From 9d4ed6d46272bb60036a6539aae74eafcbbb3d2d Mon Sep 17 00:00:00 2001 From: Andreas Hindborg Date: Fri, 4 Aug 2023 13:46:08 +0200 Subject: ublk: add helper to check if device supports user copy This will be used by ublk zoned storage support. Signed-off-by: Andreas Hindborg Reviewed-by: Ming Lei Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230804114610.179530-2-nmi@metaspace.dk Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 1c823750c95a..8d271901efac 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -185,6 +185,11 @@ struct ublk_params_header { __u32 types; }; +static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub) +{ + return ub->dev_info.flags & UBLK_F_USER_COPY; +} + static inline void __ublk_complete_rq(struct request *req); static void ublk_complete_rq(struct kref *ref); @@ -2037,7 +2042,7 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) UBLK_F_URING_CMD_COMP_IN_TASK; /* GET_DATA isn't needed any more with USER_COPY */ - if (ub->dev_info.flags & UBLK_F_USER_COPY) + if (ublk_dev_is_user_copy(ub)) ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; /* We are not ready to support zero copy */ -- cgit v1.2.3 From 1a6e88b9593b63ccdfe1d84e3f99dd91e4f8d490 Mon Sep 17 00:00:00 2001 From: Andreas Hindborg Date: Fri, 4 Aug 2023 13:46:09 +0200 Subject: ublk: move check for empty address field on command submission In preparation for zoned storage support, move the check for empty `addr` field into the command handler case statement. Note that the check makes no sense for `UBLK_IO_NEED_GET_DATA` because the `addr` field must always be set for this command. Signed-off-by: Andreas Hindborg Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20230804114610.179530-3-nmi@metaspace.dk Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 8d271901efac..0e3847579610 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1419,11 +1419,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, ^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA)) goto out; - if (ublk_support_user_copy(ubq) && ub_cmd->addr) { - ret = -EINVAL; - goto out; - } - ret = ublk_check_cmd_op(cmd_op); if (ret) goto out; @@ -1450,6 +1445,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, */ if (!ub_cmd->addr && !ublk_need_get_data(ubq)) goto out; + } else if (ub_cmd->addr) { + /* User copy requires addr to be unset */ + ret = -EINVAL; + goto out; } ublk_fill_io_cmd(io, cmd, ub_cmd->addr); @@ -1469,7 +1468,12 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) goto out; + } else if (ub_cmd->addr) { + /* User copy requires addr to be unset */ + ret = -EINVAL; + goto out; } + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_commit_completion(ub, ub_cmd); break; -- cgit v1.2.3 From 29802d7ca33bc0a75c9da2a143eeed4f9e99fca4 Mon Sep 17 00:00:00 2001 From: Andreas Hindborg Date: Fri, 4 Aug 2023 13:46:10 +0200 Subject: ublk: enable zoned storage support Add zoned storage support to ublk: report_zones and operations: - REQ_OP_ZONE_OPEN - REQ_OP_ZONE_CLOSE - REQ_OP_ZONE_FINISH - REQ_OP_ZONE_RESET - REQ_OP_ZONE_APPEND The zone append feature uses the `addr` field of `struct ublksrv_io_cmd` to communicate ALBA back to the kernel. Therefore ublk must be used with the user copy feature (UBLK_F_USER_COPY) for zoned storage support to be available. Without this feature, ublk will not allow zoned storage support. Signed-off-by: Andreas Hindborg Reviewed-by: Ming Lei Tested-by: Ming Lei Link: https://lore.kernel.org/r/20230804114610.179530-4-nmi@metaspace.dk Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 