summaryrefslogtreecommitdiff
path: root/io_uring/rw.c
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring/rw.c')
-rw-r--r--io_uring/rw.c237
1 files changed, 132 insertions, 105 deletions
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 7aa1e4c9f64a..7c2f5f70a2c5 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -23,6 +23,9 @@
#include "poll.h"
#include "rw.h"
+static void io_complete_rw(struct kiocb *kiocb, long res);
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res);
+
struct io_rw {
/* NOTE: kiocb has the file as the first member, so don't do it here */
struct kiocb kiocb;
@@ -46,24 +49,16 @@ static bool io_file_supports_nowait(struct io_kiocb *req, __poll_t mask)
return false;
}
-#ifdef CONFIG_COMPAT
static int io_iov_compat_buffer_select_prep(struct io_rw *rw)
{
- struct compat_iovec __user *uiov;
- compat_ssize_t clen;
+ struct compat_iovec __user *uiov = u64_to_user_ptr(rw->addr);
+ struct compat_iovec iov;
- uiov = u64_to_user_ptr(rw->addr);
- if (!access_ok(uiov, sizeof(*uiov)))
+ if (copy_from_user(&iov, uiov, sizeof(iov)))
return -EFAULT;
- if (__get_user(clen, &uiov->iov_len))
- return -EFAULT;
- if (clen < 0)
- return -EINVAL;
-
- rw->len = clen;
+ rw->len = iov.iov_len;
return 0;
}
-#endif
static int io_iov_buffer_select_prep(struct io_kiocb *req)
{
@@ -74,10 +69,8 @@ static int io_iov_buffer_select_prep(struct io_kiocb *req)
if (rw->len != 1)
return -EINVAL;
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
return io_iov_compat_buffer_select_prep(rw);
-#endif
uiov = u64_to_user_ptr(rw->addr);
if (copy_from_user(&iov, uiov, sizeof(*uiov)))
@@ -86,41 +79,24 @@ static int io_iov_buffer_select_prep(struct io_kiocb *req)
return 0;
}
-static int __io_import_iovec(int ddir, struct io_kiocb *req,
- struct io_async_rw *io,
- unsigned int issue_flags)
+static int io_import_vec(int ddir, struct io_kiocb *req,
+ struct io_async_rw *io,
+ const struct iovec __user *uvec,
+ size_t uvec_segs)
{
- const struct io_issue_def *def = &io_issue_defs[req->opcode];
- struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ int ret, nr_segs;
struct iovec *iov;
- void __user *buf;
- int nr_segs, ret;
- size_t sqe_len;
-
- buf = u64_to_user_ptr(rw->addr);
- sqe_len = rw->len;
-
- if (!def->vectored || req->flags & REQ_F_BUFFER_SELECT) {
- if (io_do_buffer_select(req)) {
- buf = io_buffer_select(req, &sqe_len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- rw->addr = (unsigned long) buf;
- rw->len = sqe_len;
- }
-
- return import_ubuf(ddir, buf, sqe_len, &io->iter);
- }
if (io->free_iovec) {
nr_segs = io->free_iov_nr;
iov = io->free_iovec;
} else {
- iov = &io->fast_iov;
nr_segs = 1;
+ iov = &io->fast_iov;
}
- ret = __import_iovec(ddir, buf, sqe_len, nr_segs, &iov, &io->iter,
- req->ctx->compat);
+
+ ret = __import_iovec(ddir, uvec, uvec_segs, nr_segs, &iov, &io->iter,
+ io_is_compat(req->ctx));
if (unlikely(ret < 0))
return ret;
if (iov) {
@@ -132,13 +108,35 @@ static int __io_import_iovec(int ddir, struct io_kiocb *req,
return 0;
}
-static inline int io_import_iovec(int rw, struct io_kiocb *req,
- struct io_async_rw *io,
- unsigned int issue_flags)
+static int __io_import_rw_buffer(int ddir, struct io_kiocb *req,
+ struct io_async_rw *io,
+ unsigned int issue_flags)
+{
+ const struct io_issue_def *def = &io_issue_defs[req->opcode];
+ struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ void __user *buf = u64_to_user_ptr(rw->addr);
+ size_t sqe_len = rw->len;
+
+ if (def->vectored && !(req->flags & REQ_F_BUFFER_SELECT))
+ return io_import_vec(ddir, req, io, buf, sqe_len);
+
+ if (io_do_buffer_select(req)) {
+ buf = io_buffer_select(req, &sqe_len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ rw->addr = (unsigned long) buf;
+ rw->len = sqe_len;
+ }
+ return import_ubuf(ddir, buf, sqe_len, &io->iter);
+}
+
+static inline int io_import_rw_buffer(int rw, struct io_kiocb *req,
+ struct io_async_rw *io,
+ unsigned int issue_flags)
{
int ret;
- ret = __io_import_iovec(rw, req, io, issue_flags);
+ ret = __io_import_rw_buffer(rw, req, io, issue_flags);
if (unlikely(ret < 0))
return ret;
@@ -209,20 +207,6 @@ static int io_rw_alloc_async(struct io_kiocb *req)
return 0;
}
-static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import)
-{
- struct io_async_rw *rw;
-
- if (io_rw_alloc_async(req))
- return -ENOMEM;
-
- if (!do_import || io_do_buffer_select(req))
- return 0;
