From: Ming Lei Date: Fri, 19 May 2023 06:50:29 +0000 (+0800) Subject: ublk: add read()/write() support for ublk char device X-Git-Tag: for-6.5/block-2023-06-23~182 X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=62fe99cef94a5900cac3bf15fd03ee8baad1a99c;p=linux-2.6-block.git ublk: add read()/write() support for ublk char device Support pread()/pwrite() on ublk char device for reading/writing request io buffer, so data copy between io request buffer and userspace buffer can be moved to ublk server from ublk driver. Then UBLK_F_NEED_GET_DATA becomes not necessary, so ublk server can allocate buffer without one extra round uring command communication for userspace to provide buffer. IO buffer can be located by iocb->ki_pos which encodes buffer offset, io tag and queue id info, and type of iocb->ki_pos is u64, so it is big enough for holding reasonable queue depth, nr_queues and max io buffer size. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230519065030.351216-7-ming.lei@redhat.com Signed-off-by: Jens Axboe --- diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 13523c37a165..ec40ac4f9af3 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -207,6 +207,23 @@ static unsigned int ublks_added; /* protected by ublk_ctl_mutex */ static struct miscdevice ublk_misc; +static inline unsigned ublk_pos_to_hwq(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) & + UBLK_QID_BITS_MASK; +} + +static inline unsigned ublk_pos_to_buf_off(loff_t pos) +{ + return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK; +} + +static inline unsigned ublk_pos_to_tag(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) & + UBLK_TAG_BITS_MASK; +} + static void ublk_dev_param_basic_apply(struct ublk_device *ub) { struct request_queue *q = ub->ub_disk->queue; @@ -1429,6 +1446,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, return -EIOCBQUEUED; } +static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, + struct ublk_queue *ubq, int tag, size_t offset) +{ + struct request *req; + + if (!ublk_need_req_ref(ubq)) + return NULL; + + req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag); + if (!req) + return NULL; + + if (!ublk_get_req_ref(ubq, req)) + return NULL; + + if (unlikely(!blk_mq_request_started(req) || req->tag != tag)) + goto fail_put; + + if (!ublk_rq_has_data(req)) + goto fail_put; + + if (offset > blk_rq_bytes(req)) + goto fail_put; + + return req; +fail_put: + ublk_put_req_ref(ubq, req); + return NULL; +} + static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { /* @@ -1446,11 +1493,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); } +static inline bool ublk_check_ubuf_dir(const struct request *req, + int ubuf_dir) +{ + /* copy ubuf to request pages */ + if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE) + return true; + + /* copy request pages to ubuf */ + if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST) + return true; + + return false; +} + +static struct request *ublk_check_and_get_req(struct kiocb *iocb, + struct iov_iter *iter, size_t *off, int dir) +{ + struct ublk_device *ub = iocb->ki_filp->private_data; + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + u16 tag, q_id; + + if (!ub) + return ERR_PTR(-EACCES); + + if (!user_backed_iter(iter)) + return ERR_PTR(-EACCES); + + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + return ERR_PTR(-EACCES); + + tag = ublk_pos_to_tag(iocb->ki_pos); + q_id = ublk_pos_to_hwq(iocb->ki_pos); + buf_off = ublk_pos_to_buf_off(iocb->ki_pos); + + if (q_id >= ub->dev_info.nr_hw_queues) + return ERR_PTR(-EINVAL); + + ubq = ublk_get_queue(ub, q_id); + if (!ubq) + return ERR_PTR(-EINVAL); + + if (tag >= ubq->q_depth) + return ERR_PTR(-EINVAL); + + req = __ublk_check_and_get_req(ub, ubq, tag, buf_off); + if (!req) + return ERR_PTR(-EINVAL); + + if (!req->mq_hctx || !req->mq_hctx->driver_data) + goto fail; + + if (!ublk_check_ubuf_dir(req, dir)) + goto fail; + + *off = buf_off; + return req; +fail: + ublk_put_req_ref(ubq, req); + return ERR_PTR(-EACCES); +} + +static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + +static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, .llseek = no_llseek, + .read_iter = ublk_ch_read_iter, + .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, .mmap = ublk_ch_mmap, }; @@ -2362,6 +2510,9 @@ static int __init ublk_init(void) { int ret; + BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET + + UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET); + init_waitqueue_head(&ublk_idr_wq); ret = misc_register(&ublk_misc); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 640bf687b94a..c0c1632c671e 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -93,9 +93,29 @@ #define UBLKSRV_CMD_BUF_OFFSET 0 #define UBLKSRV_IO_BUF_OFFSET 0x80000000 -/* tag bit is 12bit, so at most 4096 IOs for each queue */ +/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */ #define UBLK_MAX_QUEUE_DEPTH 4096 +/* single IO buffer max size is 32MB */ +#define UBLK_IO_BUF_OFF 0 +#define UBLK_IO_BUF_BITS 25 +#define UBLK_IO_BUF_BITS_MASK ((1ULL << UBLK_IO_BUF_BITS) - 1) + +/* so at most 64K IOs for each queue */ +#define UBLK_TAG_OFF UBLK_IO_BUF_BITS +#define UBLK_TAG_BITS 16 +#define UBLK_TAG_BITS_MASK ((1ULL << UBLK_TAG_BITS) - 1) + +/* max 4096 queues */ +#define UBLK_QID_OFF (UBLK_TAG_OFF + UBLK_TAG_BITS) +#define UBLK_QID_BITS 12 +#define UBLK_QID_BITS_MASK ((1ULL << UBLK_QID_BITS) - 1) + +#define UBLK_MAX_NR_QUEUES (1U << UBLK_QID_BITS) + +#define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) +#define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) + /* * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space