331 ++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/ublk_cmd.h | 63 ++++++-- 2 files changed, 370 insertions(+), 24 deletions(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 0e3847579610..b60394fe7be6 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -56,16 +56,21 @@ | UBLK_F_USER_RECOVERY_REISSUE \ | UBLK_F_UNPRIVILEGED_DEV \ | UBLK_F_CMD_IOCTL_ENCODE \ - | UBLK_F_USER_COPY) + | UBLK_F_USER_COPY \ + | UBLK_F_ZONED) /* All UBLK_PARAM_TYPE_* should be included here */ -#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ - UBLK_PARAM_TYPE_DISCARD | UBLK_PARAM_TYPE_DEVT) +#define UBLK_PARAM_TYPE_ALL \ + (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD | \ + UBLK_PARAM_TYPE_DEVT | UBLK_PARAM_TYPE_ZONED) struct ublk_rq_data { struct llist_node node; struct kref ref; + __u64 sector; + __u32 operation; + __u32 nr_zones; }; struct ublk_uring_cmd_pdu { @@ -185,11 +190,263 @@ struct ublk_params_header { __u32 types; }; +static inline unsigned int ublk_req_build_flags(struct request *req); +static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq, + int tag); + static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub) { return ub->dev_info.flags & UBLK_F_USER_COPY; } +static inline bool ublk_dev_is_zoned(const struct ublk_device *ub) +{ + return ub->dev_info.flags & UBLK_F_ZONED; +} + +static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq) +{ + return ubq->flags & UBLK_F_ZONED; +} + +#ifdef CONFIG_BLK_DEV_ZONED + +static int ublk_get_nr_zones(const struct ublk_device *ub) +{ + const struct ublk_param_basic *p = &ub->params.basic; + + /* Zone size is a power of 2 */ + return p->dev_sectors >> ilog2(p->chunk_sectors); +} + +static int ublk_revalidate_disk_zones(struct ublk_device *ub) +{ + return blk_revalidate_disk_zones(ub->ub_disk, NULL); +} + +static int ublk_dev_param_zoned_validate(const struct ublk_device *ub) +{ + const struct ublk_param_zoned *p = &ub->params.zoned; + int nr_zones; + + if (!ublk_dev_is_zoned(ub)) + return -EINVAL; + + if (!p->max_zone_append_sectors) + return -EINVAL; + + nr_zones = ublk_get_nr_zones(ub); + + if (p->max_active_zones > nr_zones) + return -EINVAL; + + if (p->max_open_zones > nr_zones) + return -EINVAL; + + return 0; +} + +static int ublk_dev_param_zoned_apply(struct ublk_device *ub) +{ + const struct ublk_param_zoned *p = &ub->params.zoned; + + disk_set_zoned(ub->ub_disk, BLK_ZONED_HM); + blk_queue_required_elevator_features(ub->ub_disk->queue, + ELEVATOR_F_ZBD_SEQ_WRITE); + disk_set_max_active_zones(ub->ub_disk, p->max_active_zones); + disk_set_max_open_zones(ub->ub_disk, p->max_open_zones); + blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors); + + ub->ub_disk->nr_zones = ublk_get_nr_zones(ub); + + return 0; +} + +/* Based on virtblk_alloc_report_buffer */ +static void *ublk_alloc_report_buffer(struct ublk_device *ublk, + unsigned int nr_zones, size_t *buflen) +{ + struct request_queue *q = ublk->ub_disk->queue; + size_t bufsize; + void *buf; + + nr_zones = min_t(unsigned int, nr_zones, + ublk->ub_disk->nr_zones); + + bufsize = nr_zones * sizeof(struct blk_zone); + bufsize = + min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); + + while (bufsize >= sizeof(struct blk_zone)) { + buf = kvmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); + if (buf) { + *buflen = bufsize; + return buf; + } + bufsize >>= 1; + } + + *buflen = 0; + return NULL; +} + +static int ublk_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) +{ + struct ublk_device *ub = disk->private_data; + unsigned