-
- rw = req->async_data;
- return io_import_iovec(ddir, req, rw, 0);
-}
-
static inline void io_meta_save_state(struct io_async_rw *io)
{
io->meta_state.seed = io->meta.seed;
@@ -264,14 +248,17 @@ static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir,
return ret;
}
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- int ddir, bool do_import)
+static int __io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ int ddir)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
unsigned ioprio;
u64 attr_type_mask;
int ret;
+ if (io_rw_alloc_async(req))
+ return -ENOMEM;
+
rw->kiocb.ki_pos = READ_ONCE(sqe->off);
/* used for fixed read/write too - just read unconditionally */
req->buf_index = READ_ONCE(sqe->buf_index);
@@ -289,13 +276,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
rw->kiocb.dio_complete = NULL;
rw->kiocb.ki_flags = 0;
+ if (req->ctx->flags & IORING_SETUP_IOPOLL)
+ rw->kiocb.ki_complete = io_complete_rw_iopoll;
+ else
+ rw->kiocb.ki_complete = io_complete_rw;
+
rw->addr = READ_ONCE(sqe->addr);
rw->len = READ_ONCE(sqe->len);
rw->flags = READ_ONCE(sqe->rw_flags);
- ret = io_prep_rw_setup(req, ddir, do_import);
-
- if (unlikely(ret))
- return ret;
attr_type_mask = READ_ONCE(sqe->attr_type_mask);
if (attr_type_mask) {
@@ -306,31 +294,50 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return -EINVAL;
attr_ptr = READ_ONCE(sqe->attr_ptr);
- ret = io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask);
+ return io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask);
}
- return ret;
+ return 0;
+}
+
+static int io_rw_do_import(struct io_kiocb *req, int ddir)
+{
+ if (io_do_buffer_select(req))
+ return 0;
+
+ return io_import_rw_buffer(ddir, req, req->async_data, 0);
+}
+
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ int ddir)
+{
+ int ret;
+
+ ret = __io_prep_rw(req, sqe, ddir);
+ if (unlikely(ret))
+ return ret;
+
+ return io_rw_do_import(req, ddir);
}
int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw(req, sqe, ITER_DEST, true);
+ return io_prep_rw(req, sqe, ITER_DEST);
}
int io_prep_write(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw(req, sqe, ITER_SOURCE, true);
+ return io_prep_rw(req, sqe, ITER_SOURCE);
}
static int io_prep_rwv(struct io_kiocb *req, const struct io_uring_sqe *sqe,
int ddir)
{
- const bool do_import = !(req->flags & REQ_F_BUFFER_SELECT);
int ret;
- ret = io_prep_rw(req, sqe, ddir, do_import);
+ ret = io_prep_rw(req, sqe, ddir);
if (unlikely(ret))
return ret;
- if (do_import)
+ if (!(req->flags & REQ_F_BUFFER_SELECT))
return 0;
/*
@@ -350,38 +357,30 @@ int io_prep_writev(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return io_prep_rwv(req, sqe, ITER_SOURCE);
}
-static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+static int io_init_rw_fixed(struct io_kiocb *req, unsigned int issue_flags,
int ddir)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
- struct io_ring_ctx *ctx = req->ctx;
- struct io_rsrc_node *node;
- struct io_async_rw *io;
+ struct io_async_rw *io = req->async_data;
int ret;
- ret = io_prep_rw(req, sqe, ddir, false);
- if (unlikely(ret))
- return ret;
-
- node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
- if (!node)
- return -EFAULT;
- io_req_assign_buf_node(req, node);
+ if (io->bytes_done)
+ return 0;
- io = req->async_data;
- ret = io_import_fixed(ddir, &io->iter, node->buf, rw->addr, rw->len);
+ ret = io_import_reg_buf(req, &io->iter, rw->addr, rw->len, ddir,
+ issue_flags);
iov_iter_save_state(&io->iter, &io->iter_state);
return ret;
}
int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw_fixed(req, sqe, ITER_DEST);
+ return __io_prep_rw(req, sqe, ITER_DEST);
}
int io_prep_write_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw_fixed(req, sqe, ITER_SOURCE);
+ return __io_prep_rw(req, sqe, ITER_SOURCE);
}
/*
@@ -397,7 +396,7 @@ int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (!(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
- ret = io_prep_rw(req, sqe, ITER_DEST, false);
+ ret = __io_prep_rw(req, sqe, ITER_DEST);
if (unlikely(ret))
return ret;
@@ -511,7 +510,7 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
return res;
}
-void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
+void io_req_rw_complete(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
struct kiocb *kiocb = &rw->kiocb;
@@ -528,7 +527,7 @@ void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
