summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPavel Begunkov <asml.silence@gmail.com>2020-02-24 11:32:45 +0300
committerJens Axboe <axboe@kernel.dk>2020-02-27 14:21:01 -0700
commit52b31bc9aabca8c3ba023ff60cf701c0567b1267 (patch)
tree2e007c7ac2dab6f25cfd3c28bffa926ccaa490dc
parent403c60931e317562c422774cb9f8b5ddbc7baf08 (diff)
io_uring: add splice(2) support
Add support for splice(2). - output file is specified as sqe->fd, so it's handled by generic code - hash_reg_file handled by generic code as well - len is 32bit, but should be fine - the fd_in is registered file, when SPLICE_F_FD_IN_FIXED is set, which is a splice flag (i.e. sqe->splice_flags). Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--fs/io_uring.c109
-rw-r--r--include/uapi/linux/io_uring.h14
2 files changed, 122 insertions, 1 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1a3de7337274..1ef20a2af10b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -76,6 +76,7 @@
#include <linux/fadvise.h>
#include <linux/eventpoll.h>
#include <linux/fs_struct.h>
+#include <linux/splice.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -428,6 +429,15 @@ struct io_epoll {
struct epoll_event event;
};
+struct io_splice {
+ struct file *file_out;
+ struct file *file_in;
+ loff_t off_out;
+ loff_t off_in;
+ u64 len;
+ unsigned int flags;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
@@ -544,6 +554,7 @@ struct io_kiocb {
struct io_fadvise fadvise;
struct io_madvise madvise;
struct io_epoll epoll;
+ struct io_splice splice;
};
struct io_async_ctx *io;
@@ -744,6 +755,11 @@ static const struct io_op_def io_op_defs[] = {
.unbound_nonreg_file = 1,
.file_table = 1,
},
+ [IORING_OP_SPLICE] = {
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ }
};
static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -758,6 +774,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
static int io_grab_files(struct io_kiocb *req);
static void io_ring_file_ref_flush(struct fixed_file_data *data);
static void io_cleanup_req(struct io_kiocb *req);
+static int io_file_get(struct io_submit_state *state,
+ struct io_kiocb *req,
+ int fd, struct file **out_file,
+ bool fixed);
static struct kmem_cache *req_cachep;
@@ -2404,6 +2424,77 @@ out_free:
return ret;
}
+static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_splice* sp = &req->splice;
+ unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
+ int ret;
+
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
+
+ sp->file_in = NULL;
+ sp->off_in = READ_ONCE(sqe->splice_off_in);
+ sp->off_out = READ_ONCE(sqe->off);
+ sp->len = READ_ONCE(sqe->len);
+ sp->flags = READ_ONCE(sqe->splice_flags);
+
+ if (unlikely(sp->flags & ~valid_flags))
+ return -EINVAL;
+
+ ret = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in), &sp->file_in,
+ (sp->flags & SPLICE_F_FD_IN_FIXED));
+ if (ret)
+ return ret;
+ req->flags |= REQ_F_NEED_CLEANUP;
+
+ if (!S_ISREG(file_inode(sp->file_in)->i_mode))
+ req->work.flags |= IO_WQ_WORK_UNBOUND;
+
+ return 0;
+}
+
+static bool io_splice_punt(struct file *file)
+{
+ if (get_pipe_info(file))
+ return false;
+ if (!io_file_supports_async(file))
+ return true;
+ return !(file->f_mode & O_NONBLOCK);
+}
+
+static int io_splice(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_splice *sp = &req->splice;
+ struct file *in = sp->file_in;
+ struct file *out = sp->file_out;
+ unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ loff_t *poff_in, *poff_out;
+ long ret;
+
+ if (force_nonblock) {
+ if (io_splice_punt(in) || io_splice_punt(out))
+ return -EAGAIN;
+ flags |= SPLICE_F_NONBLOCK;
+ }
+
+ poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
+ poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
+ ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+
+ io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+
+ io_cqring_add_event(req, ret);
+ if (ret != sp->len)
+ req_set_fail_links(req);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
/*
* IORING_OP_NOP just posts a completion event, nothing else.
*/
@@ -4230,6 +4321,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
case IORING_OP_EPOLL_CTL:
ret = io_epoll_ctl_prep(req, sqe);
break;
+ case IORING_OP_SPLICE:
+ ret = io_splice_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
@@ -4292,6 +4386,10 @@ static void io_cleanup_req(struct io_kiocb *req)
case IORING_OP_STATX:
putname(req->open.filename);
break;
+ case IORING_OP_SPLICE:
+ io_put_file(req, req->splice.file_in,
+ (req->splice.flags & SPLICE_F_FD_IN_FIXED));
+ break;
}
req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -4495,6 +4593,14 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
ret = io_epoll_ctl(req, nxt, force_nonblock);
break;
+ case IORING_OP_SPLICE:
+ if (sqe) {
+ ret = io_splice_prep(req, sqe);
+ if (ret < 0)
+ break;
+ }
+ ret = io_splice(req, nxt, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
@@ -7230,6 +7336,7 @@ static int __init io_uring_init(void)
BUILD_BUG_SQE_ELEM(8, __u64, off);
BUILD_BUG_SQE_ELEM(8, __u64, addr2);
BUILD_BUG_SQE_ELEM(16, __u64, addr);
+ BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in);
BUILD_BUG_SQE_ELEM(24, __u32, len);
BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags);
BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags);
@@ -7244,9 +7351,11 @@ static int __init io_uring_init(void)
BUILD_BUG_SQE_ELEM(28, __u32, open_flags);
BUILD_BUG_SQE_ELEM(28, __u32, statx_flags);
BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice);
+ BUILD_BUG_SQE_ELEM(28, __u32, splice_flags);
BUILD_BUG_SQE_ELEM(32, __u64, user_data);
BUILD_BUG_SQE_ELEM(40, __u16, buf_index);
BUILD_BUG_SQE_ELEM(42, __u16, personality);
+ BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in);
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 3f7961c1c243..08891cc1c1e7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -23,7 +23,10 @@ struct io_uring_sqe {
__u64 off; /* offset into file */
__u64 addr2;
};
- __u64 addr; /* pointer to buffer or iovecs */
+ union {
+ __u64 addr; /* pointer to buffer or iovecs */
+ __u64 splice_off_in;
+ };
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
@@ -37,6 +40,7 @@ struct io_uring_sqe {
__u32 open_flags;
__u32 statx_flags;
__u32 fadvise_advice;
+ __u32 splice_flags;
};
__u64 user_data; /* data to be passed back at completion time */
union {
@@ -45,6 +49,7 @@ struct io_uring_sqe {
__u16 buf_index;
/* personality to use, if used */
__u16 personality;
+ __s32 splice_fd_in;
};
__u64 __pad2[3];
};
@@ -113,6 +118,7 @@ enum {
IORING_OP_RECV,
IORING_OP_OPENAT2,
IORING_OP_EPOLL_CTL,
+ IORING_OP_SPLICE,
/* this goes last, obviously */
IORING_OP_LAST,
@@ -129,6 +135,12 @@ enum {
#define IORING_TIMEOUT_ABS (1U << 0)
/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */
+
+/*
* IO completion data structure (Completion Queue Entry)
*/
struct io_uring_cqe {