@@ -6,6 +6,7 @@
#include <linux/task_work.h>
#include <linux/bitmap.h>
#include <linux/llist.h>
+#include <linux/bvec.h>
#include <uapi/linux/io_uring.h>
enum {
@@ -39,6 +40,26 @@ enum io_uring_cmd_flags {
IO_URING_F_COMPAT = (1 << 12),
};
+struct io_uring_kernel_buf;
+typedef void (io_uring_buf_giveback_t) (const struct io_uring_kernel_buf *);
+
+/* buffer provided from kernel */
+struct io_uring_kernel_buf {
+ unsigned long len;
+ unsigned short nr_bvecs;
+ unsigned char dir; /* ITER_SOURCE or ITER_DEST */
+
+ /* offset in the 1st bvec */
+ unsigned int offset;
+ const struct bio_vec *bvec;
+
+ /* called when we are done with this buffer */
+ io_uring_buf_giveback_t *grp_kbuf_ack;
+
+ /* private field, user don't touch it */
+ struct bio_vec __bvec[];
+};
+
struct io_wq_work_node {
struct io_wq_work_node *next;
};
@@ -478,6 +499,7 @@ enum {
REQ_F_BUFFERS_COMMIT_BIT,
REQ_F_SQE_GROUP_LEADER_BIT,
REQ_F_SQE_GROUP_DEP_BIT,
+ REQ_F_GROUP_KBUF_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -564,6 +586,8 @@ enum {
REQ_F_SQE_GROUP_LEADER = IO_REQ_FLAG(REQ_F_SQE_GROUP_LEADER_BIT),
/* sqe group with members depending on leader */
REQ_F_SQE_GROUP_DEP = IO_REQ_FLAG(REQ_F_SQE_GROUP_DEP_BIT),
+ /* group lead provides kbuf for members, set for both lead and member */
+ REQ_F_GROUP_KBUF = IO_REQ_FLAG(REQ_F_GROUP_KBUF_BIT),
};
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -647,6 +671,15 @@ struct io_kiocb {
* REQ_F_BUFFER_RING is set.
*/
struct io_buffer_list *buf_list;
+
+ /*
+ * store kernel buffer provided by sqe group lead, valid
+ * IFF REQ_F_GROUP_KBUF
+ *
+ * The buffer meta is immutable since it is shared by
+ * all member requests
+ */
+ const struct io_uring_kernel_buf *grp_kbuf;
};
union {
@@ -114,7 +114,7 @@
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
- REQ_F_ASYNC_DATA)
+ REQ_F_ASYNC_DATA | REQ_F_GROUP_KBUF)
#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
IO_REQ_CLEAN_FLAGS)
@@ -380,6 +380,11 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
static void io_clean_op(struct io_kiocb *req)
{
+ /* GROUP_KBUF is only available for REQ_F_SQE_GROUP_DEP */
+ if ((req->flags & (REQ_F_GROUP_KBUF | REQ_F_SQE_GROUP_DEP)) ==
+ (REQ_F_GROUP_KBUF | REQ_F_SQE_GROUP_DEP))
+ io_group_kbuf_drop(req);
+
if (req->flags & REQ_F_BUFFER_SELECTED) {
spin_lock(&req->ctx->completion_lock);
io_kbuf_drop(req);
@@ -984,9 +989,12 @@ void io_queue_group_members(struct io_kiocb *req, bool async)
return;
while (member) {
+ const struct io_issue_def *def = &io_issue_defs[member->opcode];
struct io_kiocb *next = member->grp_link;
member->grp_link = req;
+ if ((req->flags & REQ_F_GROUP_KBUF) && def->accept_group_kbuf)
+ member->flags |= REQ_F_GROUP_KBUF;
/* members have to be failed if they depends on leader */
if (unlikely((req->flags & REQ_F_FAIL) &&
@@ -355,6 +355,11 @@ static inline bool req_is_group_member(struct io_kiocb *req)
return !req_is_group_leader(req) && (req->flags & REQ_F_SQE_GROUP);
}
+static inline bool req_support_group_dep(struct io_kiocb *req)
+{
+ return req_is_group_leader(req) && (req->flags & REQ_F_SQE_GROUP_DEP);
+}
+
/*
* Don't complete immediately but use deferred completion infrastructure.
* Protected by ->uring_lock and can only be used either with
@@ -823,3 +823,63 @@ int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma)
io_put_bl(ctx, bl);
return ret;
}
+
+int io_provide_group_kbuf(struct io_kiocb *req,
+ const struct io_uring_kernel_buf *grp_kbuf)
+{
+ if (unlikely(!req_support_group_dep(req)))
+ return -EINVAL;
+
+ /*
+ * Borrow this buffer from one kernel subsystem, and return them
+ * by calling `grp_kbuf_ack` when the group lead is freed.
+ *
+ * Not like pipe/splice, this kernel buffer is always owned by the
+ * provider, and has to be returned back.
