@@ -471,6 +471,7 @@ enum {
REQ_F_BL_NO_RECYCLE_BIT,
REQ_F_BUFFERS_COMMIT_BIT,
REQ_F_SQE_GROUP_LEADER_BIT,
+ REQ_F_SQE_GROUP_DEP_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -555,6 +556,8 @@ enum {
REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
/* sqe group lead */
REQ_F_SQE_GROUP_LEADER = IO_REQ_FLAG(REQ_F_SQE_GROUP_LEADER_BIT),
+ /* sqe group with members depending on leader */
+ REQ_F_SQE_GROUP_DEP = IO_REQ_FLAG(REQ_F_SQE_GROUP_DEP_BIT),
};
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -882,7 +882,13 @@ static __always_inline void io_req_commit_cqe(struct io_ring_ctx *ctx,
static inline bool need_queue_group_members(io_req_flags_t flags)
{
- return flags & REQ_F_SQE_GROUP_LEADER;
+ if (likely(!(flags & REQ_F_SQE_GROUP)))
+ return false;
+
+ if (!(flags & REQ_F_SQE_GROUP_LEADER) ||
+ (flags & REQ_F_SQE_GROUP_DEP))
+ return false;
+ return true;
}
/* Can only be called after this request is issued */
@@ -930,6 +936,9 @@ void io_queue_group_members(struct io_kiocb *req, bool async)
if (unlikely(member->flags & REQ_F_FAIL)) {
io_req_task_queue_fail(member, member->cqe.res);
+ } else if (unlikely((req->flags & REQ_F_FAIL) &&
+ (req->flags & REQ_F_SQE_GROUP_DEP))) {
+ io_req_task_queue_fail(member, -ECANCELED);
} else if (member->flags & REQ_F_FORCE_ASYNC) {
io_req_task_queue(member);
} else {
@@ -1012,6 +1021,10 @@ static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
return;
}
+ /* queue members which may depend on leader */
+ if (req_is_group_leader(req) && (req->flags & REQ_F_SQE_GROUP_DEP))
+ io_queue_group_members(req, true);
+
io_cq_lock(ctx);
if (!(req->flags & REQ_F_CQE_SKIP) && !req_is_group_leader(req)) {
if (!io_fill_cqe_req(ctx, req))
@@ -365,7 +365,10 @@ static inline void io_req_complete_defer(struct io_kiocb *req)
wq_list_add_tail(&req->comp_list, &state->compl_reqs);
- /* members may not be issued when leader is completed */
+ /*
+ * Members may not be issued when leader is completed, or members
+ * depend on leader in case of REQ_F_SQE_GROUP_DEP
+ */
if (unlikely(req_is_group_leader(req) && req->grp_link))
io_queue_group_members(req, false);
}
Generic sqe group provides flexible way for supporting N:M dependency between groups. However, some resource can't cross OPs, such as kernel buffer, otherwise the buffer may be leaked easily in case that any OP failure or application panic. Add flag REQ_F_SQE_GROUP_DEP for allowing members to depend on group leader, so that group members won't be queued until the leader request is completed, and we still commit leader's CQE after all members CQE are posted. With this way, the kernel resource lifetime can be aligned with group leader or group, one typical use case is to support zero copy for device internal buffer. This use case may not be generic enough, so set it only for specific OP which can serve as group leader, meantime we have run out of sqe flags. Signed-off-by: Ming Lei <ming.lei@redhat.com> --- include/linux/io_uring_types.h | 3 +++ io_uring/io_uring.c | 15 ++++++++++++++- io_uring/io_uring.h | 5 ++++- 3 files changed, 21 insertions(+), 2 deletions(-)