Merge tag 'io_uring-5.8-2020-06-11' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "A few late stragglers in here. In particular:

   - Validate full range for provided buffers (Bijan)

   - Fix bad use of kfree() in buffer registration failure (Denis)

   - Don't allow close of ring itself, it's not fully safe. Making it
     fully safe would require making the system call more expensive,
     which isn't worth it.

   - Buffer selection fix

   - Regression fix for O_NONBLOCK retry

   - Make IORING_OP_ACCEPT honor O_NONBLOCK (Jiufei)

   - Restrict opcode handling for SQ/IOPOLL (Pavel)

   - io-wq work handling cleanups and improvements (Pavel, Xiaoguang)

   - IOPOLL race fix (Xiaoguang)"

* tag 'io_uring-5.8-2020-06-11' of git://git.kernel.dk/linux-block:
  io_uring: fix io_kiocb.flags modification race in IOPOLL mode
  io_uring: check file O_NONBLOCK state for accept
  io_uring: avoid unnecessary io_wq_work copy for fast poll feature
  io_uring: avoid whole io_wq_work copy for requests completed inline
  io_uring: allow O_NONBLOCK async retry
  io_wq: add per-wq work handler instead of per work
  io_uring: don't arm a timeout through work.func
  io_uring: remove custom ->func handlers
  io_uring: don't derive close state from ->func
  io_uring: use kvfree() in io_sqe_buffer_register()
  io_uring: validate the full range of provided buffers for access
  io_uring: re-set iov base/len for buffer select retry
  io_uring: move send/recv IOPOLL check into prep
  io_uring: deduplicate io_openat{,2}_prep()
  io_uring: do build_open_how() only once
  io_uring: fix {SQ,IO}POLL with unsupported opcodes
  io_uring: disallow close of ring itself
This commit is contained in:
Linus Torvalds
2020-06-11 16:10:08 -07:00
3 changed files with 203 additions and 243 deletions

View File

@@ -111,6 +111,7 @@ struct io_wq {
unsigned long state;
free_work_fn *free_work;
io_wq_work_fn *do_work;
struct task_struct *manager;
struct user_struct *user;
@@ -523,7 +524,7 @@ get_next:
hash = io_get_work_hash(work);
linked = old_work = work;
linked->func(&linked);
wq->do_work(&linked);
linked = (old_work == linked) ? NULL : linked;
work = next_hashed;
@@ -780,7 +781,7 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
struct io_wq_work *old_work = work;
work->flags |= IO_WQ_WORK_CANCEL;
work->func(&work);
wq->do_work(&work);
work = (work == old_work) ? NULL : work;
wq->free_work(old_work);
} while (work);
@@ -1018,7 +1019,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
int ret = -ENOMEM, node;
struct io_wq *wq;
if (WARN_ON_ONCE(!data->free_work))
if (WARN_ON_ONCE(!data->free_work || !data->do_work))
return ERR_PTR(-EINVAL);
wq = kzalloc(sizeof(*wq), GFP_KERNEL);
@@ -1032,6 +1033,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
}
wq->free_work = data->free_work;
wq->do_work = data->do_work;
/* caller must already hold a reference to this */
wq->user = data->user;
@@ -1088,7 +1090,7 @@ err:
bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
{
if (data->free_work != wq->free_work)
if (data->free_work != wq->free_work || data->do_work != wq->do_work)
return false;
return refcount_inc_not_zero(&wq->use_refs);