+ */
+ req->grp_kbuf = grp_kbuf;
+ req->flags |= REQ_F_GROUP_KBUF;
+
+ return 0;
+}
+
+int io_import_group_kbuf(struct io_kiocb *req, unsigned long buf_off,
+ unsigned int len, int dir, struct iov_iter *iter)
+{
+ struct io_kiocb *lead = req->grp_link;
+ const struct io_uring_kernel_buf *kbuf;
+ unsigned long offset;
+
+ WARN_ON_ONCE(!(req->flags & REQ_F_GROUP_KBUF));
+
+ if (!req_is_group_member(req))
+ return -EINVAL;
+
+ if (!lead || !req_support_group_dep(lead) || !lead->grp_kbuf)
+ return -EINVAL;
+
+ /* req->fused_cmd_kbuf is immutable */
+ kbuf = lead->grp_kbuf;
+ offset = kbuf->offset;
+
+ if (!kbuf->bvec)
+ return -EINVAL;
+
+ if (dir != kbuf->dir)
+ return -EINVAL;
+
+ if (unlikely(buf_off > kbuf->len))
+ return -EFAULT;
+
+ if (unlikely(len > kbuf->len - buf_off))
+ return -EFAULT;
+
+ /* don't use io_import_fixed which doesn't support multipage bvec */
+ offset += buf_off;
+ iov_iter_bvec(iter, dir, kbuf->bvec, kbuf->nr_bvecs, offset + len);
+
+ if (offset)
+ iov_iter_advance(iter, offset);
+
+ return 0;
+}
@@ -82,6 +82,11 @@ struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
unsigned long bgid);
int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma);
+int io_provide_group_kbuf(struct io_kiocb *req,
+ const struct io_uring_kernel_buf *grp_kbuf);
+int io_import_group_kbuf(struct io_kiocb *req, unsigned long buf_off,
+ unsigned int len, int dir, struct iov_iter *iter);
+
static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
{
/*
@@ -180,4 +185,12 @@ static inline unsigned int io_put_kbufs(struct io_kiocb *req, int nbufs,
{
return __io_put_kbufs(req, nbufs, issue_flags);
}
+
+static inline void io_group_kbuf_drop(struct io_kiocb *req)
+{
+ const struct io_uring_kernel_buf *gbuf = req->grp_kbuf;
+
+ if (gbuf && gbuf->grp_kbuf_ack)
+ gbuf->grp_kbuf_ack(gbuf);
+}
#endif
@@ -78,6 +78,13 @@ struct io_sr_msg {
*/
#define MULTISHOT_MAX_RETRY 32
+#define user_ptr_to_u64(x) ( \
+{ \
+ typecheck(void __user *, (x)); \
+ (u64)(unsigned long)(x); \
+} \
+)
+
int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -364,7 +371,7 @@ static int io_send_setup(struct io_kiocb *req)
kmsg->msg.msg_name = &kmsg->addr;
kmsg->msg.msg_namelen = sr->addr_len;
}
- if (!io_do_buffer_select(req)) {
+ if (!io_do_buffer_select(req) && !(req->flags & REQ_F_GROUP_KBUF)) {
ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len,
&kmsg->msg.msg_iter);
if (unlikely(ret < 0))
@@ -584,6 +591,15 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
+ if (req->flags & REQ_F_GROUP_KBUF) {
+ ret = io_import_group_kbuf(req,
+ user_ptr_to_u64(sr->buf),
+ sr->len, ITER_SOURCE,
+ &kmsg->msg.msg_iter);
+ if (unlikely(ret))
+ return ret;
+ }
+
retry_bundle:
if (io_do_buffer_select(req)) {
struct buf_sel_arg arg = {
@@ -1131,6 +1147,11 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(ret))
goto out_free;
sr->buf = NULL;
+ } else if (req->flags & REQ_F_GROUP_KBUF) {
+ ret = io_import_group_kbuf(req, user_ptr_to_u64(sr->buf),
+ sr->len, ITER_DEST, &kmsg->msg.msg_iter);
+ if (unlikely(ret))
+ goto out_free;
}
kmsg->msg.msg_inq = -1;
@@ -1333,6 +1354,14 @@ static int io_send_zc_import(struct io_kiocb *req, struct io_async_msghdr *kmsg)
if (unlikely(ret))
return ret;
kmsg->msg.sg_from_iter = io_sg_from_iter;
+ } else if (req->flags & REQ_F_GROUP_KBUF) {
+ struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+
+ ret = io_import_group_kbuf(req, user_ptr_to_u64(sr->buf),
+ sr->len, ITER_SOURCE, &kmsg->msg.msg_iter);
+ if (unlikely(ret))
+ return ret;
+ kmsg->msg.sg_from_iter = io_sg_from_iter;
} else {
ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
if (unlikely(ret))
@@ -246,6 +246,7 @@ const struct io_issue_def io_issue_defs[] = {
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
+ .accept_group_kbuf = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_read,
.issue = io_read,
@@ -260,6 +261,7 @@ const struct io_issue_def io_issue_defs[] = {
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
+ .accept_group_kbuf = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_write,
.issue = io_write,
@@ -282,6 +284,7 @@ const struct io_issue_def io_issue_defs[] = {
.audit_skip = 1,
.ioprio = 1,
.buffer_select = 1,
+ .accept_group_kbuf = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_sendmsg_prep,
