ublk_register_io_buf() performs an expensive atomic refcount increment,
as well as a lot of pointer chasing to look up the struct request.
Create a separate ublk_daemon_register_io_buf() for the daemon task to
call. Initialize ublk_io's reference count to a large number, introduce
a field task_registered_buffers to count the buffers registered on the
daemon task, and atomically subtract the large number minus
task_registered_buffers in ublk_commit_and_fetch().
Also obtain the struct request directly from ublk_io's req field instead
of looking it up on the tagset.
Signed-off-by: Caleb Sander Mateos <csander@xxxxxxxxxxxxxxx>
---
drivers/block/ublk_drv.c | 70 ++++++++++++++++++++++++++++++++++------
1 file changed, 61 insertions(+), 9 deletions(-)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index f53618391141..b2925e15279a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -146,10 +146,17 @@ struct ublk_uring_cmd_pdu {
#define UBLK_IO_FLAG_AUTO_BUF_REG 0x10
/* atomic RW with ubq->cancel_lock */
#define UBLK_IO_FLAG_CANCELED 0x80000000
+/*
+ * Initialize refcount to a large number to include any registered buffers.
+ * UBLK_IO_COMMIT_AND_FETCH_REQ will release these references minus those for
+ * any buffers registered on the io daemon task.
+ */
+#define UBLK_REFCOUNT_INIT (REFCOUNT_MAX / 2)
+
struct ublk_io {
/* userspace buffer address from io cmd */
__u64 addr;
unsigned int flags;
int res;
@@ -164,18 +171,21 @@ struct ublk_io {
struct task_struct *task;
/*
* The number of uses of this I/O by the ublk server
* if user copy or zero copy are enabled:
- * - 1 from dispatch to the server until UBLK_IO_COMMIT_AND_FETCH_REQ
+ * - UBLK_REFCOUNT_INIT from dispatch to the server
+ * until UBLK_IO_COMMIT_AND_FETCH_REQ
* - 1 for each inflight ublk_ch_{read,write}_iter() call
- * - 1 for each io_uring registered buffer
+ * - 1 for each io_uring registered buffer not registered on task
* The I/O can only be completed once all references are dropped.
* User copy and buffer registration operations are only permitted
* if the reference count is nonzero.
*/
refcount_t ref;
+ /* Count of buffers registered on task and not yet unregistered */
+ unsigned task_registered_buffers;
/* auto-registered buffer, valid if UBLK_IO_FLAG_AUTO_BUF_REG is set */
u16 buf_index;
void *buf_ctx_handle;
};
@@ -684,11 +694,11 @@ static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
struct ublk_io *io)
{
if (ublk_need_req_ref(ubq))
- refcount_set(&io->ref, 1);
+ refcount_set(&io->ref, UBLK_REFCOUNT_INIT);
}
static inline bool ublk_get_req_ref(const struct ublk_queue *ubq,
struct ublk_io *io)
{
@@ -707,10 +717,19 @@ static inline void ublk_put_req_ref(const struct ublk_queue *ubq,
} else {
__ublk_complete_rq(req);
}
}
+static inline void ublk_sub_req_ref(struct ublk_io *io, struct request *req)
+{
+ unsigned sub_refs = UBLK_REFCOUNT_INIT - io->task_registered_buffers;
+
+ io->task_registered_buffers = 0;
+ if (refcount_sub_and_test(sub_refs, &io->ref))
+ __ublk_complete_rq(req);
+}
+
static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
{
return ubq->flags & UBLK_F_NEED_GET_DATA;
}
@@ -1188,11 +1207,10 @@ ublk_auto_buf_reg_fallback(const struct ublk_queue *ubq, struct ublk_io *io)
{
unsigned tag = io - ubq->ios;
struct ublksrv_io_desc *iod = ublk_get_iod(ubq, tag);
iod->op_flags |= UBLK_IO_F_NEED_REG_BUF;
- refcount_set(&io->ref, 1);
}
static bool ublk_auto_buf_reg(const struct ublk_queue *ubq, struct request *req,
struct ublk_io *io, unsigned int issue_flags)
{