req->cqe.flags |= io_put_kbuf(req, req->cqe.res, 0);
io_req_rw_cleanup(req, 0);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
static void io_complete_rw(struct kiocb *kiocb, long res)
@@ -552,19 +551,20 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
if (kiocb->ki_flags & IOCB_WRITE)
io_req_end_write(req);
if (unlikely(res != req->cqe.res)) {
- if (res == -EAGAIN && io_rw_should_reissue(req)) {
+ if (res == -EAGAIN && io_rw_should_reissue(req))
req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
- return;
- }
- req->cqe.res = res;
+ else
+ req->cqe.res = res;
}
/* order with io_iopoll_complete() checking ->iopoll_completed */
smp_store_release(&req->iopoll_completed, 1);
}
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+static inline void io_rw_done(struct io_kiocb *req, ssize_t ret)
{
+ struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+
/* IO was queued async, completion will happen later */
if (ret == -EIOCBQUEUED)
return;
@@ -586,8 +586,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
}
}
- INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
- io_complete_rw, kiocb, ret);
+ if (req->ctx->flags & IORING_SETUP_IOPOLL)
+ io_complete_rw_iopoll(&rw->kiocb, ret);
+ else
+ io_complete_rw(&rw->kiocb, ret);
}
static int kiocb_done(struct io_kiocb *req, ssize_t ret,
@@ -598,7 +600,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
if (ret >= 0 && req->flags & REQ_F_CUR_POS)
req->file->f_pos = rw->kiocb.ki_pos;
- if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
+ if (ret >= 0 && !(req->ctx->flags & IORING_SETUP_IOPOLL)) {
__io_complete_rw_common(req, ret);
/*
* Safe to call io_end from here as we're inline
@@ -609,7 +611,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
io_req_rw_cleanup(req, issue_flags);
return IOU_OK;
} else {
- io_rw_done(&rw->kiocb, ret);
+ io_rw_done(req, ret);
}
return IOU_ISSUE_SKIP_COMPLETE;
@@ -626,6 +628,7 @@ 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;
@@ -641,6 +644,8 @@ static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
if ((kiocb->ki_flags & IOCB_NOWAIT) &&
!(kiocb->ki_filp->f_flags & O_NONBLOCK))
return -EAGAIN;
+ if ((req->flags & REQ_F_BUF_NODE) && req->buf_node->buf->is_kbuf)
+ return -EFAULT;
ppos = io_kiocb_ppos(kiocb);
@@ -813,10 +818,8 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
if (ctx->flags & IORING_SETUP_IOPOLL) {
if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
return -EOPNOTSUPP;
-
kiocb->private = NULL;
kiocb->ki_flags |= IOCB_HIPRI;
- kiocb->ki_complete = io_complete_rw_iopoll;
req->iopoll_completed = 0;
if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
/* make sure every req only blocks once*/
@@ -826,7 +829,6 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
} else {
if (kiocb->ki_flags & IOCB_HIPRI)
return -EINVAL;
- kiocb->ki_complete = io_complete_rw;
}
if (req->flags & REQ_F_HAS_METADATA) {
@@ -855,7 +857,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
loff_t *ppos;
if (io_do_buffer_select(req)) {
- ret = io_import_iovec(ITER_DEST, req, io, issue_flags);
+ ret = io_import_rw_buffer(ITER_DEST, req, io, issue_flags);
if (unlikely(ret < 0))
return ret;
}
@@ -904,7 +906,8 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
} else if (ret == -EIOCBQUEUED) {
return IOU_ISSUE_SKIP_COMPLETE;
} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
- (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
+ (req->flags & REQ_F_NOWAIT) || !need_complete_io(req) ||
+ (issue_flags & IO_URING_F_MULTISHOT)) {
/* read all, failed, already did sync or don't want to retry */
goto done;
}
@@ -977,6 +980,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
if (!io_file_can_poll(req))
return -EBADFD;
+ /* make it sync, multishot doesn't support async execution */
+ rw->kiocb.ki_complete = NULL;
ret = __io_read(req, issue_flags);
/*
@@ -1143,6 +1148,28 @@ ret_eagain:
}
}
+int io_read_fixed(struct io_kiocb *req, unsigned int issue_flags)
+{
+ int ret;
+
+ ret = io_init_rw_fixed(req, issue_flags, ITER_DEST);
+ if (unlikely(ret))
+ return ret;
+
+ return io_read(req, issue_flags);
+}
+
+int io_write_fixed(struct io_kiocb *req, unsigned int issue_flags)
+{
+ int ret;
+
+ ret = io_init_rw_fixed(req, issue_flags, ITER_SOURCE);
+ if (unlikely(ret))
+ return ret;
+
+ return io_write(req, issue_flags);
+}
+
void io_rw_fail(struct io_kiocb *req)
{
int res;