struct filename *filename;
};
+struct io_mkdir {
+ struct file *file;
+ int dfd;
+ umode_t mode;
+ struct filename *filename;
+};
+
+struct io_symlink {
+ struct file *file;
+ int new_dfd;
+ struct filename *oldpath;
+ struct filename *newpath;
+};
+
+struct io_hardlink {
+ struct file *file;
+ int old_dfd;
+ int new_dfd;
+ struct filename *oldpath;
+ struct filename *newpath;
+ int flags;
+};
+
struct io_completion {
struct file *file;
u32 cflags;
struct io_shutdown shutdown;
struct io_rename rename;
struct io_unlink unlink;
+ struct io_mkdir mkdir;
+ struct io_symlink symlink;
+ struct io_hardlink hardlink;
/* use only after cleaning per-op data, see io_clean_op() */
struct io_completion compl;
};
},
[IORING_OP_RENAMEAT] = {},
[IORING_OP_UNLINKAT] = {},
+ [IORING_OP_MKDIRAT] = {},
+ [IORING_OP_SYMLINKAT] = {},
+ [IORING_OP_LINKAT] = {},
};
/* requests with any of those set should undergo io_disarm_next() */
struct io_timeout_data *io = req->async_data;
if (hrtimer_try_to_cancel(&io->timer) != -1) {
+ if (status)
+ req_set_fail(req);
atomic_set(&req->ctx->cq_timeouts,
atomic_read(&req->ctx->cq_timeouts) + 1);
list_del_init(&req->timeout.list);
static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
{
+ /* see waitqueue_active() comment */
+ smp_mb();
+
if (ctx->flags & IORING_SETUP_SQPOLL) {
- if (wq_has_sleeper(&ctx->cq_wait))
+ if (waitqueue_active(&ctx->cq_wait))
wake_up_all(&ctx->cq_wait);
}
if (io_should_trigger_evfd(ctx))
while (1) {
struct io_wq_work_node *node;
+ if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr)
+ io_submit_flush_completions(ctx);
+
spin_lock_irq(&tctx->task_lock);
node = tctx->task_list.first;
INIT_WQ_LIST(&tctx->task_list);
{
if (__io_complete_rw_common(req, res))
return;
- __io_req_complete(req, 0, req->result, io_put_rw_kbuf(req));
+ __io_req_complete(req, issue_flags, req->result, io_put_rw_kbuf(req));
}
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
!kiocb->ki_filp->f_op->iopoll)
return -EOPNOTSUPP;
- kiocb->ki_flags |= IOCB_HIPRI;
+ kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
kiocb->ki_complete = io_complete_rw_iopoll;
req->iopoll_completed = 0;
} else {
if (req->flags & REQ_F_NOWAIT)
goto done;
/* some cases will consume bytes even on error returns */
+ iov_iter_reexpand(iter, iter->count + iter->truncated);
iov_iter_revert(iter, io_size - iov_iter_count(iter));
ret = 0;
} else if (ret == -EIOCBQUEUED) {
} else {
copy_iov:
/* some cases will consume bytes even on error returns */
+ iov_iter_reexpand(iter, iter->count + iter->truncated);
iov_iter_revert(iter, io_size - iov_iter_count(iter));
ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
return ret ?: -EAGAIN;
return 0;
}
+static int io_mkdirat_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_mkdir *mkd = &req->mkdir;
+ const char __user *fname;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index ||
+ sqe->splice_fd_in)
+ return -EINVAL;
+ if (unlikely(req->flags & REQ_F_FIXED_FILE))
+ return -EBADF;
+
+ mkd->dfd = READ_ONCE(sqe->fd);
+ mkd->mode = READ_ONCE(sqe->len);
+
+ fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ mkd->filename = getname(fname);
+ if (IS_ERR(mkd->filename))
+ return PTR_ERR(mkd->filename);
+
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return 0;
+}
+
+static int io_mkdirat(struct io_kiocb *req, int issue_flags)
+{
+ struct io_mkdir *mkd = &req->mkdir;
+ int ret;
+
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
+ ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
+
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+ if (ret < 0)
+ req_set_fail(req);
+ io_req_complete(req, ret);
+ return 0;
+}
+
+static int io_symlinkat_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_symlink *sl = &req->symlink;
+ const char __user *oldpath, *newpath;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index ||
+ sqe->splice_fd_in)
+ return -EINVAL;
+ if (unlikely(req->flags & REQ_F_FIXED_FILE))
+ return -EBADF;
+
+ sl->new_dfd = READ_ONCE(sqe->fd);
+ oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+
+ sl->oldpath = getname(oldpath);
+ if (IS_ERR(sl->oldpath))
+ return PTR_ERR(sl->oldpath);
+
+ sl->newpath = getname(newpath);
+ if (IS_ERR(sl->newpath)) {
+ putname(sl->oldpath);
+ return PTR_ERR(sl->newpath);