int zone_size_sectors = disk->queue->limits.chunk_sectors; + unsigned int first_zone = sector >> ilog2(zone_size_sectors); + unsigned int done_zones = 0; + unsigned int max_zones_per_request; + int ret; + struct blk_zone *buffer; + size_t buffer_length; + + nr_zones = min_t(unsigned int, ub->ub_disk->nr_zones - first_zone, + nr_zones); + + buffer = ublk_alloc_report_buffer(ub, nr_zones, &buffer_length); + if (!buffer) + return -ENOMEM; + + max_zones_per_request = buffer_length / sizeof(struct blk_zone); + + while (done_zones < nr_zones) { + unsigned int remaining_zones = nr_zones - done_zones; + unsigned int zones_in_request = + min_t(unsigned int, remaining_zones, max_zones_per_request); + struct request *req; + struct ublk_rq_data *pdu; + blk_status_t status; + + memset(buffer, 0, buffer_length); + + req = blk_mq_alloc_request(disk->queue, REQ_OP_DRV_IN, 0); + if (IS_ERR(req)) { + ret = PTR_ERR(req); + goto out; + } + + pdu = blk_mq_rq_to_pdu(req); + pdu->operation = UBLK_IO_OP_REPORT_ZONES; + pdu->sector = sector; + pdu->nr_zones = zones_in_request; + + ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length, + GFP_KERNEL); + if (ret) { + blk_mq_free_request(req); + goto out; + } + + status = blk_execute_rq(req, 0); + ret = blk_status_to_errno(status); + blk_mq_free_request(req); + if (ret) + goto out; + + for (unsigned int i = 0; i < zones_in_request; i++) { + struct blk_zone *zone = buffer + i; + + /* A zero length zone means no more zones in this response */ + if (!zone->len) + break; + + ret = cb(zone, i, data); + if (ret) + goto out; + + done_zones++; + sector += zone_size_sectors; + + } + } + + ret = done_zones; + +out: + kvfree(buffer); + return ret; +} + +static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, + struct request *req) +{ + struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag); + struct ublk_io *io = &ubq->ios[req->tag]; + struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req); + u32 ublk_op; + + switch (req_op(req)) { + case REQ_OP_ZONE_OPEN: + ublk_op = UBLK_IO_OP_ZONE_OPEN; + break; + case REQ_OP_ZONE_CLOSE: + ublk_op = UBLK_IO_OP_ZONE_CLOSE; + break; + case REQ_OP_ZONE_FINISH: + ublk_op = UBLK_IO_OP_ZONE_FINISH; + break; + case REQ_OP_ZONE_RESET: + ublk_op = UBLK_IO_OP_ZONE_RESET; + break; + case REQ_OP_ZONE_APPEND: + ublk_op = UBLK_IO_OP_ZONE_APPEND; + break; + case REQ_OP_DRV_IN: + ublk_op = pdu->operation; + switch (ublk_op) { + case UBLK_IO_OP_REPORT_ZONES: + iod->op_flags = ublk_op | ublk_req_build_flags(req); + iod->nr_zones = pdu->nr_zones; + iod->start_sector = pdu->sector; + return BLK_STS_OK; + default: + return BLK_STS_IOERR; + } + case REQ_OP_ZONE_RESET_ALL: + case REQ_OP_DRV_OUT: + /* We do not support reset_all and drv_out */ + return BLK_STS_NOTSUPP; + default: + return BLK_STS_IOERR; + } + + iod->op_flags = ublk_op | ublk_req_build_flags(req); + iod->nr_sectors = blk_rq_sectors(req); + iod->start_sector = blk_rq_pos(req); + iod->addr = io->addr; + + return BLK_STS_OK; +} + +#else + +#define ublk_report_zones (NULL) + +static int ublk_dev_param_zoned_validate(const struct ublk_device *ub) +{ + return -EOPNOTSUPP; +} + +static int ublk_dev_param_zoned_apply(struct ublk_device *ub) +{ + return -EOPNOTSUPP; +} + +static int ublk_revalidate_disk_zones(struct ublk_device *ub) +{ + return 0; +} + +static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, + struct request *req) +{ + return -EOPNOTSUPP; +} + +#endif + static inline void __ublk_complete_rq(struct request *req); static void ublk_complete_rq(struct