From: Jens Axboe <axboe@xxxxxxxxx>
file_operations->uring_cmd is a file private handler, similar to ioctls
but hopefully a lot more sane and useful.
IORING_OP_URING_CMD is a file private kind of request. io_uring doesn't
know what is in this command type, it's for the provider of ->uring_cmd()
to deal with. This operation can be issued only on the ring that is
setup with both IORING_SETUP_SQE128 and IORING_SETUP_CQE32 flags.
Co-developed-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 81 ++++++++++++++++++++++++++++++++---
include/linux/fs.h | 2 +
include/linux/io_uring.h | 29 +++++++++++++
include/uapi/linux/io_uring.h | 8 +++-
4 files changed, 112 insertions(+), 8 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c7e3f7e74d92..b774e6eac538 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -202,13 +202,6 @@ 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;
@@ -969,6 +962,7 @@ struct io_kiocb {
struct io_xattr xattr;
struct io_socket sock;
struct io_nop nop;
+ struct io_uring_cmd uring_cmd;
};
u8 opcode;
@@ -1254,6 +1248,10 @@ static const struct io_op_def io_op_defs[] = {
[IORING_OP_SOCKET] = {
.audit_skip = 1,
},
+ [IORING_OP_URING_CMD] = {
+ .needs_file = 1,
+ .plug = 1,
+ },
};
/* requests with any of those set should undergo io_disarm_next() */
@@ -1393,6 +1391,8 @@ const char *io_uring_get_opcode(u8 opcode)
return "GETXATTR";
case IORING_OP_SOCKET:
return "SOCKET";
+ case IORING_OP_URING_CMD:
+ return "URING_CMD";
case IORING_OP_LAST:
return "INVALID";
}
@@ -4907,6 +4907,66 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
return 0;
}
+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);
+
+/*
+ * 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, ssize_t res2)
+{
+ struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+ if (ret < 0)
+ req_set_fail(req);
+ __io_req_complete32(req, 0, ret, 0, res2, 0);
+}
+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->ctx->flags & IORING_SETUP_IOPOLL)
+ return -EOPNOTSUPP;
+ /* do not support uring-cmd without big SQE/CQE */
+ if (!(req->ctx->flags & IORING_SETUP_SQE128))
+ return -EOPNOTSUPP;
+ if (!(req->ctx->flags & IORING_SETUP_CQE32))
+ return -EOPNOTSUPP;
+ ioucmd->cmd = (void *) &sqe->cmd;
+ ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
+ ioucmd->flags = 0;
+ return 0;
+}
+
+static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct file *file = req->file;
+ struct io_uring_cmd *ioucmd = &req->uring_cmd;
+
+ if (!req->file->f_op->uring_cmd)
+ return -EOPNOTSUPP;
+ ioucmd->flags |= issue_flags;
+ file->f_op->uring_cmd(ioucmd);
+ return 0;
+}
+
static int io_shutdown_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
@@ -7764,6 +7824,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return io_getxattr_prep(req, sqe);
case IORING_OP_SOCKET:
return io_socket_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",
@@ -8085,6 +8147,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
case IORING_OP_SOCKET:
ret = io_socket(req, issue_flags);
break;
+ case IORING_OP_URING_CMD:
+ ret = io_uring_cmd(req, issue_flags);
+ break;
default:
ret = -EINVAL;
break;
@@ -12688,6 +12753,8 @@ 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/fs.h b/include/linux/fs.h
index bbde95387a23..6b64c07efcf4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1953,6 +1953,7 @@ struct dir_context {
#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN)
struct iov_iter;
+struct io_uring_cmd;
struct file_operations {
struct module *owner;
@@ -1995,6 +1996,7 @@ struct file_operations {
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
int (*fadvise)(struct file *, loff_t, loff_t, int);
+ void (*uring_cmd)(struct io_uring_cmd *ioucmd);
} __randomize_layout;
struct inode_operations {
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 24651c229ed2..a4ff4696cbea 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,7 +5,28 @@
#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;
+ u32 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, ssize_t res2);
+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);
@@ -30,6 +51,14 @@ 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,
+ ssize_t ret2)
+{
+}
+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 881e508767f8..c081511119bf 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 {
@@ -61,7 +63,10 @@ struct io_uring_sqe {
__s32 splice_fd_in;
__u32 file_index;
};
- __u64 addr3;
+ union {
+ __u64 addr3;
+ __u64 cmd;
+ };
__u64 __pad2[1];
/*
@@ -160,6 +165,7 @@ enum io_uring_op {
IORING_OP_FGETXATTR,
IORING_OP_GETXATTR,
IORING_OP_SOCKET,
+ IORING_OP_URING_CMD,
/* this goes last, obviously */
IORING_OP_LAST,
--
2.25.1
