From 6a0cb1bc106fc07ce0443303bcdb7f7da5131e5c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 18 Oct 2016 15:40:33 +0900 Subject: block: Implement support for zoned block devices Implement zoned block device zone information reporting and reset. Zone information are reported as struct blk_zone. This implementation does not differentiate between host-aware and host-managed device models and is valid for both. Two functions are provided: blkdev_report_zones for discovering the zone configuration of a zoned block device, and blkdev_reset_zones for resetting the write pointer of sequential zones. The helper function blk_queue_zone_size and bdev_zone_size are also provided for, as the name suggest, obtaining the zone size (in 512B sectors) of the zones of the device. Signed-off-by: Hannes Reinecke [Damien: * Removed the zone cache * Implement report zones operation based on earlier proposal by Shaun Tancheff ] Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- block/blk-zoned.c | 257 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 257 insertions(+) create mode 100644 block/blk-zoned.c (limited to 'block/blk-zoned.c') diff --git a/block/blk-zoned.c b/block/blk-zoned.c new file mode 100644 index 000000000000..1603573f9605 --- /dev/null +++ b/block/blk-zoned.c @@ -0,0 +1,257 @@ +/* + * Zoned block device handling + * + * Copyright (c) 2015, Hannes Reinecke + * Copyright (c) 2015, SUSE Linux GmbH + * + * Copyright (c) 2016, Damien Le Moal + * Copyright (c) 2016, Western Digital + */ + +#include +#include +#include +#include + +static inline sector_t blk_zone_start(struct request_queue *q, + sector_t sector) +{ + sector_t zone_mask = blk_queue_zone_size(q) - 1; + + return sector & ~zone_mask; +} + +/* + * Check that a zone report belongs to the partition. + * If yes, fix its start sector and write pointer, copy it in the + * zone information array and return true. Return false otherwise. + */ +static bool blkdev_report_zone(struct block_device *bdev, + struct blk_zone *rep, + struct blk_zone *zone) +{ + sector_t offset = get_start_sect(bdev); + + if (rep->start < offset) + return false; + + rep->start -= offset; + if (rep->start + rep->len > bdev->bd_part->nr_sects) + return false; + + if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL) + rep->wp = rep->start + rep->len; + else + rep->wp -= offset; + memcpy(zone, rep, sizeof(struct blk_zone)); + + return true; +} + +/** + * blkdev_report_zones - Get zones information + * @bdev: Target block device + * @sector: Sector from which to report zones + * @zones: Array of zone structures where to return the zones information + * @nr_zones: Number of zone structures in the zone array + * @gfp_mask: Memory allocation flags (for bio_alloc) + * + * Description: + * Get zone information starting from the zone containing @sector. + * The number of zone information reported may be less than the number + * requested by @nr_zones. The number of zones actually reported is + * returned in @nr_zones. + */ +int blkdev_report_zones(struct block_device *bdev, + sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct request_queue *q = bdev_get_queue(bdev); + struct blk_zone_report_hdr *hdr; + unsigned int nrz = *nr_zones; + struct page *page; + unsigned int nr_rep; + size_t rep_bytes; + unsigned int nr_pages; + struct bio *bio; + struct bio_vec *bv; + unsigned int i, n, nz; + unsigned int ofst; + void *addr; + int ret = 0; + + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -EOPNOTSUPP; + + if (!nrz) + return 0; + + if (sector > bdev->bd_part->nr_sects) { + *nr_zones = 0; + return 0; + } + + /* + * The zone report has a header. So make room for it in the + * payload. Also make sure that the report fits in a single BIO + * that will not be split down the stack. + */ + rep_bytes = sizeof(struct blk_zone_report_hdr) + + sizeof(struct blk_zone) * nrz; + rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK; + if (rep_bytes > (queue_max_sectors(q) << 9)) + rep_bytes = queue_max_sectors(q) << 9; + + nr_pages = min_t(unsigned int, BIO_MAX_PAGES, + rep_bytes >> PAGE_SHIFT); + nr_pages = min_t(unsigned int, nr_pages, + queue_max_segments(q)); + + bio = bio_alloc(gfp_mask, nr_pages); + if (!bio) + return -ENOMEM; + + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = blk_zone_start(q, sector); + bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0); + + for (i = 0; i < nr_pages; i++) { + page = alloc_page(gfp_mask); + if (!page) { + ret = -ENOMEM; + goto out; + } + if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { + __free_page(page); + break; + } + } + + if (i == 0) + ret = -ENOMEM; + else + ret = submit_bio_wait(bio); + if (ret) + goto out; + + /* + * Process the report result: skip the header and go through the + * reported zones to fixup and fixup the zone information for + * partitions. At the same time, return the zone