On Mon, Sep 19, 2016 at 4:27 PM, Damien Le Moal <damien.lemoal@xxxxxxxx> wrote:
> From: Shaun Tancheff <shaun.tancheff@xxxxxxxxxxx>
>
> Adds the new BLKUPDATEZONES, BLKREPORTZONE, BLKRESETZONE,
> BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctls.
>
> BLKREPORTZONE implementation uses the device queue zone RB-tree by
> default and no actual command is issued to the device. If the
> application needs access to the untracked zone attributes (non-seq
> flag or reset recommended flag, offline or read-only zone condition,
> etc), BLKUPDATEZONES must be issued first to force an update of the
> cached zone information.
>
> Changelog (Damien):
> * Simplified blkzone descriptor (removed bit-fields and use CPU
> endianness)
> * Changed report ioctl to operate on single zone instead of an
> array of blkzone structures.
I think something with this degree of changes from what
I posted should not include my signed-off-by.
I also really don't like forcing the reply to be a single zone. I
think the user should be able to ask for as many or as few as
they would like.
> Signed-off-by: Shaun Tancheff <shaun.tancheff@xxxxxxxxxxx>
> Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxxx>
> ---
> block/blk-zoned.c | 115 ++++++++++++++++++++++++++++++++++++++++++
> block/ioctl.c | 8 +++
> include/linux/blkdev.h | 7 +++
> include/uapi/linux/Kbuild | 1 +
> include/uapi/linux/blkzoned.h | 91 +++++++++++++++++++++++++++++++++
> include/uapi/linux/fs.h | 1 +
> 6 files changed, 223 insertions(+)
> create mode 100644 include/uapi/linux/blkzoned.h
>
> diff --git a/block/blk-zoned.c b/block/blk-zoned.c
> index a107940..71205c8 100644
> --- a/block/blk-zoned.c
> +++ b/block/blk-zoned.c
> @@ -12,6 +12,7 @@
> #include <linux/module.h>
> #include <linux/rbtree.h>
> #include <linux/blkdev.h>
> +#include <linux/blkzoned.h>
>
> void blk_init_zones(struct request_queue *q)
> {
> @@ -336,3 +337,117 @@ int blkdev_finish_zone(struct block_device *bdev,
> return blkdev_issue_zone_action(bdev, sector, REQ_OP_ZONE_FINISH,
> gfp_mask);
> }
> +
> +static int blkdev_report_zone_ioctl(struct block_device *bdev,
> + void __user *argp)
> +{
> + struct blk_zone *zone;
> + struct blkzone z;
> +
> + if (copy_from_user(&z, argp, sizeof(struct blkzone)))
> + return -EFAULT;
> +
> + zone = blk_lookup_zone(bdev_get_queue(bdev), z.start);
> + if (!zone)
> + return -EINVAL;
> +
> + memset(&z, 0, sizeof(struct blkzone));
> +
> + blk_lock_zone(zone);
> +
> + blk_wait_for_zone_update(zone);
> +
> + z.len = zone->len;
> + z.start = zone->start;
> + z.wp = zone->wp;
> + z.type = zone->type;
> + z.cond = zone->cond;
> + z.non_seq = zone->non_seq;
> + z.reset = zone->reset;
> +
> + blk_unlock_zone(zone);
> +
> + if (copy_to_user(argp, &z, sizeof(struct blkzone)))
> + return -EFAULT;
> +
> + return 0;
> +}
> +
> +static int blkdev_zone_action_ioctl(struct block_device *bdev,
> + unsigned cmd, void __user *argp)
> +{
> + unsigned int op;
> + u64 sector;
> +
> + if (get_user(sector, (u64 __user *)argp))
> + return -EFAULT;
> +
> + switch (cmd) {
> + case BLKRESETZONE:
> + op = REQ_OP_ZONE_RESET;
> + break;
> + case BLKOPENZONE:
> + op = REQ_OP_ZONE_OPEN;
> + break;
> + case BLKCLOSEZONE:
> + op = REQ_OP_ZONE_CLOSE;
> + break;
> + case BLKFINISHZONE:
> + op = REQ_OP_ZONE_FINISH;
> + break;
> + }
> +
> + return blkdev_issue_zone_action(bdev, sector, op, GFP_KERNEL);
> +}
> +
> +/**
> + * Called from blkdev_ioctl.
