)
+ __must_hold(&node->rsrc_data->ctx->uring_lock)
{
- if (data && !atomic_dec_and_test(&data->refs))
- wait_for_completion(&data->done);
-}
-
-void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
-{
- percpu_ref_exit(&ref_node->refs);
- kfree(ref_node);
-}
-
-static __cold 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)
+ if (node->refs)
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)
- return;
- if (ctx->submitter_task) {
- if (!task_work_add(ctx->submitter_task, &ctx->rsrc_put_tw,
- ctx->notify_method))
- return;
+ if (likely(!node->empty))
+ io_rsrc_put_work(node->rsrc_data, &node->item);
+ io_rsrc_node_destroy(ctx, node);
}
- mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay);
+ if (list_empty(&ctx->rsrc_ref_list) && unlikely(ctx->rsrc_quiesce))
+ wake_up_all(&ctx->rsrc_quiesce_wq);
}
-static struct io_rsrc_node *io_rsrc_node_alloc(void)
+struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
{
struct io_rsrc_node *ref_node;
+ struct io_cache_entry *entry;
- 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;
-}
-
-void io_rsrc_node_switch(struct io_ring_ctx *ctx,
- struct io_rsrc_data *data_to_kill)
- __must_hold(&ctx->uring_lock)
-{
- WARN_ON_ONCE(!ctx->rsrc_backup_node);
- WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);
-
- io_rsrc_refs_drop(ctx);
-
- 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;
+ entry = io_alloc_cache_get(&ctx->rsrc_node_cache);
+ if (entry) {
+ ref_node = container_of(entry, struct io_rsrc_node, cache);
+ } else {
+ ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL);
+ if (!ref_node)
+ return NULL;
}
-}
-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();
- return ctx->rsrc_backup_node ? 0 : -ENOMEM;
+ ref_node->rsrc_data = NULL;
+ ref_node->empty = 0;
+ ref_node->refs = 1;
+ return ref_node;
}
__cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
struct io_ring_ctx *ctx)
{
+ struct io_rsrc_node *backup;
+ DEFINE_WAIT(we);
int ret;
- /* As we may drop ->uring_lock, other task may have started quiesce */
+ /* As We may drop ->uring_lock, other task may have started quiesce */
if (data->quiesce)
return -ENXIO;
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- return ret;
- io_rsrc_node_switch(ctx, data);
- /* kill initial ref, already quiesced if zero */
- if (atomic_dec_and_test(&data->refs))
+ backup = io_rsrc_node_alloc(ctx);
+ if (!backup)
+ return -ENOMEM;
+ ctx->rsrc_node->empty = true;
+ ctx->rsrc_node->rsrc_data = data;
+ list_add_tail(&ctx->rsrc_node->node, &ctx->rsrc_ref_list);
+ io_put_rsrc_node(ctx, ctx->rsrc_node);
+ ctx->rsrc_node = backup;
+
+ if (list_empty(&ctx->rsrc_ref_list))
return 0;
+ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
+ atomic_set(&ctx->cq_wait_nr, 1);
+ smp_mb();
+ }
+
+ ctx->rsrc_quiesce++;
data->quiesce = true;
- mutex_unlock(&ctx->uring_lock);
do {
+ prepare_to_wait(&ctx->rsrc_quiesce_wq, &we, TASK_INTERRUPTIBLE);
+ mutex_unlock(&ctx->uring_lock);
+
ret = io_run_task_work_sig(ctx);
if (ret < 0) {
- atomic_inc(&data->refs);
- /* wait for all works potentially completing data->done */
- flush_delayed_work(&ctx->rsrc_put_work);
- reinit_completion(&data->done);
mutex_lock(&ctx->uring_lock);
+ if (list_empty(&ctx->rsrc_ref_list))
+ ret = 0;
break;
}
- 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)
- break;
- /*
- * it has been revived by another thread while
- * we were unlocked
- */
- mutex_unlock(&ctx->uring_lock);
- }
- } while (1);
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ mutex_lock(&ctx->uring_lock);
+ ret = 0;