@@ -297,6 +300,7 @@ const struct io_issue_def io_issue_defs[] = {
.buffer_select = 1,
.audit_skip = 1,
.ioprio = 1,
+ .accept_group_kbuf = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_recvmsg_prep,
@@ -424,6 +428,7 @@ const struct io_issue_def io_issue_defs[] = {
.pollout = 1,
.audit_skip = 1,
.ioprio = 1,
+ .accept_group_kbuf = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_send_zc_prep,
@@ -29,6 +29,8 @@ struct io_issue_def {
unsigned iopoll_queue : 1;
/* vectored opcode, set if 1) vectored, and 2) handler needs to know */
unsigned vectored : 1;
+ /* opcodes which accept provided group kbuf */
+ unsigned accept_group_kbuf : 1;
/* size of async data needed, if any */
unsigned short async_size;
@@ -235,7 +235,8 @@ static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import)
if (io_rw_alloc_async(req))
return -ENOMEM;
- if (!do_import || io_do_buffer_select(req))
+ if (!do_import || io_do_buffer_select(req) ||
+ (req->flags & REQ_F_GROUP_KBUF))
return 0;
rw = req->async_data;
@@ -620,11 +621,16 @@ static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
*/
static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
{
+ struct io_kiocb *req = cmd_to_io_kiocb(rw);
struct kiocb *kiocb = &rw->kiocb;
struct file *file = kiocb->ki_filp;
ssize_t ret = 0;
loff_t *ppos;
+ /* group buffer is kernel buffer and doesn't have userspace addr */
+ if (req->flags & REQ_F_GROUP_KBUF)
+ return -EOPNOTSUPP;
+
/*
* Don't support polled IO through this interface, and we can't
* support non-blocking either. For the latter, this just causes
@@ -830,6 +836,11 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
ret = io_import_iovec(ITER_DEST, req, io, issue_flags);
if (unlikely(ret < 0))
return ret;
+ } else if (req->flags & REQ_F_GROUP_KBUF) {
+ ret = io_import_group_kbuf(req, rw->addr, rw->len, ITER_DEST,
+ &io->iter);
+ if (unlikely(ret))
+ return ret;
}
ret = io_rw_init_file(req, FMODE_READ);
@@ -1012,6 +1023,13 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
ssize_t ret, ret2;
loff_t *ppos;
+ if (req->flags & REQ_F_GROUP_KBUF) {
+ ret = io_import_group_kbuf(req, rw->addr, rw->len, ITER_SOURCE,
+ &io->iter);
+ if (unlikely(ret))
+ return ret;
+ }
+
ret = io_rw_init_file(req, FMODE_WRITE);
if (unlikely(ret))
return ret;
SQE group with REQ_F_SQE_GROUP_DEP introduces one new mechanism to share resource among one group of requests, and all member requests can consume the resource provided by group lead efficiently in parallel. This patch uses the added sqe group feature REQ_F_SQE_GROUP_DEP to share kernel buffer in sqe group: - the group lead provides kernel buffer to member requests - member requests use the provided buffer to do FS or network IO, or more operations in future - this kernel buffer is returned back after member requests use it up This way looks a bit similar with kernel's pipe/splice, but there are some important differences: - splice is for transferring data between two FDs via pipe, and fd_out can only read data from pipe; this feature can borrow buffer from group lead to members, so member request can write data to this buffer if the provided buffer is allowed to write to. - splice implements data transfer by moving pages between subsystem and pipe, that means page ownership is transferred, and this way is one of the most complicated thing of splice; this patch supports scenarios in which the buffer can't be transferred, and buffer is only borrowed to member requests, and is returned back after member requests consume the provided buffer, so buffer lifetime is simplified a lot. Especially the buffer is guaranteed to be returned back. - splice can't run in async way basically It can help to implement generic zero copy between device and related operations, such as ublk, fuse, vdpa, even network receive or whatever. Signed-off-by: Ming Lei <ming.lei@redhat.com> --- include/linux/io_uring_types.h | 33 +++++++++++++++++++ io_uring/io_uring.c | 10 +++++- io_uring/io_uring.h | 5 +++ io_uring/kbuf.c | 60 ++++++++++++++++++++++++++++++++++ io_uring/kbuf.h | 13 ++++++++ io_uring/net.c | 31 +++++++++++++++++- io_uring/opdef.c | 5 +++ io_uring/opdef.h | 2 ++ io_uring/rw.c | 20 +++++++++++- 9 files changed, 176 insertions(+), 3 deletions(-)