[PATCH 03/17] io_uring: add infra and support for IORING_OP_URING_CMD
Kanchan Joshi
joshi.k at samsung.com
Tue Mar 8 07:20:51 PST 2022
From: Jens Axboe <axboe at kernel.dk>
This is a file private kind of request. io_uring doesn't know what's
in this command type, it's for the file_operations->async_cmd()
handler to deal with.
Signed-off-by: Jens Axboe <axboe at kernel.dk>
Signed-off-by: Kanchan Joshi <joshi.k at samsung.com>
---
fs/io_uring.c | 79 +++++++++++++++++++++++++++++++----
include/linux/io_uring.h | 29 +++++++++++++
include/uapi/linux/io_uring.h | 9 +++-
3 files changed, 108 insertions(+), 9 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 241ba1cd6dcf..1f228a79e68f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -200,13 +200,6 @@ struct io_rings {
struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp;
};
-enum io_uring_cmd_flags {
- IO_URING_F_COMPLETE_DEFER = 1,
- IO_URING_F_UNLOCKED = 2,
- /* int's last bit, sign checks are usually faster than a bit test */
- IO_URING_F_NONBLOCK = INT_MIN,
-};
-
struct io_mapped_ubuf {
u64 ubuf;
u64 ubuf_end;
@@ -860,6 +853,7 @@ struct io_kiocb {
struct io_mkdir mkdir;
struct io_symlink symlink;
struct io_hardlink hardlink;
+ struct io_uring_cmd uring_cmd;
};
u8 opcode;
@@ -1110,6 +1104,9 @@ static const struct io_op_def io_op_defs[] = {
[IORING_OP_MKDIRAT] = {},
[IORING_OP_SYMLINKAT] = {},
[IORING_OP_LINKAT] = {},
+ [IORING_OP_URING_CMD] = {
+ .needs_file = 1,
+ },
};
/* requests with any of those set should undergo io_disarm_next() */
@@ -2464,6 +2461,22 @@ static void io_req_task_submit(struct io_kiocb *req, bool *locked)
io_req_complete_failed(req, -EFAULT);
}
+static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
+{
+ req->uring_cmd.driver_cb(&req->uring_cmd);
+}
+
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+ void (*driver_cb)(struct io_uring_cmd *))
+{
+ struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+ req->uring_cmd.driver_cb = driver_cb;
+ req->io_task_work.func = io_uring_cmd_work;
+ io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL));
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);
+
static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
req->result = ret;
@@ -4109,6 +4122,51 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
return 0;
}
+/*
+ * Called by consumers of io_uring_cmd, if they originally returned
+ * -EIOCBQUEUED upon receiving the command.
+ */
+void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret)
+{
+ struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+ if (ret < 0)
+ req_set_fail(req);
+ io_req_complete(req, ret);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_done);
+
+static int io_uring_cmd_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_uring_cmd *ioucmd = &req->uring_cmd;
+
+ if (!req->file->f_op->async_cmd || !(req->ctx->flags & IORING_SETUP_SQE128))
+ return -EOPNOTSUPP;
+ if (req->ctx->flags & IORING_SETUP_IOPOLL)
+ return -EOPNOTSUPP;
+ ioucmd->cmd = (void *) &sqe->cmd;
+ ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
+ ioucmd->cmd_len = READ_ONCE(sqe->cmd_len);
+ ioucmd->flags = 0;
+ return 0;
+}
+
+static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct file *file = req->file;
+ int ret;
+ struct io_uring_cmd *ioucmd = &req->uring_cmd;
+
+ ioucmd->flags |= issue_flags;
+ ret = file->f_op->async_cmd(ioucmd);
+ /* queued async, consumer will call io_uring_cmd_done() when complete */
+ if (ret == -EIOCBQUEUED)
+ return 0;
+ io_uring_cmd_done(ioucmd, ret);
+ return 0;
+}
+
static int io_shutdown_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
@@ -6588,6 +6646,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return io_symlinkat_prep(req, sqe);
case IORING_OP_LINKAT:
return io_linkat_prep(req, sqe);
+ case IORING_OP_URING_CMD:
+ return io_uring_cmd_prep(req, sqe);
}
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -6871,6 +6931,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
case IORING_OP_LINKAT:
ret = io_linkat(req, issue_flags);
break;
+ case IORING_OP_URING_CMD:
+ ret = io_uring_cmd(req, issue_flags);
+ break;
default:
ret = -EINVAL;
break;
@@ -11215,6 +11278,8 @@ static int __init io_uring_init(void)
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
+ BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64);
+
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT);
return 0;
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 649a4d7c241b..cedc68201469 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,7 +5,29 @@
#include <linux/sched.h>
#include <linux/xarray.h>
+enum io_uring_cmd_flags {
+ IO_URING_F_COMPLETE_DEFER = 1,
+ IO_URING_F_UNLOCKED = 2,
+ /* int's last bit, sign checks are usually faster than a bit test */
+ IO_URING_F_NONBLOCK = INT_MIN,
+};
+
+struct io_uring_cmd {
+ struct file *file;
+ void *cmd;
+ /* for irq-completion - if driver requires doing stuff in task-context*/
+ void (*driver_cb)(struct io_uring_cmd *cmd);
+ u32 flags;
+ u32 cmd_op;
+ u16 cmd_len;
+ u16 unused;
+ u8 pdu[28]; /* available inline for free use */
+};
+
#if defined(CONFIG_IO_URING)
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret);
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+ void (*driver_cb)(struct io_uring_cmd *));
struct sock *io_uring_get_socket(struct file *file);
void __io_uring_cancel(bool cancel_all);
void __io_uring_free(struct task_struct *tsk);
@@ -26,6 +48,13 @@ static inline void io_uring_free(struct task_struct *tsk)
__io_uring_free(tsk);
}
#else
+static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret)
+{
+}
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+ void (*driver_cb)(struct io_uring_cmd *))
+{
+}
static inline struct sock *io_uring_get_socket(struct file *file)
{
return NULL;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index c5db68433ca5..9bf1d6c0ed7f 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -22,10 +22,12 @@ struct io_uring_sqe {
union {
__u64 off; /* offset into file */
__u64 addr2;
+ __u32 cmd_op;
};
union {
__u64 addr; /* pointer to buffer or iovecs */
__u64 splice_off_in;
+ __u16 cmd_len;
};
__u32 len; /* buffer size or number of iovecs */
union {
@@ -60,8 +62,10 @@ struct io_uring_sqe {
__s32 splice_fd_in;
__u32 file_index;
};
- __u64 __pad2[2];
-
+ union {
+ __u64 __pad2[2];
+ __u64 cmd;
+ };
/*
* If the ring is initializefd with IORING_SETUP_SQE128, then this field
* contains 64-bytes of padding, doubling the size of the SQE.
@@ -150,6 +154,7 @@ enum {
IORING_OP_MKDIRAT,
IORING_OP_SYMLINKAT,
IORING_OP_LINKAT,
+ IORING_OP_URING_CMD,
/* this goes last, obviously */
IORING_OP_LAST,
--
2.25.1
More information about the Linux-nvme
mailing list