Files
Linus Torvalds f5437ff729 Merge tag 'for-7.3/io_uring-20260819' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux
Pull io_uring update from Jens Axboe:
 "On top of the usual cleanups and fixes, the bigger items in here are:

   - zcrx work, most of it centered around adding dynamic area
     provisioning, plus a bunch of prep and cleanups leading up to it:
     scale refilling with large pages, coalesce same-niov RQEs on
     refill, separate the RQ head/tail cache lines and cache the RQ
     tail, and rework the area creation locking.

   - Fix the futex inflight accounting so that only private futex waits
     are marked inflight, and don't mark wake requests as inflight at
     all.

   - Drop the custom iov copy in the buffer select prep and msg header
     copy paths, using the generic helpers instead.

   - Fix a folio size overflow in io_vec_fill_bvec(), and account the
     pages a compound region really uses in the memmap path.

   - Fix an iovec leak in uring_cmd when the async cmd isn't recycled,
     skip the blocking task work for io_uring_cmd_issue_blocking(), and
     don't skip completion for a synchronous multishot cmd

   - Defer eventfd signaling when queued from a wakeup handler

   - Fix io-wq worker accounting when canceling creation callbacks

   - Annotate remote tasks for kcoverage"

* tag 'for-7.3/io_uring-20260819' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (30 commits)
  io_uring: Add missing include for ITER_SOURCE and ITER_DEST
  io_uring/uring_cmd: don't skip completion for a synchronous multishot cmd
  io_uring/memmap: account the pages a compound region really uses
  io_uring/zcrx: add dynamic area provisioning
  io_uring/zcrx: lock area creation with pp_lock
  io_uring/zcrx: keep array of areas
  io_uring/zcrx: move freelist lock to struct zcrx
  io_uring/zcrx: unmap under netdev lock
  io_uring/zcrx: split dmabuf unmap and release
  io_uring/zcrx: don't pass ifq_reg to area creation
  io_uring/zcrx: add helper for deriving area token
  io_uring/zcrx: don't reload skb_shinfo
  io_urint/zcrx: narrow var scope in io_zcrx_recv_skb()
  io_uring/zcrx: constify area_reg on import
  io_uring/zcrx: coalesce same-niov RQEs on refill
  io_uring/zcrx: cache RQ tail
  io_uring/zcrx: add RQ iterator
  io_uring/zcrx: move RQ head/tail to separate cache lines
  io_uring/zcrx: scale refilling with large pages
  io_uring/io-wq: fix worker accounting when canceling creation callbacks
  ...
2026-08-20 13:47:56 -07:00

141 lines
3.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
#ifndef IOU_ZC_RX_H
#define IOU_ZC_RX_H
#include <linux/io_uring_types.h>
#include <linux/dma-buf.h>
#include <linux/socket.h>
#include <net/page_pool/types.h>
#include <net/net_trackers.h>
#define ZCRX_SUPPORTED_REG_FLAGS (ZCRX_REG_IMPORT | ZCRX_REG_NODEV)
#define ZCRX_FEATURES (ZCRX_FEATURE_RX_PAGE_SIZE |\
ZCRX_FEATURE_EVENT)
#define ZCRX_EVENT_TYPE_MASK ((1U << ZCRX_EVENT_ALLOC_FAIL) |\
(1U << ZCRX_EVENT_COPY))
struct io_zcrx_mem {
unsigned long size;
bool is_dmabuf;
struct page **pages;
unsigned long nr_folios;
struct sg_table page_sg_table;
unsigned long account_pages;
struct sg_table *sgt;
struct dma_buf_attachment *attach;
struct dma_buf *dmabuf;
};
struct io_zcrx_area {
struct net_iov_area nia;
struct io_zcrx_ifq *ifq;
atomic_t *user_refs;
bool is_mapped;
u16 area_id;
/* freelist */
u32 free_count;
u32 *freelist;
struct io_zcrx_mem mem;
};
struct zcrx_rq_hdr {
u32 head ____cacheline_aligned_in_smp;
u32 tail ____cacheline_aligned_in_smp;
};
struct zcrx_rq {
spinlock_t lock;
struct zcrx_rq_hdr *ring;
struct io_uring_zcrx_rqe *rqes;
u32 cached_head;
u32 cached_tail;
u32 nr_entries;
};
struct io_zcrx_ifq {
/* read-protected by any of: ->pp_lock, ->alloc_lock, ->rq.lock */
struct io_zcrx_area **areas;
unsigned nr_areas;
unsigned niov_shift;
struct user_struct *user;
struct mm_struct *mm_account;
bool kern_readable;
struct zcrx_rq rq ____cacheline_aligned_in_smp;
spinlock_t alloc_lock ____cacheline_aligned_in_smp;
u32 if_rxq;
struct device *dev;
struct net_device *netdev;
netdevice_tracker netdev_tracker;
refcount_t refs;
/* counts userspace facing users like io_uring */
refcount_t user_refs;
/*
* Page pool and net configuration lock, can be taken deeper in the
* net stack.
*/
struct mutex pp_lock;
struct io_mapped_region rq_region;
spinlock_t ctx_lock;
struct io_ring_ctx *master_ctx;
u32 allowed_notif_mask;
u32 fired_notifs;
u64 notif_data;
struct zcrx_stats *notif_stats;
};
#if defined(CONFIG_IO_URING_ZCRX)
int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_arg);
int io_register_zcrx(struct io_ring_ctx *ctx,
struct io_uring_zcrx_ifq_reg __user *arg);
void io_unregister_zcrx(struct io_ring_ctx *ctx);
void io_terminate_zcrx(struct io_ring_ctx *ctx);
int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
struct socket *sock, unsigned int flags,
unsigned issue_flags, unsigned int *len);
struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
unsigned int id);
#else
static inline int io_register_zcrx(struct io_ring_ctx *ctx,
struct io_uring_zcrx_ifq_reg __user *arg)
{
return -EOPNOTSUPP;
}
static inline void io_unregister_zcrx(struct io_ring_ctx *ctx)
{
}
static inline void io_terminate_zcrx(struct io_ring_ctx *ctx)
{
}
static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
struct socket *sock, unsigned int flags,
unsigned issue_flags, unsigned int *len)
{
return -EOPNOTSUPP;
}
static inline struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
unsigned int id)
{
return NULL;
}
static inline int io_zcrx_ctrl(struct io_ring_ctx *ctx,
void __user *arg, unsigned nr_arg)
{
return -EOPNOTSUPP;
}
#endif
int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
#endif