forked from Minki/linux
b48c312be0
Following user feedback, this patch simplifies zerocopy send API. One of the main complaints is that the current API is difficult with the userspace managing notification slots, and then send retries with error handling make it even worse. Instead of keeping notification slots change it to the per-request notifications model, which posts both completion and notification CQEs for each request when any data has been sent, and only one CQE if it fails. All notification CQEs will have IORING_CQE_F_NOTIF set and IORING_CQE_F_MORE in completion CQEs indicates whether to wait a notification or not. IOSQE_CQE_SKIP_SUCCESS is disallowed with zerocopy sends for now. This is less flexible, but greatly simplifies the user API and also the kernel implementation. We reuse notif helpers in this patch, but in the future there won't be need for keeping two requests. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/95287640ab98fc9417370afb16e310677c63e6ce.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
41 lines
896 B
C
41 lines
896 B
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/net.h>
|
|
#include <linux/uio.h>
|
|
#include <net/sock.h>
|
|
#include <linux/nospec.h>
|
|
|
|
#include "rsrc.h"
|
|
|
|
#define IO_NOTIF_SPLICE_BATCH 32
|
|
|
|
struct io_notif_data {
|
|
struct file *file;
|
|
struct ubuf_info uarg;
|
|
unsigned long account_pages;
|
|
};
|
|
|
|
void io_notif_flush(struct io_kiocb *notif);
|
|
struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx);
|
|
|
|
static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif)
|
|
{
|
|
return io_kiocb_to_cmd(notif, struct io_notif_data);
|
|
}
|
|
|
|
static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len)
|
|
{
|
|
struct io_ring_ctx *ctx = notif->ctx;
|
|
struct io_notif_data *nd = io_notif_to_data(notif);
|
|
unsigned nr_pages = (len >> PAGE_SHIFT) + 2;
|
|
int ret;
|
|
|
|
if (ctx->user) {
|
|
ret = __io_account_mem(ctx->user, nr_pages);
|
|
if (ret)
|
|
return ret;
|
|
nd->account_pages += nr_pages;
|
|
}
|
|
return 0;
|
|
}
|