> + */
> +int blkdev_zone_ioctl(struct block_device *bdev, fmode_t mode,
> + unsigned cmd, unsigned long arg)
> +{
> + void __user *argp = (void __user *)arg;
> + struct request_queue *q;
> + int ret;
> +
> + if (!argp)
> + return -EINVAL;
> +
> + q = bdev_get_queue(bdev);
> + if (!q)
> + return -ENXIO;
> +
> + if (!blk_queue_zoned(q))
> + return -ENOTTY;
> +
> + if (!capable(CAP_SYS_ADMIN))
> + return -EACCES;
> +
> + switch (cmd) {
> + case BLKREPORTZONE:
> + ret = blkdev_report_zone_ioctl(bdev, argp);
> + break;
> + case BLKUPDATEZONES:
> + if (!(mode & FMODE_WRITE)) {
> + ret = -EBADF;
> + break;
> + }
> + ret = blkdev_update_zones(bdev, GFP_KERNEL);
> + break;
> + case BLKRESETZONE:
> + case BLKOPENZONE:
> + case BLKCLOSEZONE:
> + case BLKFINISHZONE:
> + if (!(mode & FMODE_WRITE)) {
> + ret = -EBADF;
> + break;
> + }
> + ret = blkdev_zone_action_ioctl(bdev, cmd, argp);
> + break;
> + default:
> + ret = -ENOTTY;
> + break;
> + }
> +
> + return ret;
> +}
> diff --git a/block/ioctl.c b/block/ioctl.c
> index ed2397f..f09679a 100644
> --- a/block/ioctl.c
> +++ b/block/ioctl.c
> @@ -3,6 +3,7 @@
> #include <linux/export.h>
> #include <linux/gfp.h>
> #include <linux/blkpg.h>
> +#include <linux/blkzoned.h>
> #include <linux/hdreg.h>
> #include <linux/backing-dev.h>
> #include <linux/fs.h>
> @@ -513,6 +514,13 @@ 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 BLKUPDATEZONES:
> + case BLKREPORTZONE:
> + case BLKRESETZONE:
> + case BLKOPENZONE:
> + case BLKCLOSEZONE:
> + case BLKFINISHZONE:
> + return blkdev_zone_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 a85f95b..0299d41 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -405,9 +405,16 @@ extern int blkdev_reset_zone(struct block_device *, sector_t, gfp_t);
> extern int blkdev_open_zone(struct block_device *, sector_t, gfp_t);
> extern int blkdev_close_zone(struct block_device *, sector_t, gfp_t);
> extern int blkdev_finish_zone(struct block_device *, sector_t, gfp_t);
> +extern int blkdev_zone_ioctl(struct block_device *, fmode_t, unsigned int,
> + unsigned long);
> #else /* CONFIG_BLK_DEV_ZONED */
> static inline void blk_init_zones(struct request_queue *q) { };
> static inline void blk_drop_zones(struct request_queue *q) { };
> +static inline int blkdev_zone_ioctl(struct block_device *bdev, fmode_t mode,
> + unsigned cmd, unsigned long arg)
> +{
> + return -ENOTTY;
> +}
> #endif /* CONFIG_BLK_DEV_ZONED */
>
> struct request_queue {
> diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
> index 185f8ea..a2a7522 100644
> --- a/include/uapi/linux/Kbuild
> +++ b/include/uapi/linux/Kbuild
> @@ -70,6 +70,7 @@ header-y += bfs_fs.h
> header-y += binfmts.h
> header-y += blkpg.h
> header-y += blktrace_api.h
> +header-y += blkzoned.h
> header-y += bpf_common.h
> header-y += bpf.h
> header-y += bpqether.h
> diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
> new file mode 100644
> index 0000000..23a2702
> --- /dev/null
> +++ b/include/uapi/linux/blkzoned.h
> @@ -0,0 +1,91 @@
> +/*
> + * Zoned block devices handling.
> + *
> + * Copyright (C) 2015 Seagate Technology PLC
> + *
> + * Written by: Shaun Tancheff <shaun.tancheff@xxxxxxxxxxx>
> + *
> + * Modified by: Damien Le Moal <damien.lemoal@xxxxxxxx>
> + * Copyright (C) 2016 Western Digital
> + *
> + * This file is licensed under the terms of the GNU General Public
> + * License version 2. This program is licensed "as is" without any
> + * warranty of any kind, whether express or implied.
