/* below is for ring provided buffers */
__u16 buf_nr_pages;
__u16 nr_entries;
- __u32 head;
- __u32 mask;
+ __u16 head;
+ __u16 mask;
};
struct io_buffer {
struct file *file;
int fd;
u32 file_slot;
- u32 flags;
};
struct io_timeout_data {
u32 len;
};
-struct io_nop {
- struct file *file;
- u64 extra1;
- u64 extra2;
-};
-
struct io_async_connect {
struct sockaddr_storage address;
};
REQ_F_SINGLE_POLL_BIT,
REQ_F_DOUBLE_POLL_BIT,
REQ_F_PARTIAL_IO_BIT,
+ REQ_F_CQE32_INIT_BIT,
REQ_F_APOLL_MULTISHOT_BIT,
/* keep async read/write and isreg together and in order */
REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
/* fast poll multishot mode */
REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
+ /* ->extra1 and ->extra2 are initialised */
+ REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT),
};
struct async_poll {
struct io_msg msg;
struct io_xattr xattr;
struct io_socket sock;
- struct io_nop nop;
struct io_uring_cmd uring_cmd;
};
[IORING_OP_NOP] = {
.audit_skip = 1,
.iopoll = 1,
- .buffer_select = 1,
},
[IORING_OP_READV] = {
.needs_file = 1,
if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
return;
- /* don't recycle if we already did IO to this buffer */
- if (req->flags & REQ_F_PARTIAL_IO)
+ /*
+ * For legacy provided buffer mode, don't recycle if we already did
+ * IO to this buffer. For ring-mapped provided buffer mode, we should
+ * increment ring->head to explicitly monopolize the buffer to avoid
+ * multiple use.
+ */
+ if ((req->flags & REQ_F_BUFFER_SELECTED) &&
+ (req->flags & REQ_F_PARTIAL_IO))
return;
+
/*
* We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
* the flag and hence ensure that bl->head doesn't get incremented.
*/
if (req->flags & REQ_F_BUFFER_RING) {
if (req->buf_list) {
- req->buf_index = req->buf_list->bgid;
- req->flags &= ~REQ_F_BUFFER_RING;
+ if (req->flags & REQ_F_PARTIAL_IO) {
+ req->buf_list->head++;
+ req->buf_list = NULL;
+ } else {
+ req->buf_index = req->buf_list->bgid;
+ req->flags &= ~REQ_F_BUFFER_RING;
+ }
}
return;
}
return true;
}
-static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data,
- s32 res, u32 cflags)
+static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
+ struct io_kiocb *req)
{
struct io_uring_cqe *cqe;
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- WRITE_ONCE(cqe->user_data, user_data);
- WRITE_ONCE(cqe->res, res);
- WRITE_ONCE(cqe->flags, cflags);
- return true;
- }
- return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
-}
+ if (!(ctx->flags & IORING_SETUP_CQE32)) {
+ trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags, 0, 0);
-static inline bool __io_fill_cqe_req_filled(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
-{
- struct io_uring_cqe *cqe;
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqe(ctx);
+ if (likely(cqe)) {
+ memcpy(cqe, &req->cqe, sizeof(*cqe));
+ return true;
+ }
- trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
- req->cqe.res, req->cqe.flags, 0, 0);
+ return io_cqring_event_overflow(ctx, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags,
+ 0, 0);
+ } else {
+ u64 extra1 = 0, extra2 = 0;
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- memcpy(cqe, &req->cqe, sizeof(*cqe));
- return true;
- }
- return io_cqring_event_overflow(ctx, req->cqe.user_data,
- req->cqe.res, req->cqe.flags, 0, 0);
-}
+ if (req->flags & REQ_F_CQE32_INIT) {
+ extra1 = req->extra1;
+ extra2 = req->extra2;
+ }
-static inline bool __io_fill_cqe32_req_filled(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
-{
- struct io_uring_cqe *cqe;
- u64 extra1 = req->extra1;
- u64 extra2 = req->extra2;
+ trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags, extra1, extra2);
- trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
- req->cqe.res, req->cqe.flags, extra1, extra2);
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqe(ctx);
+ if (likely(cqe)) {
+ memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe));
+ WRITE_ONCE(cqe->big_cqe[0], extra1);
+ WRITE_ONCE(cqe->big_cqe[1], extra2);
+ return true;
+ }
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe));
- cqe->big_cqe[0] = extra1;
- cqe->big_cqe[1] = extra2;
- return true;
+ return io_cqring_event_overflow(ctx, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags,
+ extra1, extra2);
}
-
- return io_cqring_event_overflow(ctx, req->cqe.user_data, req->cqe.res,
- req->cqe.flags, extra1, extra2);
-}
-
-static inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
-{
- trace_io_uring_complete(req->ctx, req, req->cqe.user_data, res, cflags, 0, 0);
- return __io_fill_cqe(req->ctx, req->cqe.user_data, res, cflags);
}
-static inline void __io_fill_cqe32_req(struct io_kiocb *req, s32 res, u32 cflags,
- u64 extra1, u64 extra2)
+static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
+ s32 res, u32 cflags)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_uring_cqe *cqe;
- if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32)))
- return;
- if (req->flags & REQ_F_CQE_SKIP)
- return;
-
- trace_io_uring_complete(ctx, req, req->cqe.user_data, res, cflags,
- extra1, extra2);
+ ctx->cq_extra++;
+ trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
/*
* If we can't get a cq entry, userspace overflowed the
*/
cqe = io_get_cqe(ctx);
if (likely(cqe)) {
- WRITE_ONCE(cqe->user_data, req->cqe.user_data);
+ WRITE_ONCE(cqe->user_data, user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
- WRITE_ONCE(cqe->big_cqe[0], extra1);
- WRITE_ONCE(cqe->big_cqe[1], extra2);
- return;
- }
- io_cqring_event_overflow(ctx, req->cqe.user_data, res, cflags, extra1, extra2);
-}
-
-static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
- s32 res, u32 cflags)
-{
- ctx->cq_extra++;
- trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
- return __io_fill_cqe(ctx, user_data, res, cflags);
+ if (ctx->flags & IORING_SETUP_CQE32) {
+ WRITE_ONCE(cqe->big_cqe[0], 0);
+ WRITE_ONCE(cqe->big_cqe[1], 0);
+ }
+ return true;
+ }
+ return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
}
static void __io_req_complete_put(struct io_kiocb *req)
static void __io_req_complete_post(struct io_kiocb *req, s32 res,
u32 cflags)
{
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe_req(req, res, cflags);
- __io_req_complete_put(req);
-}
-
-static void __io_req_complete_post32(struct io_kiocb *req, s32 res,
- u32 cflags, u64 extra1, u64 extra2)
-{
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe32_req(req, res, cflags, extra1, extra2);
+ if (!(req->flags & REQ_F_CQE_SKIP)) {
+ req->cqe.res = res;
+ req->cqe.flags = cflags;
+ __io_fill_cqe_req(req->ctx, req);
+ }
__io_req_complete_put(req);
}
io_cqring_ev_posted(ctx);
}
-static void io_req_complete_post32(struct io_kiocb *req, s32 res,
- u32 cflags, u64 extra1, u64 extra2)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock(&ctx->completion_lock);
- __io_req_complete_post32(req, res, cflags, extra1, extra2);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
-}
-
static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
u32 cflags)
{
io_req_complete_post(req, res, cflags);
}
-static inline void __io_req_complete32(struct io_kiocb *req,
- unsigned int issue_flags, s32 res,
- u32 cflags, u64 extra1, u64 extra2)
-{
- if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