kref *ref); @@ -286,6 +543,9 @@ static int ublk_validate_params(const struct ublk_device *ub) if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9)) return -EINVAL; + + if (ublk_dev_is_zoned(ub) && !p->chunk_sectors) + return -EINVAL; } else return -EINVAL; @@ -304,6 +564,11 @@ static int ublk_validate_params(const struct ublk_device *ub) if (ub->params.types & UBLK_PARAM_TYPE_DEVT) return -EINVAL; + if (ub->params.types & UBLK_PARAM_TYPE_ZONED) + return ublk_dev_param_zoned_validate(ub); + else if (ublk_dev_is_zoned(ub)) + return -EINVAL; + return 0; } @@ -317,6 +582,9 @@ static int ublk_apply_params(struct ublk_device *ub) if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) ublk_dev_param_discard_apply(ub); + if (ub->params.types & UBLK_PARAM_TYPE_ZONED) + return ublk_dev_param_zoned_apply(ub); + return 0; } @@ -487,6 +755,7 @@ static const struct block_device_operations ub_fops = { .owner = THIS_MODULE, .open = ublk_open, .free_disk = ublk_free_disk, + .report_zones = ublk_report_zones, }; #define UBLK_MAX_PIN_PAGES 32 @@ -601,7 +870,8 @@ static inline bool ublk_need_map_req(const struct request *req) static inline bool ublk_need_unmap_req(const struct request *req) { - return ublk_rq_has_data(req) && req_op(req) == REQ_OP_READ; + return ublk_rq_has_data(req) && + (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN); } static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, @@ -685,8 +955,13 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req) { struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag); struct ublk_io *io = &ubq->ios[req->tag]; + enum req_op op = req_op(req); u32 ublk_op; + if (!ublk_queue_is_zoned(ubq) && + (op_is_zone_mgmt(op) || op == REQ_OP_ZONE_APPEND)) + return -EIO; + switch (req_op(req)) { case REQ_OP_READ: ublk_op = UBLK_IO_OP_READ; @@ -704,6 +979,8 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req) ublk_op = UBLK_IO_OP_WRITE_ZEROES; break; default: + if (ublk_queue_is_zoned(ubq)) + return ublk_setup_iod_zoned(ubq, req); return BLK_STS_IOERR; } @@ -756,7 +1033,8 @@ static inline void __ublk_complete_rq(struct request *req) * * Both the two needn't unmap. */ - if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE) + if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE && + req_op(req) != REQ_OP_DRV_IN) goto exit; /* for READ request, writing data in iod->addr to rq buffers */ @@ -1120,6 +1398,9 @@ static void ublk_commit_completion(struct ublk_device *ub, /* find the io request and complete */ req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag); + if (req_op(req) == REQ_OP_ZONE_APPEND) + req->__sector = ub_cmd->zone_append_lba; + if (req && likely(!blk_should_fake_timeout(req->q))) ublk_put_req_ref(ubq, req); } @@ -1468,8 +1749,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) goto out; - } else if (ub_cmd->addr) { - /* User copy requires addr to be unset */ + } else if (req_op(req) != REQ_OP_ZONE_APPEND && ub_cmd->addr) { + /* + * User copy requires addr to be unset when command is + * not zone append + */ ret = -EINVAL; goto out; } @@ -1546,11 +1830,14 @@ 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) + if ((req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_DRV_IN) && + ubuf_dir == ITER_SOURCE) return true; /* copy request pages to ubuf */ - if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST) + if ((req_op(req) == REQ_OP_WRITE || + req_op(req) == REQ_OP_ZONE_APPEND) && + ubuf_dir == ITER_DEST) return true; return false; @@ -1889,17 +2176,24 