@@ -1207,13 +1225,12 @@ static bool ublk_auto_buf_reg(const struct ublk_queue *ubq, struct request *req,
return true;
}
blk_mq_end_request(req, BLK_STS_IOERR);
return false;
}
- /* one extra reference is dropped by ublk_io_release */
- refcount_set(&io->ref, 2);
+ io->task_registered_buffers = 1;
io->buf_ctx_handle = io_uring_cmd_ctx_handle(io->cmd);
/* store buffer index in request payload */
io->buf_index = pdu->buf.index;
io->flags |= UBLK_IO_FLAG_AUTO_BUF_REG;
return true;
@@ -1221,14 +1238,14 @@ static bool ublk_auto_buf_reg(const struct ublk_queue *ubq, struct request *req,
static bool ublk_prep_auto_buf_reg(struct ublk_queue *ubq,
struct request *req, struct ublk_io *io,
unsigned int issue_flags)
{
+ ublk_init_req_ref(ubq, io);
if (ublk_support_auto_buf_reg(ubq) && ublk_rq_has_data(req))
return ublk_auto_buf_reg(ubq, req, io, issue_flags);
- ublk_init_req_ref(ubq, io);
return true;
}
static bool ublk_start_io(const struct ublk_queue *ubq, struct request *req,
struct ublk_io *io)
@@ -1488,10 +1505,11 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
put_task_struct(io->task);
io->task = NULL;
}
WARN_ON_ONCE(refcount_read(&io->ref));
+ WARN_ON_ONCE(io->task_registered_buffers);
}
}
static int ublk_ch_open(struct inode *inode, struct file *filp)
{
@@ -2023,10 +2041,39 @@ static int ublk_register_io_buf(struct io_uring_cmd *cmd,
}
return 0;
}
+static int
+ublk_daemon_register_io_buf(struct io_uring_cmd *cmd,
+ const struct ublk_queue *ubq, struct ublk_io *io,
+ unsigned index, unsigned issue_flags)
+{
+ unsigned new_registered_buffers;
+ struct request *req = io->req;
+ int ret;
+
+ /*
+ * Ensure there are still references for ublk_sub_req_ref() to release.
+ * If not, fall back on the thread-safe buffer registration.
+ */
+ new_registered_buffers = io->task_registered_buffers + 1;
+ if (unlikely(new_registered_buffers >= UBLK_REFCOUNT_INIT))
+ return ublk_register_io_buf(cmd, ubq, io, index, issue_flags);
+
+ if (!ublk_support_zero_copy(ubq) || !ublk_rq_has_data(req))
+ return -EINVAL;
+
+ ret = io_buffer_register_bvec(cmd, req, ublk_io_release, index,
+ issue_flags);
+ if (ret)
+ return ret;
+
+ io->task_registered_buffers = new_registered_buffers;
+ return 0;
+}
+
static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
const struct ublk_device *ub,
unsigned int index, unsigned int issue_flags)
{
if (!(ub->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY))
@@ -2146,11 +2193,14 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq,
req->__sector = ub_cmd->zone_append_lba;
if (unlikely(blk_should_fake_timeout(req->q)))
return 0;
- ublk_put_req_ref(ubq, io, req);
+ if (ublk_need_req_ref(ubq))
+ ublk_sub_req_ref(io, req);
+ else
+ __ublk_complete_rq(req);
return 0;
}
static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io)
{
@@ -2244,11 +2294,12 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
goto out;
switch (_IOC_NR(cmd_op)) {
case UBLK_IO_REGISTER_IO_BUF:
- return ublk_register_io_buf(cmd, ubq, io, ub_cmd->addr, issue_flags);
+ return ublk_daemon_register_io_buf(cmd, ubq, io, ub_cmd->addr,
+ issue_flags);
case UBLK_IO_COMMIT_AND_FETCH_REQ:
ret = ublk_commit_and_fetch(ubq, io, cmd, ub_cmd, issue_flags);
if (ret)
goto out;
@@ -2473,10 +2524,11 @@ static void ublk_deinit_queue(struct ublk_device *ub, int q_id)
for (i = 0; i < ubq->q_depth; i++) {
struct ublk_io *io = &ubq->ios[i];
if (io->task)
put_task_struct(io->task);
WARN_ON_ONCE(refcount_read(&io->ref));
+ WARN_ON_ONCE(io->task_registered_buffers);
}
if (ubq->io_cmd_buf)
free_pages((unsigned long)ubq->io_cmd_buf, get_order(size));
}
--
2.45.2