- io_req_complete_state(req, res, cflags);
- req->extra1 = extra1;
- req->extra2 = extra2;
- } else {
- io_req_complete_post32(req, res, cflags, extra1, extra2);
- }
-}
-
static inline void io_req_complete(struct io_kiocb *req, s32 res)
{
if (res < 0)
struct io_kiocb *req = container_of(node, struct io_kiocb,
comp_list);
- if (!(req->flags & REQ_F_CQE_SKIP)) {
- if (!(ctx->flags & IORING_SETUP_CQE32))
- __io_fill_cqe_req_filled(ctx, req);
- else
- __io_fill_cqe32_req_filled(ctx, req);
- }
+ if (!(req->flags & REQ_F_CQE_SKIP))
+ __io_fill_cqe_req(ctx, req);
}
io_commit_cqring(ctx);
nr_events++;
if (unlikely(req->flags & REQ_F_CQE_SKIP))
continue;
- __io_fill_cqe_req(req, req->cqe.res, io_put_kbuf(req, 0));
+
+ req->cqe.flags = io_put_kbuf(req, 0);
+ __io_fill_cqe_req(req->ctx, req);
}
if (unlikely(!nr_events))
int ret;
kiocb->ki_pos = READ_ONCE(sqe->off);
+ /* used for fixed read/write too - just read unconditionally */
+ req->buf_index = READ_ONCE(sqe->buf_index);
+
+ if (req->opcode == IORING_OP_READ_FIXED ||
+ req->opcode == IORING_OP_WRITE_FIXED) {
+ struct io_ring_ctx *ctx = req->ctx;
+ u16 index;
+
+ if (unlikely(req->buf_index >= ctx->nr_user_bufs))
+ return -EFAULT;
+ index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
+ req->imu = ctx->user_bufs[index];
+ io_req_set_rsrc_node(req, ctx, 0);
+ }
ioprio = READ_ONCE(sqe->ioprio);
if (ioprio) {
kiocb->ki_ioprio = get_current_ioprio();
}
- req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
req->rw.flags = READ_ONCE(sqe->rw_flags);
- /* used for fixed read/write too - just read unconditionally */
- req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
unsigned int issue_flags)
{
- struct io_mapped_ubuf *imu = req->imu;
- u16 index, buf_index = req->buf_index;
-
- if (likely(!imu)) {
- struct io_ring_ctx *ctx = req->ctx;
-
- if (unlikely(buf_index >= ctx->nr_user_bufs))
- return -EFAULT;
- io_req_set_rsrc_node(req, ctx, issue_flags);
- index = array_index_nospec(buf_index, ctx->nr_user_bufs);
- imu = READ_ONCE(ctx->user_bufs[index]);
- req->imu = imu;
- }
- return __io_import_fixed(req, rw, iter, imu);
+ if (WARN_ON_ONCE(!req->imu))
+ return -EFAULT;
+ return __io_import_fixed(req, rw, iter, req->imu);
}
static int io_buffer_add_list(struct io_ring_ctx *ctx,
{
struct io_uring_buf_ring *br = bl->buf_ring;
struct io_uring_buf *buf;
- __u32 head = bl->head;
+ __u16 head = bl->head;
- if (unlikely(smp_load_acquire(&br->tail) == head)) {
- io_ring_submit_unlock(req->ctx, issue_flags);
+ if (unlikely(smp_load_acquire(&br->tail) == head))
return NULL;
- }
head &= bl->mask;
if (head < IO_BUFFER_LIST_BUF_PER_PAGE) {
buf = &br->bufs[head];
} else {
int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1);
- int index = head / IO_BUFFER_LIST_BUF_PER_PAGE - 1;
+ int index = head / IO_BUFFER_LIST_BUF_PER_PAGE;
buf = page_address(bl->buf_pages[index]);
buf += off;
}
req->buf_list = bl;
req->buf_index = buf->bid;
- if (issue_flags & IO_URING_F_UNLOCKED) {
+ if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
/*
* If we came in unlocked, we have no choice but to consume the
* buffer here. This does mean it'll be pinned until the IO
req->uring_cmd.task_work_cb = task_work_cb;
req->io_task_work.func = io_uring_cmd_work;
- io_req_task_prio_work_add(req);
+ io_req_task_work_add(req);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);
+static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
+ u64 extra1, u64 extra2)
+{
+ req->extra1 = extra1;
+ req->extra2 = extra2;
+ req->flags |= REQ_F_CQE32_INIT;
+}
+
/*
* Called by consumers of io_uring_cmd, if they originally returned
* -EIOCBQUEUED upon receiving the command.
