linux-next/io_uring/kbuf.h
Jens Axboe 87585b0575 io_uring/kbuf: use vm_insert_pages() for mmap'ed pbuf ring
Rather than use remap_pfn_range() for this and manually free later,
switch to using vm_insert_page() and have it Just Work.

This requires a bit of effort on the mmap lookup side, as the ctx
uring_lock isn't held, which  otherwise protects buffer_lists from being
torn down, and it's not safe to grab from mmap context that would
introduce an ABBA deadlock between the mmap lock and the ctx uring_lock.
Instead, lookup the buffer_list under RCU, as the the list is RCU freed
already. Use the existing reference count to determine whether it's
possible to safely grab a reference to it (eg if it's not zero already),
and drop that reference when done with the mapping. If the mmap
reference is the last one, the buffer_list and the associated memory can
go away, since the vma insertion has references to the inserted pages at
that point.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-04-15 08:10:26 -06:00

153 lines
4.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
#ifndef IOU_KBUF_H
#define IOU_KBUF_H
#include <uapi/linux/io_uring.h>
struct io_buffer_list {
/*
* If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not,
* then these are classic provided buffers and ->buf_list is used.
*/
union {
struct list_head buf_list;
struct {
struct page **buf_pages;
struct io_uring_buf_ring *buf_ring;
};
struct rcu_head rcu;
};
__u16 bgid;
/* below is for ring provided buffers */
__u16 buf_nr_pages;
__u16 nr_entries;
__u16 head;
__u16 mask;
atomic_t refs;
/* ring mapped provided buffers */
__u8 is_buf_ring;
/* ring mapped provided buffers, but mmap'ed by application */
__u8 is_mmap;
};
struct io_buffer {
struct list_head list;
__u64 addr;
__u32 len;
__u16 bid;
__u16 bgid;
};
void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
unsigned int issue_flags);
void io_destroy_buffers(struct io_ring_ctx *ctx);
int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags);
int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl);
struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
unsigned long bgid);
int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma);
static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
{
/*
* We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
* the flag and hence ensure that bl->head doesn't get incremented.
* If the tail has already been incremented, hang on to it.
* The exception is partial io, that case we should increment bl->head
* to monopolize the buffer.
*/
if (req->buf_list) {
req->buf_index = req->buf_list->bgid;
req->flags &= ~REQ_F_BUFFER_RING;
return true;
}
return false;
}
static inline bool io_do_buffer_select(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_BUFFER_SELECT))
return false;
return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
}
static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
{
if (req->flags & REQ_F_BL_NO_RECYCLE)
return false;
if (req->flags & REQ_F_BUFFER_SELECTED)
return io_kbuf_recycle_legacy(req, issue_flags);
if (req->flags & REQ_F_BUFFER_RING)
return io_kbuf_recycle_ring(req);
return false;
}
static inline void __io_put_kbuf_ring(struct io_kiocb *req)
{
if (req->buf_list) {
req->buf_index = req->buf_list->bgid;
req->buf_list->head++;
}
req->flags &= ~REQ_F_BUFFER_RING;
}
static inline void __io_put_kbuf_list(struct io_kiocb *req,
struct list_head *list)
{
if (req->flags & REQ_F_BUFFER_RING) {
__io_put_kbuf_ring(req);
} else {
req->buf_index = req->kbuf->bgid;
list_add(&req->kbuf->list, list);
req->flags &= ~REQ_F_BUFFER_SELECTED;
}
}
static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
{
unsigned int ret;
lockdep_assert_held(&req->ctx->completion_lock);
if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
return 0;
ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
__io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
return ret;
}
static inline unsigned int io_put_kbuf(struct io_kiocb *req,
unsigned issue_flags)
{
unsigned int ret;
if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
return 0;
ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
if (req->flags & REQ_F_BUFFER_RING)
__io_put_kbuf_ring(req);
else
__io_put_kbuf(req, issue_flags);
return ret;
}
#endif