@@ -235,9 +235,15 @@ enum io_uring_op {
* sqe->uring_cmd_flags
* IORING_URING_CMD_FIXED use registered buffer; pass this flag
* along with setting sqe->buf_index.
+ *
+ * IORING_URING_CMD_FUSED_SPLIT_SQE fused command only, secondary sqe is
+ * provided from another new sqe; without
+ * setting the flag, secondary sqe is from
+ * 2nd 64byte of this sqe, so SQE128 has
+ * to be enabled
*/
#define IORING_URING_CMD_FIXED (1U << 0)
-
+#define IORING_URING_CMD_FUSED_SPLIT_SQE (1U << 1)
/*
* sqe->fsync_flags
@@ -43,18 +43,34 @@ static inline void io_fused_cmd_update_link_flags(struct io_kiocb *req,
req->flags |= REQ_F_LINK;
}
+static const struct io_uring_sqe *fused_cmd_get_secondary_sqe(
+ struct io_ring_ctx *ctx, const struct io_uring_sqe *primary,
+ bool split_sqe)
+{
+ if (unlikely(!(ctx->flags & IORING_SETUP_SQE128) && !split_sqe))
+ return NULL;
+
+ if (split_sqe) {
+ const struct io_uring_sqe *sqe;
+
+ if (unlikely(!io_get_secondary_sqe(ctx, &sqe)))
+ return NULL;
+ return sqe;
+ }
+
+ return primary + 1;
+}
+
int io_fused_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
__must_hold(&req->ctx->uring_lock)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
- const struct io_uring_sqe *secondary_sqe = sqe + 1;
+ const struct io_uring_sqe *secondary_sqe;
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *secondary;
u8 secondary_op;
int ret;
-
- if (unlikely(!(ctx->flags & IORING_SETUP_SQE128)))
- return -EINVAL;
+ bool split_sqe;
if (unlikely(sqe->__pad1))
return -EINVAL;
@@ -67,7 +83,12 @@ int io_fused_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return -EINVAL;
ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags);
- if (unlikely(ioucmd->flags))
+ if (unlikely(ioucmd->flags & ~IORING_URING_CMD_FUSED_SPLIT_SQE))
+ return -EINVAL;
+
+ split_sqe = ioucmd->flags & IORING_URING_CMD_FUSED_SPLIT_SQE;
+ secondary_sqe = fused_cmd_get_secondary_sqe(ctx, sqe, split_sqe);
+ if (unlikely(!secondary_sqe))
return -EINVAL;
secondary_op = READ_ONCE(secondary_sqe->opcode);
@@ -78,8 +99,12 @@ int io_fused_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
req->fused_cmd_kbuf = NULL;
- /* take one extra reference for the secondary request */
- io_get_task_refs(1);
+ /*
+ * Take one extra reference for the secondary request built from
+ * builtin SQE since io_uring core code doesn't grab it for us
+ */
+ if (!split_sqe)
+ io_get_task_refs(1);
ret = -ENOMEM;
if (unlikely(!io_alloc_req(ctx, &secondary)))
@@ -103,7 +128,8 @@ int io_fused_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
fail_free_req:
io_free_req(secondary);
fail:
- current->io_uring->cached_refs += 1;
+ if (!split_sqe)
+ current->io_uring->cached_refs += 1;
return ret;
}
@@ -2414,7 +2414,8 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
* used, it's important that those reads are done through READ_ONCE() to
* prevent a re-load down the line.
*/
-static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
+static inline bool io_get_sqe(struct io_ring_ctx *ctx,
+ const struct io_uring_sqe **sqe)
{
unsigned head, mask = ctx->sq_entries - 1;
unsigned sq_idx = ctx->cached_sq_head++ & mask;
@@ -2443,19 +2444,26 @@ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
return false;
}
+bool io_get_secondary_sqe(struct io_ring_ctx *ctx,
+ const struct io_uring_sqe **sqe)
+{
+ return io_get_sqe(ctx, sqe);
+}
+
int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
__must_hold(&ctx->uring_lock)
{
unsigned int entries = io_sqring_entries(ctx);
- unsigned int left;
+ unsigned old_head = ctx->cached_sq_head;
+ unsigned int left = 0;
int ret;
if (unlikely(!entries))
return 0;
/* make sure SQ entry isn't read before tail */
- ret = left = min3(nr, ctx->sq_entries, entries);
- io_get_task_refs(left);
- io_submit_state_start(&ctx->submit_state, left);
+ ret = min3(nr, ctx->sq_entries, entries);
+ io_get_task_refs(ret);
+ io_submit_state_start(&ctx->submit_state, ret);
do {
const struct io_uring_sqe *sqe;
@@ -2474,11 +2482,12 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
*/
if (unlikely(io_submit_sqe(ctx, req, sqe)) &&
!(ctx->flags & IORING_SETUP_SUBMIT_ALL)) {
- left--;
+ left = 1;
break;
}
- } while (--left);
+ } while ((ctx->cached_sq_head - old_head) < ret);
+ left = ret - (ctx->cached_sq_head - old_head) - left;
if (unlikely(left)) {
ret -= left;
/* try again if it submitted nothing and can't allocate a req */
@@ -78,6 +78,8 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
+bool io_get_secondary_sqe(struct io_ring_ctx *ctx,
+ const struct io_uring_sqe **sqe);
int io_init_secondary_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe);
So far, the secondary sqe is saved in the 2nd 64 byte of primary sqe, which requires that SQE128 has to be enabled. Relax this limit by allowing to fetch secondary SQE from SQ directly. IORING_URING_CMD_FUSED_SPLIT_SQE has to be set for this usage, and userspace has to put secondary SQE following the primary sqe. Signed-off-by: Ming Lei <ming.lei@redhat.com> --- include/uapi/linux/io_uring.h | 8 ++++++- io_uring/fused_cmd.c | 42 ++++++++++++++++++++++++++++------- io_uring/io_uring.c | 23 +++++++++++++------ io_uring/io_uring.h | 2 ++ 4 files changed, 59 insertions(+), 16 deletions(-)