struct io_kiocb *req, *tmp;
struct io_tw_state ts = { .locked = true, };
+ percpu_ref_get(&ctx->refs);
mutex_lock(&ctx->uring_lock);
llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
req->io_task_work.func(req, &ts);
return;
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
+ percpu_ref_put(&ctx->refs);
}
static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
INIT_LIST_HEAD(&ctx->sqd_list);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
INIT_LIST_HEAD(&ctx->io_buffers_cache);
+ INIT_HLIST_HEAD(&ctx->io_buf_list);
io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
sizeof(struct io_rsrc_node));
io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX,
io_req_complete_defer(req);
else
io_req_complete_post(req, issue_flags);
- } else if (ret != IOU_ISSUE_SKIP_COMPLETE)
+
+ return 0;
+ }
+
+ if (ret != IOU_ISSUE_SKIP_COMPLETE)
return ret;
/* If the op doesn't have a file, we're not polling for it */
__set_current_state(TASK_RUNNING);
atomic_set(&ctx->cq_wait_nr, 0);
- if (ret < 0)
- break;
/*
* Run task_work after scheduling and before io_should_wake().
* If we got woken because of task_work being processed, run it
if (!llist_empty(&ctx->work_llist))
io_run_local_work(ctx);
+ /*
+ * Non-local task_work will be run on exit to userspace, but
+ * if we're using DEFER_TASKRUN, then we could have waited
+ * with a timeout for a number of requests. If the timeout
+ * hits, we could have some requests ready to process. Ensure
+ * this break is _after_ we have run task_work, to avoid
+ * deferring running potentially pending requests until the
+ * next time we wait for events.
+ */
+ if (ret < 0)
+ break;
+
check_cq = READ_ONCE(ctx->check_cq);
if (unlikely(check_cq)) {
/* let the caller flush overflows, retry */
return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
}
-static void io_mem_free(void *ptr)
+void io_mem_free(void *ptr)
{
if (!ptr)
return;
{
struct page **page_array;
unsigned int nr_pages;
+ void *page_addr;
int ret, i;
*npages = 0;
io_pages_free(&page_array, ret > 0 ? ret : 0);
return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT);
}
- /*
- * Should be a single page. If the ring is small enough that we can
- * use a normal page, that is fine. If we need multiple pages, then
- * userspace should use a huge page. That's the only way to guarantee
- * that we get contigious memory, outside of just being lucky or
- * (currently) having low memory fragmentation.
- */
- if (page_array[0] != page_array[ret - 1])
- goto err;
- /*
- * Can't support mapping user allocated ring memory on 32-bit archs
- * where it could potentially reside in highmem. Just fail those with
- * -EINVAL, just like we did on kernels that didn't support this
- * feature.
- */
+ page_addr = page_address(page_array[0]);
for (i = 0; i < nr_pages; i++) {
- if (PageHighMem(page_array[i])) {
- ret = -EINVAL;
+ ret = -EINVAL;
+
+ /*
+ * Can't support mapping user allocated ring memory on 32-bit
+ * archs where it could potentially reside in highmem. Just
+ * fail those with -EINVAL, just like we did on kernels that
+ * didn't support this feature.
+ */
+ if (PageHighMem(page_array[i]))
goto err;
- }
+
+ /*
+ * No support for discontig pages for now, should either be a
+ * single normal page, or a huge page. Later on we can add
+ * support for remapping discontig pages, for now we will
+ * just fail them with EINVAL.
+ */
+ if (page_address(page_array[i]) != page_addr)
+ goto err;
+ page_addr += PAGE_SIZE;
}
*pages = page_array;
}
}
-static void *io_mem_alloc(size_t size)
+void *io_mem_alloc(size_t size)
{
gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
void *ret;
ctx->mm_account = NULL;
}
io_rings_free(ctx);
+ io_kbuf_mmap_list_free(ctx);
percpu_ref_exit(&ctx->refs);
free_uid(ctx->user);
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));
struct page *page;
void *ptr;
- /* Don't allow mmap if the ring was setup without it */
- if (ctx->flags & IORING_SETUP_NO_MMAP)
- return ERR_PTR(-EINVAL);
-
switch (offset & IORING_OFF_MMAP_MASK) {
case IORING_OFF_SQ_RING:
case IORING_OFF_CQ_RING:
+ /* Don't allow mmap if the ring was setup without it */
+ if (ctx->flags & IORING_SETUP_NO_MMAP)
+ return ERR_PTR(-EINVAL);
ptr = ctx->rings;
break;
case IORING_OFF_SQES:
+ /* Don't allow mmap if the ring was setup without it */
+ if (ctx->flags & IORING_SETUP_NO_MMAP)
+ return ERR_PTR(-EINVAL);
ptr = ctx->sq_sqes;
break;
case IORING_OFF_PBUF_RING: {
unsigned int bgid;
bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
- mutex_lock(&ctx->uring_lock);
+ rcu_read_lock();
ptr = io_pbuf_get_address(ctx, bgid);
- mutex_unlock(&ctx->uring_lock);
+ rcu_read_unlock();
if (!ptr)
return ERR_PTR(-EINVAL);
break;
size_t, argsz)
{
struct io_ring_ctx *ctx;
- struct fd f;
+ struct file *file;
long ret;
if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
return -EINVAL;
fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
- f.file = tctx->registered_rings[fd];
- f.flags = 0;
- if (unlikely(!f.file))
+ file = tctx->registered_rings[fd];
+ if (unlikely(!file))
return -EBADF;
} else {
- f = fdget(fd);
- if (unlikely(!f.file))
+ file = fget(fd);
+ if (unlikely(!file))
return -EBADF;
ret = -EOPNOTSUPP;
- if (unlikely(!io_is_uring_fops(f.file)))
+ if (unlikely(!io_is_uring_fops(file)))
goto out;
}
- ctx = f.file->private_data;
+ ctx = file->private_data;
ret = -EBADFD;
if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
goto out;
}
}
out:
- fdput(f);
+ if (!(flags & IORING_ENTER_REGISTERED_RING))
+ fput(file);
return ret;
}
{
struct io_ring_ctx *ctx;
long ret = -EBADF;
- struct fd f;
+ struct file *file;
bool use_registered_ring;
use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
return -EINVAL;
fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
- f.file = tctx->registered_rings[fd];
- f.flags = 0;
- if (unlikely(!f.file))
+ file = tctx->registered_rings[fd];
+ if (unlikely(!file))
return -EBADF;
} else {
- f = fdget(fd);
- if (unlikely(!f.file))
+ file = fget(fd);
+ if (unlikely(!file))
return -EBADF;
ret = -EOPNOTSUPP;
- if (!io_is_uring_fops(f.file))
+ if (!io_is_uring_fops(file))
goto out_fput;
}
- ctx = f.file->private_data;
+ ctx = file->private_data;
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, ret);
out_fput:
- fdput(f);
+ if (!use_registered_ring)
+ fput(file);
return ret;
}