| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230324135808.855245-4-ming.lei@redhat.com>
Date: Fri, 24 Mar 2023 21:57:54 +0800
From: Ming Lei <ming.lei@...hat.com>
To: Jens Axboe <axboe@...nel.dk>, io-uring@...r.kernel.org,
linux-block@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, Miklos Szeredi <mszeredi@...hat.com>,
ZiyangZhang <ZiyangZhang@...ux.alibaba.com>,
Xiaoguang Wang <xiaoguang.wang@...ux.alibaba.com>,
Bernd Schubert <bschubert@....com>,
Pavel Begunkov <asml.silence@...il.com>,
Stefan Hajnoczi <stefanha@...hat.com>,
Ming Lei <ming.lei@...hat.com>
Subject: [PATCH V4 03/17] io_uring: support normal SQE for fused command
So far, the slave sqe is saved in the 2nd 64 byte of master sqe, which
requires that SQE128 has to be enabled. Relax this limit by allowing to
fetch slave SQE from SQ directly.
IORING_URING_CMD_FUSED_SPLIT_SQE has to be set for this usage, and
userspace has to put slave SQE following the master sqe.
However, not sure if this way is useful, given fused command needs at least
two SQEs for running io in fast path, and SQE128 matches this usecase
perfectly.
Signed-off-by: Ming Lei <ming.lei@...hat.com>
---
include/uapi/linux/io_uring.h | 8 ++++++-
io_uring/fused_cmd.c | 42 ++++++++++++++++++++++++++++-------
io_uring/io_uring.c | 22 ++++++++++++------
io_uring/io_uring.h | 1 +
4 files changed, 57 insertions(+), 16 deletions(-)
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 9762a2989747..6f25ca85639f 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -233,9 +233,15 @@ 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, slave sqe is
+ * provided from another new sqe; without
+ * setting the flag, slave 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
diff --git a/io_uring/fused_cmd.c b/io_uring/fused_cmd.c
index ff3921f6a5df..4cfe02e316f9 100644
--- a/io_uring/fused_cmd.c
+++ b/io_uring/fused_cmd.c
@@ -43,24 +43,45 @@ 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_slave_sqe(
+ struct io_ring_ctx *ctx, const struct io_uring_sqe *master,
+ 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_slave_sqe(ctx, &sqe)))
+ return NULL;
+ return sqe;
+ }
+
+ return master + 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 *slave_sqe = sqe + 1;
+ const struct io_uring_sqe *slave_sqe;
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *slave;
u8 slave_op;
int ret;
-
- if (unlikely(!(ctx->flags & IORING_SETUP_SQE128)))
- return -EINVAL;
+ bool split_sqe;
if (unlikely(sqe->__pad1))
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;
+ slave_sqe = fused_cmd_get_slave_sqe(ctx, sqe, split_sqe);
+ if (unlikely(!slave_sqe))
return -EINVAL;
slave_op = READ_ONCE(slave_sqe->opcode);
@@ -71,8 +92,12 @@ 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 slave request */
- io_get_task_refs(1);
+ /*
+ * Take one extra reference for the slave 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, &slave)))
@@ -96,7 +121,8 @@ int io_fused_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
fail_free_req:
io_free_req(slave);
fail:
- current->io_uring->cached_refs += 1;
+ if (!split_sqe)
+ current->io_uring->cached_refs += 1;
return ret;
}
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index e5e43637d313..b0008d380686 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -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 +2444,25 @@ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
return false;
}
+bool io_get_slave_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 +2481,12 @@ 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 */
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 637e12e4fb9f..ee22e65c4aef 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -78,6 +78,7 @@ 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_slave_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe);
int io_init_slave_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe);
--
2.39.2
Powered by blists - more mailing lists