> + */
> +#ifndef _UAPI_BLKZONED_H
> +#define _UAPI_BLKZONED_H
> +
> +#include <linux/types.h>
> +#include <linux/ioctl.h>
> +
> +/*
> + * Zone type.
> + */
> +enum blkzone_type {
> + BLKZONE_TYPE_UNKNOWN,
> + BLKZONE_TYPE_CONVENTIONAL,
> + BLKZONE_TYPE_SEQWRITE_REQ,
> + BLKZONE_TYPE_SEQWRITE_PREF,
> +};
> +
> +/*
> + * Zone condition.
> + */
> +enum blkzone_cond {
> + BLKZONE_COND_NO_WP,
> + BLKZONE_COND_EMPTY,
> + BLKZONE_COND_IMP_OPEN,
> + BLKZONE_COND_EXP_OPEN,
> + BLKZONE_COND_CLOSED,
> + BLKZONE_COND_READONLY = 0xd,
> + BLKZONE_COND_FULL,
> + BLKZONE_COND_OFFLINE,
> +};
> +
> +/*
> + * Zone descriptor for BLKREPORTZONE.
> + * start, len and wp use the regulare 512 B sector unit,
> + * regardless of the device logical block size. The overall
> + * structure size is 64 B to match the ZBC/ZAC defined zone descriptor
> + * and allow support for future additional zone information.
> + */
> +struct blkzone {
> + __u64 start; /* Zone start sector */
> + __u64 len; /* Zone length in number of sectors */
> + __u64 wp; /* Zone write pointer position */
> + __u8 type; /* Zone type */
> + __u8 cond; /* Zone condition */
> + __u8 non_seq; /* Non-sequential write resources active */
> + __u8 reset; /* Reset write pointer recommended */
> + __u8 reserved[36];
> +};
> +
> +/*
> + * Zone ioctl's:
> + *
> + * BLKUPDATEZONES : Force update of all zones information
> + * BLKREPORTZONE : Get a zone descriptor. Takes a zone descriptor as
> + * argument. The zone to report is the one
> + * containing the sector initially specified in the
> + * descriptor start field.
> + * BLKRESETZONE : Reset the write pointer of the zone containing the
> + * specified sector, or of all written zones if the
> + * sector is ~0ull.
> + * BLKOPENZONE : Explicitely open the zone containing the
> + * specified sector, or all possible zones if the
> + * sector is ~0ull (the drive determines which zone
> + * to open in this case).
> + * BLKCLOSEZONE : Close the zone containing the specified sector, or
> + * all open zones if the sector is ~0ull.
> + * BLKFINISHZONE : Finish the zone (make it full) containing the
> + * specified sector, or all open and closed zones if
> + * the sector is ~0ull.
> + */
> +#define BLKUPDATEZONES _IO(0x12,130)
> +#define BLKREPORTZONE _IOWR(0x12,131,struct blkzone)
> +#define BLKRESETZONE _IOW(0x12,132,unsigned long long)
> +#define BLKOPENZONE _IOW(0x12,133,unsigned long long)
> +#define BLKCLOSEZONE _IOW(0x12,134,unsigned long long)
> +#define BLKFINISHZONE _IOW(0x12,135,unsigned long long)
> +
> +#endif /* _UAPI_BLKZONED_H */
> diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
> index 3b00f7c..1db6d66 100644
> --- a/include/uapi/linux/fs.h
> +++ b/include/uapi/linux/fs.h
> @@ -222,6 +222,7 @@ struct fsxattr {
> #define BLKSECDISCARD _IO(0x12,125)
> #define BLKROTATIONAL _IO(0x12,126)
> #define BLKZEROOUT _IO(0x12,127)
> +/* A jump here: 130-135 are used for zoned block devices (see uapi/linux/blkzoned.h) */
>
> #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
> #define FIBMAP _IO(0x00,1) /* bmap access */
> --
> 2.7.4
>
> Western Digital Corporation (and its subsidiaries) E-mail Confidentiality Notice & Disclaimer:
>
> This e-mail and any files transmitted with it may contain confidential or legally privileged information of WDC and/or its affiliates, and are intended solely for the use of the individual or entity to which they are addressed. If you are not the intended recipient, any disclosure, copying, distribution or any action taken or omitted to be taken in reliance on it, is prohibited. If you have received this e-mail in error, please notify the sender immediately and delete the e-mail in its entirety from your system.
>
--
Shaun Tancheff
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