if (ret < 0)
req_set_fail(req);
+
if (req->ctx->flags & IORING_SETUP_CQE32)
- __io_req_complete32(req, 0, ret, 0, res2, 0);
- else
- io_req_complete(req, ret);
+ io_req_set_cqe32_extra(req, res2, 0);
+ io_req_complete(req, ret);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_done);
static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- /*
- * If the ring is setup with CQE32, relay back addr/addr
- */
- if (req->ctx->flags & IORING_SETUP_CQE32) {
- req->nop.extra1 = READ_ONCE(sqe->addr);
- req->nop.extra2 = READ_ONCE(sqe->addr2);
- }
-
return 0;
}
*/
static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
{
- unsigned int cflags;
- void __user *buf;
-
- if (req->flags & REQ_F_BUFFER_SELECT) {
- size_t len = 1;
-
- buf = io_buffer_select(req, &len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- }
-
- cflags = io_put_kbuf(req, issue_flags);
- if (!(req->ctx->flags & IORING_SETUP_CQE32))
- __io_req_complete(req, issue_flags, 0, cflags);
- else
- __io_req_complete32(req, issue_flags, 0, cflags,
- req->nop.extra1, req->nop.extra2);
+ __io_req_complete(req, issue_flags, 0, 0);
return 0;
}
static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- if (sqe->off || sqe->addr || sqe->len || sqe->buf_index)
+ if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index)
return -EINVAL;
if (req->flags & REQ_F_FIXED_FILE)
return -EBADF;
req->close.fd = READ_ONCE(sqe->fd);
req->close.file_slot = READ_ONCE(sqe->file_index);
- req->close.flags = READ_ONCE(sqe->close_flags);
- if (req->close.flags & ~IORING_CLOSE_FD_AND_FILE_SLOT)
- return -EINVAL;
- if (!(req->close.flags & IORING_CLOSE_FD_AND_FILE_SLOT) &&
- req->close.file_slot && req->close.fd)
+ if (req->close.file_slot && req->close.fd)
return -EINVAL;
return 0;
if (req->close.file_slot) {
ret = io_close_fixed(req, issue_flags);
- if (ret || !(req->close.flags & IORING_CLOSE_FD_AND_FILE_SLOT))
- goto err;
+ goto err;
}
spin_lock(&files->file_lock);
if (ret < 0)
break;
if (copy_to_user(&fds[done], &ret, sizeof(ret))) {
- ret = -EFAULT;
__io_close_fixed(req, issue_flags, ret);
+ ret = -EFAULT;
break;
}
}
* Queued up for async execution, worker will release
* submit reference when the iocb is actually submitted.
*/
+ io_kbuf_recycle(req, 0);
io_queue_iowq(req, NULL);
break;
case IO_APOLL_OK:
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
+ unsigned nr = ctx->nr_user_files;
int ret;
if (!ctx->file_data)
return -ENXIO;
+
+ /*
+ * Quiesce may unlock ->uring_lock, and while it's not held
+ * prevent new requests using the table.
+ */
+ ctx->nr_user_files = 0;
ret = io_rsrc_ref_quiesce(ctx->file_data, ctx);
+ ctx->nr_user_files = nr;
if (!ret)
__io_sqe_files_unregister(ctx);
return ret;
static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
{
+ unsigned nr = ctx->nr_user_bufs;
int ret;
if (!ctx->buf_data)
return -ENXIO;
+ /*
+ * Quiesce may unlock ->uring_lock, and while it's not held
+ * prevent new requests using the table.
+ */
+ ctx->nr_user_bufs = 0;
ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx);
+ ctx->nr_user_bufs = nr;
if (!ret)
__io_sqe_buffers_unregister(ctx);
return ret;
if (!is_power_of_2(reg.ring_entries))
return -EINVAL;
+ /* cannot disambiguate full vs empty due to head/tail size */
+ if (reg.ring_entries >= 65536)
+ return -EINVAL;
+
if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) {
int ret = io_init_bl_list(ctx);
if (ret)
projects / linux-2.6-microblaze.git / blobdiff