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) get_device(&ub->cdev_dev); ub->dev_info.state = UBLK_S_DEV_LIVE; + + if (ublk_dev_is_zoned(ub)) { + ret = ublk_revalidate_disk_zones(ub); + if (ret) + goto out_put_cdev; + } + ret = add_disk(disk); + if (ret) + goto out_put_cdev; + + set_bit(UB_STATE_USED, &ub->state); + +out_put_cdev: if (ret) { - /* - * Has to drop the reference since ->free_disk won't be - * called in case of add_disk failure. - */ ub->dev_info.state = UBLK_S_DEV_DEAD; ublk_put_device(ub); - goto out_put_disk; } - set_bit(UB_STATE_USED, &ub->state); out_put_disk: if (ret) put_disk(disk); @@ -2049,6 +2343,13 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) if (ublk_dev_is_user_copy(ub)) ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; + /* Zoned storage support requires user copy feature */ + if (ublk_dev_is_zoned(ub) && + (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) { + ret = -EINVAL; + goto out_free_dev_number; + } + /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 4b8558db90e1..2685e53e4752 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -176,6 +176,12 @@ /* Copy between request and user buffer by pread()/pwrite() */ #define UBLK_F_USER_COPY (1UL << 7) +/* + * User space sets this flag when setting up the device to request zoned storage support. Kernel may + * deny the request by returning an error. + */ +#define UBLK_F_ZONED (1ULL << 8) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -232,9 +238,26 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_OP_READ 0 #define UBLK_IO_OP_WRITE 1 #define UBLK_IO_OP_FLUSH 2 -#define UBLK_IO_OP_DISCARD 3 -#define UBLK_IO_OP_WRITE_SAME 4 -#define UBLK_IO_OP_WRITE_ZEROES 5 +#define UBLK_IO_OP_DISCARD 3 +#define UBLK_IO_OP_WRITE_SAME 4 +#define UBLK_IO_OP_WRITE_ZEROES 5 +#define UBLK_IO_OP_ZONE_OPEN 10 +#define UBLK_IO_OP_ZONE_CLOSE 11 +#define UBLK_IO_OP_ZONE_FINISH 12 +#define UBLK_IO_OP_ZONE_APPEND 13 +#define UBLK_IO_OP_ZONE_RESET 15 +/* + * Construct a zone report. The report request is carried in `struct + * ublksrv_io_desc`. The `start_sector` field must be the first sector of a zone + * and shall indicate the first zone of the report. The `nr_zones` shall + * indicate how many zones should be reported at most. The report shall be + * delivered as a `struct blk_zone` array. To report fewer zones than requested, + * zero the last entry of the returned array. + * + * Related definitions(blk_zone, blk_zone_cond, blk_zone_type, ...) in + * include/uapi/linux/blkzoned.h are part of ublk UAPI. + */ +#define UBLK_IO_OP_REPORT_ZONES 18 #define UBLK_IO_F_FAILFAST_DEV (1U << 8) #define UBLK_IO_F_FAILFAST_TRANSPORT (1U << 9) @@ -255,7 +278,10 @@ struct ublksrv_io_desc { /* op: bit 0-7, flags: bit 8-31 */ __u32 op_flags; - __u32 nr_sectors; + union { + __u32 nr_sectors; + __u32 nr_zones; /* for UBLK_IO_OP_REPORT_ZONES */ + }; /* start sector for this io */ __u64 start_sector; @@ -284,11 +310,21 @@ struct ublksrv_io_cmd { /* io result, it is valid for COMMIT* command only */ __s32 result; - /* - * userspace buffer address in ublksrv daemon process, valid for - * FETCH* command only - */ - __u64 addr; + union { + /* + * userspace buffer address in ublksrv daemon process, valid for + * FETCH* command only + * + * `addr` should not be used when UBLK_F_USER_COPY is enabled, + * because userspace handles data copy by pread()/pwrite() over + * /dev/ublkcN. But in case of UBLK_F_ZONED, this union is + * re-used to pass back the allocated LBA for + * UBLK_IO_OP_ZONE_APPEND which actually depends on + * UBLK_F_USER_COPY + */ + __u64 addr; + __u64 zone_append_lba; + }; }; struct ublk_param_basic { @@ -331,6 +367,13 @@ struct ublk_param_devt { __u32 disk_minor; }; +struct ublk_param_zoned { + __u32 max_open_zones; + __u32 max_active_zones; + __u32 max_zone_append_sectors; + __u8 reserved[20]; +}; + struct ublk_params { /* * Total length of parameters, userspace has to set 'len' for both @@ -342,11 +385,13 @@ struct ublk_params { #define UBLK_PARAM_TYPE_BASIC (1 << 0) #define UBLK_PARAM_TYPE_DISCARD (1 << 1) #define UBLK_PARAM_TYPE_DEVT (1 << 2) +#define UBLK_PARAM_TYPE_ZONED (1 << 3) __u32 types; /* types of parameter included */ struct ublk_param_basic basic; struct ublk_param_discard discard; struct ublk_param_devt devt; + struct ublk_param_zoned zoned; }; #endif -- cgit v1.2.3 From c8659bbb15cd42577a9b16a23b527436b028c8b2 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 10 Aug 2023 16:48:36 +0800 Subject: ublk: Fix signedness bug returning warning There are two warnings reported by smatch: drivers/block/ublk_drv.c:445 ublk_setup_iod_zoned() warn: signedness bug returning '(-95)' drivers/block/ublk_drv.c:963 ublk_setup_iod() warn: signedness bug returning '(-5)' The type of "blk_status_t" is either be a u32 or u8, but this two functions return a negative value when not supported or failed. Use the error code of the blk module to fix these warnings. Fixes: 29802d7ca33b ("ublk: enable zoned storage support") Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202308100201.TCRhgdvN-lkp@intel.com/ Signed-off-by: Li Zetao Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20230810084836.3535322-1-lizetao1@huawei.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index b60394fe7be6..109a5b17537d 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -442,7 +442,7 @@ static int ublk_revalidate_disk_zones(struct ublk_device *ub) static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, struct request *req) { - return -EOPNOTSUPP; + return BLK_STS_NOTSUPP; } #endif @@ -960,7 +960,7 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req) if (!ublk_queue_is_zoned(ubq) && (op_is_zone_mgmt(op) || op == REQ_OP_ZONE_APPEND)) - return -EIO; + return BLK_STS_IOERR; switch (req_op(req)) { case REQ_OP_READ: -- cgit v1.2.3 From e24721e441a7c640e4e7b2b63c23c06d9a750880 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 11 Aug 2023 21:52:16 +0800 Subject: ublk: fix 'warn: variable dereferenced before check 'req'' from Smatch The added check of 'req_op(req) == REQ_OP_ZONE_APPEND' should have been done after the request is confirmed as valid. Actually here, the request should always been true, so add one WARN_ON_ONCE(!req), meantime move the zone_append check after checking the request. Cc: Andreas Hindborg Reported-by: Dan Carpenter Fixes: 29802d7ca33b ("ublk: enable zoned storage support") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230811135216.420404-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 109a5b17537d..e85e075b5bce 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1397,11 +1397,13 @@ static void ublk_commit_completion(struct ublk_device *ub, /* find the io request and complete */ req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag); + if (WARN_ON_ONCE(unlikely(!req))) + return; if (req_op(req) == REQ_OP_ZONE_APPEND) req->__sector = ub_cmd->zone_append_lba; - if (req && likely(!blk_should_fake_timeout(req->q))) + if (likely(!blk_should_fake_timeout(req->q))) ublk_put_req_ref(ubq, req); } -- cgit v1.2.3 From 66a6a5d0ec852eaced589da066376e69397cd71e Mon Sep 17 00:00:00 2001 From: Ruan Jinjie Date: Tue, 15 Aug 2023 19:48:14 +0800 Subject: ublk: Switch to memdup_user_nul() helper Use memdup_user_nul() helper instead of open-coding to simplify the code. Signed-off-by: Ruan Jinjie Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20230815114815.1551171-1-ruanjinjie@huawei.