+ } while (!list_empty(&ctx->rsrc_ref_list));
+
+ finish_wait(&ctx->rsrc_quiesce_wq, &we);
data->quiesce = false;
+ ctx->rsrc_quiesce--;
+ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
+ atomic_set(&ctx->cq_wait_nr, 0);
+ smp_mb();
+ }
return ret;
}
goto fail;
}
}
-
- atomic_set(&data->refs, 1);
- init_completion(&data->done);
*pdata = data;
return 0;
fail:
struct file *file;
int fd, i, err = 0;
unsigned int done;
- bool needs_switch = false;
if (!ctx->file_data)
return -ENXIO;
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);
+ err = io_queue_rsrc_removal(data, i, file);
if (err)
break;
file_slot->file_ptr = 0;
io_file_bitmap_clear(&ctx->file_table, i);
- needs_switch = true;
}
if (fd != -1) {
file = fget(fd);
io_file_bitmap_set(&ctx->file_table, i);
}
}
-
- if (needs_switch)
- io_rsrc_node_switch(ctx, data);
return done ? done : err;
}
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;
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;
- i = array_index_nospec(offset, ctx->nr_user_bufs);
+ i = array_index_nospec(up->offset + done, 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]);
+ ctx->user_bufs[i]);
if (unlikely(err)) {
io_buffer_unmap(ctx, &imu);
break;
}
ctx->user_bufs[i] = ctx->dummy_ubuf;
- needs_switch = true;
}
ctx->user_bufs[i] = imu;
- *io_get_tag_slot(ctx->buf_data, offset) = tag;
+ *io_get_tag_slot(ctx->buf_data, i) = tag;
}
-
- if (needs_switch)
- io_rsrc_node_switch(ctx, ctx->buf_data);
return done ? done : err;
}
unsigned nr_args)
{
__u32 tmp;
- int err;
+
+ lockdep_assert_held(&ctx->uring_lock);
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 IOU_OK;
}
-int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
- struct io_rsrc_node *node, void *rsrc)
+int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, void *rsrc)
{
+ struct io_ring_ctx *ctx = data->ctx;
+ struct io_rsrc_node *node = ctx->rsrc_node;
u64 *tag_slot = io_get_tag_slot(data, idx);
- struct io_rsrc_put *prsrc;
- prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
- if (!prsrc)
+ ctx->rsrc_node = io_rsrc_node_alloc(ctx);
+ if (unlikely(!ctx->rsrc_node)) {
+ ctx->rsrc_node = node;
return -ENOMEM;
+ }
- prsrc->tag = *tag_slot;
+ node->item.rsrc = rsrc;
+ node->item.tag = *tag_slot;
*tag_slot = 0;
- prsrc->rsrc = rsrc;
- list_add(&prsrc->list, &node->rsrc_list);
+
+ node->rsrc_data = data;
+ list_add_tail(&node->node, &ctx->rsrc_ref_list);
+ io_put_rsrc_node(ctx, node);
return 0;
}
return 0;
}
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
+static __cold void io_rsrc_file_scm_put(struct io_ring_ctx *ctx, struct file *file)
{
- 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;
- if (!io_file_need_scm(file)) {
- fput(file);
- return;
- }
-
__skb_queue_head_init(&list);
/*
__skb_queue_tail(head, skb);
spin_unlock_irq(&head->lock);
}
-#else
- fput(file);
#endif
}
+static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
+{
+ struct file *file = prsrc->file;
+
+ if (likely(!io_file_need_scm(file)))
+ fput(file);
+ else
+ io_rsrc_file_scm_put(ctx, file);
+}
+
int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args, u64 __user *tags)
{
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)
/* default it to the whole table */
io_file_table_set_alloc_range(ctx, 0, ctx->nr_user_files);
- io_rsrc_node_switch(ctx, NULL);
return 0;
fail:
__io_sqe_files_unregister(ctx);
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;
ctx->buf_data = data;
if (ret)
__io_sqe_buffers_unregister(ctx);
- else
- io_rsrc_node_switch(ctx, NULL);
return ret;
}