information into + * the zone array. + */ + n = 0; + nz = 0; + nr_rep = 0; + bio_for_each_segment_all(bv, bio, i) { + + if (!bv->bv_page) + break; + + addr = kmap_atomic(bv->bv_page); + + /* Get header in the first page */ + ofst = 0; + if (!nr_rep) { + hdr = (struct blk_zone_report_hdr *) addr; + nr_rep = hdr->nr_zones; + ofst = sizeof(struct blk_zone_report_hdr); + } + + /* Fixup and report zones */ + while (ofst < bv->bv_len && + n < nr_rep && nz < nrz) { + if (blkdev_report_zone(bdev, addr + ofst, &zones[nz])) + nz++; + ofst += sizeof(struct blk_zone); + n++; + } + + kunmap_atomic(addr); + + if (n >= nr_rep || nz >= nrz) + break; + + } + +out: + bio_for_each_segment_all(bv, bio, i) + __free_page(bv->bv_page); + bio_put(bio); + + if (ret == 0) + *nr_zones = nz; + + return ret; +} +EXPORT_SYMBOL_GPL(blkdev_report_zones); + +/** + * blkdev_reset_zones - Reset zones write pointer + * @bdev: Target block device + * @sector: Start sector of the first zone to reset + * @nr_sectors: Number of sectors, at least the length of one zone + * @gfp_mask: Memory allocation flags (for bio_alloc) + * + * Description: + * Reset the write pointer of the zones contained in the range + * @sector..@sector+@nr_sectors. Specifying the entire disk sector range + * is valid, but the specified range should not contain conventional zones. + */ +int blkdev_reset_zones(struct block_device *bdev, + sector_t sector, sector_t nr_sectors, + gfp_t gfp_mask) +{ + struct request_queue *q = bdev_get_queue(bdev); + sector_t zone_sectors; + sector_t end_sector = sector + nr_sectors; + struct bio *bio; + int ret; + + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -EOPNOTSUPP; + + if (end_sector > bdev->bd_part->nr_sects) + /* Out of range */ + return -EINVAL; + + /* Check alignment (handle eventual smaller last zone) */ + zone_sectors = blk_queue_zone_size(q); + if (sector & (zone_sectors - 1)) + return -EINVAL; + + if ((nr_sectors & (zone_sectors - 1)) && + end_sector != bdev->bd_part->nr_sects) + return -EINVAL; + + while (sector < end_sector) { + + bio = bio_alloc(gfp_mask, 0); + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = bdev; + bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0); + + ret = submit_bio_wait(bio); + bio_put(bio); + + if (ret) + return ret; + + sector += zone_sectors; + + /* This may take a while, so be nice to others */ + cond_resched(); + + } + + return 0; +} +EXPORT_SYMBOL_GPL(blkdev_reset_zones); -- cgit v1.2.3 From 3ed05a987e0f63b21e634101e0b460d32f3581c3 Mon Sep 17 00:00:00 2001 From: Shaun Tancheff Date: Tue, 18 Oct 2016 15:40:35 +0900 Subject: blk-zoned: implement ioctls Adds the new BLKREPORTZONE and BLKRESETZONE ioctls for respectively obtaining the zone configuration of a zoned block device and resetting the write pointer of sequential zones of a zoned block device. The BLKREPORTZONE ioctl maps directly to a single call of the function blkdev_report_zones. The zone information result is passed as an array of struct blk_zone identical to the structure used internally for processing the REQ_OP_ZONE_REPORT operation. The BLKRESETZONE ioctl maps to a single call of the blkdev_reset_zones function. Signed-off-by: Shaun Tancheff Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-zoned.c | 93 +++++++++++++++++++++++++++++++++++++++++++ block/ioctl.c | 4 ++ include/linux/blkdev.h | 21 ++++++++++ include/uapi/linux/blkzoned.h | 40 +++++++++++++++++++ include/uapi/linux/fs.h | 4 ++ 5 files changed, 162 insertions(+) (limited to 'block/blk-zoned.c') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 1603573f9605..667f95d86695 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -255,3 +255,96 @@ int blkdev_reset_zones(struct block_device *bdev, return 0; } EXPORT_SYMBOL_GPL(blkdev_reset_zones); + +/** + * BLKREPORTZONE ioctl processing. + * Called from blkdev_ioctl. + */ +int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct request_queue *q; + struct blk_zone_report rep; + struct blk_zone *zones; + int ret; + + if (!argp) + return -EINVAL; + + q = bdev_get_queue(bdev); + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -ENOTTY; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) + return -EFAULT; + + if (!rep.nr_zones) + return -EINVAL; + + zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL); + if (!zones) + return -ENOMEM; + + ret = blkdev_report_zones(bdev, rep.sector, + zones, &rep.nr_zones, + GFP_KERNEL); + if (ret) + goto out; + + if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) { + ret = -EFAULT; + goto out; + } + + if (rep.nr_zones) { + if (copy_to_user(argp + sizeof(struct blk_zone_report), zones, + sizeof(struct blk_zone) * rep.nr_zones)) + ret = -EFAULT; + } + + out: + kfree(zones); + + return ret; +} + +/** + * BLKRESETZONE ioctl processing. + * Called from blkdev_ioctl. + */ +int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct request_queue *q; + struct blk_zone_range zrange; + + if (!argp) + return -EINVAL; + + q = bdev_get_queue(bdev); + if (!q) + return -ENXIO; + + if (!blk_queue_is_zoned(q)) + return -ENOTTY; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) + return -EFAULT; + + return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); +} diff --git a/block/ioctl.c b/block/ioctl.c index 755119c3c1b9..f856963204f4 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -519,6 +519,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, BLKDEV_DISCARD_SECURE); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); + case BLKREPORTZONE: + return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); + case BLKRESETZONE: + return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg); case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKRAGET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 252043f7cd2c..90097dd8b8ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -316,6 +316,27 @@ extern int blkdev_report_zones(struct block_device *bdev, extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); +extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); + +#else /* CONFIG_BLK_DEV_ZONED */ + +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + +static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) +{ + return -ENOTTY; +} + #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index a3817214b0e0..40d1d7bff537 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -16,6 +16,7 @@ #define _UAPI_BLKZONED_H #include +#include /** * enum blk_zone_type - Types of zones allowed in a zoned device. @@ -100,4 +101,43 @@ struct blk_zone { __u8 reserved[36]; }; +/** + * struct blk_zone_report - BLKREPORTZONE ioctl request/reply + * + * @sector: starting sector of report + * @nr_zones: IN maximum / OUT actual + * @reserved: padding to 16 byte alignment + * @zones: Space to hold @nr_zones @zones entries on reply. + * + * The array of at most @nr_zones must follow this structure in memory. + */ +struct blk_zone_report { + __u64 sector; + __u32 nr_zones; + __u8 reserved[4]; + struct blk_zone zones[0]; +} __packed; + +/** + * struct blk_zone_range - BLKRESETZONE ioctl request + * @sector: starting sector of the first zone to issue reset write pointer + * @nr_sectors: Total number of sectors of 1 or more zones to reset + */ +struct blk_zone_range { + __u64 sector; + __u64 nr_sectors; +}; + +/** + * Zoned block device ioctl's: + * + * @BLKREPORTZONE: Get zone information. Takes a zone report as argument. + * The zone report will start from the zone containing the + * sector specified in the report request structure. + * @BLKRESETZONE: Reset the write pointer of the zones in the specified + * sector range. The sector range must be zone aligned. + */ +#define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) +#define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) + #endif /* _UAPI_BLKZONED_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index acb2b6152ba0..c1d11df07b28 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -225,6 +225,10 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +/* + * A jump here: 130-131 are reserved for zoned block devices + * (see uapi/linux/blkzoned.h) + */ #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 3c4da75814c4b8871116940eb32d3a5243026918 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 21 Oct 2016 17:42:33 +0200 Subject: block: zoned: fix harmless maybe-uninitialized warning The blkdev_report_zones produces a harmless warning when -Wmaybe-uninitialized is set, after gcc gets a little confused about the multiple 'goto' here: block/blk-zoned.c: In function 'blkdev_report_zones': block/blk-zoned.c:188:13: error: 'nz' may be used uninitialized in this function [-Werror=maybe-uninitialized] Moving the assignment to nr_zones makes this a little simpler while also avoiding the warning reliably. I'm removing the extraneous initialization of 'int ret' in the same patch, as that is semi-related and could cause an uninitialized use of that variable to not produce a warning. Fixes: 6a0cb1bc106f ("block: Implement support for zoned block devices") Signed-off-by: Arnd Bergmann Reviewed-by: Shaun Tancheff Reviewed-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'block/blk-zoned.c') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 667f95d86695..472211fa183a 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -80,7 +80,7 @@ int blkdev_report_zones(struct block_device *bdev, unsigned int i, n, nz; unsigned int ofst; void *addr; - int ret = 0; + int ret; if (!q) return -ENXIO; @@ -179,14 +179,12 @@ int blkdev_report_zones(struct block_device *bdev, } + *nr_zones = nz; out: bio_for_each_segment_all(bv, bio, i) __free_page(bv->bv_page); bio_put(bio); - if (ret == 0) - *nr_zones = nz; - return ret; } EXPORT_SYMBOL_GPL(blkdev_report_zones); -- cgit v1.2.3