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index e85e075b5bce..6ecd728ee5ce 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2742,14 +2742,9 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, if (header->len < header->dev_path_len) return -EINVAL; - dev_path = kmalloc(header->dev_path_len + 1, GFP_KERNEL); - if (!dev_path) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(dev_path, argp, header->dev_path_len)) - goto exit; - dev_path[header->dev_path_len] = 0; + dev_path = memdup_user_nul(argp, header->dev_path_len); + if (IS_ERR(dev_path)) + return PTR_ERR(dev_path); ret = -EINVAL; switch (_IOC_NR(cmd->cmd_op)) { -- cgit v1.2.3 From 851e06297f20bbd85c93bbf09469f2150d1db218 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 10 Aug 2023 20:43:26 +0800 Subject: ublk: zoned: support REQ_OP_ZONE_RESET_ALL There isn't any reason to not support REQ_OP_ZONE_RESET_ALL given everything is actually handled in userspace, not mention it is pretty easy to support RESET_ALL. So enable REQ_OP_ZONE_RESET_ALL and let userspace handle it. Verified by 'tools/zbc_reset_zone -all /dev/ublkb0' in libzbc[1] with libublk-rs based ublk-zoned target prototype[2], follows command line for creating ublk-zoned: cargo run --example zoned -- add -1 1024 # add $dev_id $DEV_SIZE [1] https://github.com/westerndigitalcorporation/libzbc [2] https://github.com/ming1/libublk-rs/tree/zoned.v2 Cc: Niklas Cassel Cc: Damien Le Moal Cc: Andreas Hindborg Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230810124326.321472-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 7 +++++-- include/uapi/linux/ublk_cmd.h | 1 + 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/block/ublk_drv.c') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6ecd728ee5ce..2d9cb59f8027 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -251,6 +251,7 @@ static int ublk_dev_param_zoned_apply(struct ublk_device *ub) const struct ublk_param_zoned *p = &ub->params.zoned; disk_set_zoned(ub->ub_disk, BLK_ZONED_HM); + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue); blk_queue_required_elevator_features(ub->ub_disk->queue, ELEVATOR_F_ZBD_SEQ_WRITE); disk_set_max_active_zones(ub->ub_disk, p->max_active_zones); @@ -393,6 +394,9 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, case REQ_OP_ZONE_APPEND: ublk_op = UBLK_IO_OP_ZONE_APPEND; break; + case REQ_OP_ZONE_RESET_ALL: + ublk_op = UBLK_IO_OP_ZONE_RESET_ALL; + break; case REQ_OP_DRV_IN: ublk_op = pdu->operation; switch (ublk_op) { @@ -404,9 +408,8 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, default: return BLK_STS_IOERR; } - case REQ_OP_ZONE_RESET_ALL: case REQ_OP_DRV_OUT: - /* We do not support reset_all and drv_out */ + /* We do not support drv_out */ return BLK_STS_NOTSUPP; default: return BLK_STS_IOERR; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 2685e53e4752..b9cfc5c96268 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -245,6 +245,7 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_OP_ZONE_CLOSE 11 #define UBLK_IO_OP_ZONE_FINISH 12 #define UBLK_IO_OP_ZONE_APPEND 13 +#define UBLK_IO_OP_ZONE_RESET_ALL 14 #define UBLK_IO_OP_ZONE_RESET 15 /* * Construct a zone report. The report request is carried in `struct -- cgit v1.2.3