+ }
+
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return 0;
+}
+
+static int io_symlinkat(struct io_kiocb *req, int issue_flags)
+{
+ struct io_symlink *sl = &req->symlink;
+ int ret;
+
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
+ ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
+
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+ if (ret < 0)
+ req_set_fail(req);
+ io_req_complete(req, ret);
+ return 0;
+}
+
+static int io_linkat_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_hardlink *lnk = &req->hardlink;
+ const char __user *oldf, *newf;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+ if (sqe->ioprio || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+ return -EINVAL;
+ if (unlikely(req->flags & REQ_F_FIXED_FILE))
+ return -EBADF;
+
+ lnk->old_dfd = READ_ONCE(sqe->fd);
+ lnk->new_dfd = READ_ONCE(sqe->len);
+ oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+ lnk->flags = READ_ONCE(sqe->hardlink_flags);
+
+ lnk->oldpath = getname(oldf);
+ if (IS_ERR(lnk->oldpath))
+ return PTR_ERR(lnk->oldpath);
+
+ lnk->newpath = getname(newf);
+ if (IS_ERR(lnk->newpath)) {
+ putname(lnk->oldpath);
+ return PTR_ERR(lnk->newpath);
+ }
+
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return 0;
+}
+
+static int io_linkat(struct io_kiocb *req, int issue_flags)
+{
+ struct io_hardlink *lnk = &req->hardlink;
+ int ret;
+
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
+ ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
+ lnk->newpath, lnk->flags);
+
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+ if (ret < 0)
+ req_set_fail(req);
+ io_req_complete(req, ret);
+ return 0;
+}
+
static int io_shutdown_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
}
}
-static bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
+static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask)
__must_hold(&req->ctx->completion_lock)
{
struct io_ring_ctx *ctx = req->ctx;
if (flags & IORING_CQE_F_MORE)
ctx->cq_extra++;
- io_commit_cqring(ctx);
return !(flags & IORING_CQE_F_MORE);
}
+static inline bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
+ __must_hold(&req->ctx->completion_lock)
+{
+ bool done;
+
+ done = __io_poll_complete(req, mask);
+ io_commit_cqring(req->ctx);
+ return done;
+}
+
static void io_poll_task_func(struct io_kiocb *req, bool *locked)
{
struct io_ring_ctx *ctx = req->ctx;
} else {
bool done;
- done = io_poll_complete(req, req->result);
+ done = __io_poll_complete(req, req->result);
if (done) {
io_poll_remove_double(req);
hash_del(&req->hash_node);
req->result = 0;
add_wait_queue(req->poll.head, &req->poll.wait);
}
+ io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
return io_renameat_prep(req, sqe);
case IORING_OP_UNLINKAT:
return io_unlinkat_prep(req, sqe);
+ case IORING_OP_MKDIRAT:
+ return io_mkdirat_prep(req, sqe);
+ case IORING_OP_SYMLINKAT:
+ return io_symlinkat_prep(req, sqe);
+ case IORING_OP_LINKAT:
+ return io_linkat_prep(req, sqe);
}
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
case IORING_OP_UNLINKAT:
putname(req->unlink.filename);
break;
+ case IORING_OP_MKDIRAT:
+ putname(req->mkdir.filename);
+ break;
+ case IORING_OP_SYMLINKAT:
+ putname(req->symlink.oldpath);
+ putname(req->symlink.newpath);
+ break;
+ case IORING_OP_LINKAT:
+ putname(req->hardlink.oldpath);
+ putname(req->hardlink.newpath);
+ break;
}
}
if ((req->flags & REQ_F_POLLED) && req->apoll) {
case IORING_OP_UNLINKAT:
ret = io_unlinkat(req, issue_flags);
break;
+ case IORING_OP_MKDIRAT:
+ ret = io_mkdirat(req, issue_flags);
+ break;
+ case IORING_OP_SYMLINKAT:
+ ret = io_symlinkat(req, issue_flags);
+ break;
+ case IORING_OP_LINKAT:
+ ret = io_linkat(req, issue_flags);
+ break;
default:
ret = -EINVAL;
break;
if (ctx->flags & IORING_SETUP_SQPOLL) {
sqd = ctx->sq_data;
if (sqd) {
+ /*
+ * Observe the correct sqd->lock -> ctx->uring_lock
+ * ordering. Fine to drop uring_lock here, we hold
+ * a ref to the ctx.
+ */
+ mutex_unlock(&ctx->uring_lock);
mutex_lock(&sqd->lock);
+ mutex_lock(&ctx->uring_lock);
tctx = sqd->thread->io_uring;
}
} else {
BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
- BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
+ BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT);