* [PATCH 1/5] block: cleanup blkdev_ioctl
2015-08-26 16:56 Persistent Reservation API V3 Christoph Hellwig
@ 2015-08-26 16:56 ` Christoph Hellwig
2015-08-26 16:56 ` [PATCH 2/5] block: add an API for Persistent Reservations Christoph Hellwig
` (3 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
Split out helpers for all non-trivial ioctls to make this function simpler,
and also start passing around a pointer version of the argument, as that's
what most ioctl handlers actually need.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/ioctl.c | 227 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..df62b47 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -193,10 +193,20 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
-static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
- uint64_t len, int secure)
+static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
{
- unsigned long flags = 0;
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
if (start & 511)
return -EINVAL;
@@ -207,14 +217,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
- if (secure)
- flags |= BLKDEV_DISCARD_SECURE;
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
-static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
- uint64_t len)
+static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+ unsigned long arg)
{
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
+
if (start & 511)
return -EINVAL;
if (len & 511)
@@ -295,89 +315,115 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}
-/*
- * always keep this in sync with compat_blkdev_ioctl()
- */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
{
- struct gendisk *disk = bdev->bd_disk;
- struct backing_dev_info *bdi;
- loff_t size;
- int ret, n;
- unsigned int max_sectors;
+ int ret;
- switch(cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
- fsync_bdev(bdev);
- invalidate_bdev(bdev);
- return 0;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
- case BLKROSET:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (get_user(n, (int __user *)(arg)))
- return -EFAULT;
- set_device_ro(bdev, n);
- return 0;
+ fsync_bdev(bdev);
+ invalidate_bdev(bdev);
+ return 0;
+}
- case BLKDISCARD:
- case BLKSECDISCARD: {
- uint64_t range[2];
+static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
+{
+ int ret, n;
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (get_user(n, (int __user *)arg))
+ return -EFAULT;
+ set_device_ro(bdev, n);
+ return 0;
+}
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+static int blkdev_getgeo(struct block_device *bdev,
+ struct hd_geometry __user *argp)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct hd_geometry geo;
+ int ret;
- return blk_ioctl_discard(bdev, range[0], range[1],
- cmd == BLKSECDISCARD);
- }
- case BLKZEROOUT: {
- uint64_t range[2];
+ if (!argp)
+ return -EINVAL;
+ if (!disk->fops->getgeo)
+ return -ENOTTY;
+
+ /*
+ * We need to set the startsect first, the driver may
+ * want to override it.
+ */
+ memset(&geo, 0, sizeof(geo));
+ geo.start = get_start_sect(bdev);
+ ret = disk->fops->getgeo(bdev, &geo);
+ if (ret)
+ return ret;
+ if (copy_to_user(argp, &geo, sizeof(geo)))
+ return -EFAULT;
+ return 0;
+}
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+/* set the logical block size */
+static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+ int __user *argp)
+{
+ int ret, n;
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (!argp)
+ return -EINVAL;
+ if (get_user(n, argp))
+ return -EFAULT;
- return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
}
- case HDIO_GETGEO: {
- struct hd_geometry geo;
+ ret = set_blocksize(bdev, n);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
+ return ret;
+}
- if (!arg)
- return -EINVAL;
- if (!disk->fops->getgeo)
- return -ENOTTY;
-
- /*
- * We need to set the startsect first, the driver may
- * want to override it.
- */
- memset(&geo, 0, sizeof(geo));
- geo.start = get_start_sect(bdev);
- ret = disk->fops->getgeo(bdev, &geo);
- if (ret)
- return ret;
- if (copy_to_user((struct hd_geometry __user *)arg, &geo,
- sizeof(geo)))
- return -EFAULT;
- return 0;
- }
+/*
+ * always keep this in sync with compat_blkdev_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+ unsigned long arg)
+{
+ struct backing_dev_info *bdi;
+ void __user *argp = (void __user *)arg;
+ loff_t size;
+ unsigned int max_sectors;
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ return blkdev_flushbuf(bdev, mode, cmd, arg);
+ case BLKROSET:
+ return blkdev_roset(bdev, mode, cmd, arg);
+ case BLKDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg, 0);
+ case BLKSECDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg,
+ BLKDEV_DISCARD_SECURE);
+ case BLKZEROOUT:
+ return blk_ioctl_zeroout(bdev, mode, arg);
+ case HDIO_GETGEO:
+ return blkdev_getgeo(bdev, argp);
case BLKRAGET:
case BLKFRAGET:
if (!arg)
@@ -414,28 +460,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
- /* set the logical block size */
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (!arg)
- return -EINVAL;
- if (get_user(n, (int __user *) arg))
- return -EFAULT;
- if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
- }
- ret = set_blocksize(bdev, n);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
- return ret;
+ return blkdev_bszset(bdev, mode, argp);
case BLKPG:
- ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
- break;
+ return blkpg_ioctl(bdev, argp);
case BLKRRPART:
- ret = blkdev_reread_part(bdev);
- break;
+ return blkdev_reread_part(bdev);
case BLKGETSIZE:
size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
@@ -447,11 +476,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
- ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
- break;
+ return blk_trace_ioctl(bdev, cmd, argp);
default:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2/5] block: add an API for Persistent Reservations
2015-08-26 16:56 Persistent Reservation API V3 Christoph Hellwig
2015-08-26 16:56 ` [PATCH 1/5] block: cleanup blkdev_ioctl Christoph Hellwig
@ 2015-08-26 16:56 ` Christoph Hellwig
2015-08-26 16:56 ` [PATCH 4/5] dm: refactor ioctl handling Christoph Hellwig
` (2 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
This commits adds a driver API and ioctls for controlling Persistent
Reservations s/genericly/generically/ at the block layer. Persistent
Reservations are supported by SCSI and NVMe and allow controlling who gets
access to a device in a shared storage setup.
Note that we add a pr_ops structure to struct block_device_operations
instead of adding the members directly to avoid bloating all instances
of devices that will never support Persistent Reservations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/block/pr.txt | 119 +++++++++++++++++++++++++++++++++++++++++++++
block/ioctl.c | 93 +++++++++++++++++++++++++++++++++++
include/linux/blkdev.h | 2 +
include/linux/pr.h | 18 +++++++
include/uapi/linux/pr.h | 48 ++++++++++++++++++
5 files changed, 280 insertions(+)
create mode 100644 Documentation/block/pr.txt
create mode 100644 include/linux/pr.h
create mode 100644 include/uapi/linux/pr.h
diff --git a/Documentation/block/pr.txt b/Documentation/block/pr.txt
new file mode 100644
index 0000000..d3eb1ca
--- /dev/null
+++ b/Documentation/block/pr.txt
@@ -0,0 +1,119 @@
+
+Block layer support for Persistent Reservations
+===============================================
+
+The Linux kernel supports a user space interface for simplified
+Persistent Reservations which map to block devices that support
+these (like SCSI). Persistent Reservations allow restricting
+access to block devices to specific initiators in a shared storage
+setup.
+
+This document gives a general overview of the support ioctl commands.
+For a more detailed reference please refer the the SCSI Primary
+Commands standard, specifically the section on Reservations and the
+"PERSISTENT RESERVE IN" and "PERSISTENT RESERVE OUT" commands.
+
+All implementations are expected to ensure the reservations survive
+a power loss and cover all connections in a multi path environment.
+These behaviors are optional in SPC but will be automatically applied
+by Linux.
+
+
+The following types of reservations are supported:
+--------------------------------------------------
+
+ - PR_WRITE_EXCLUSIVE
+
+ Only the initiator that owns the reservation can write to the
+ device. Any initiator can read from the device.
+
+ - PR_EXCLUSIVE_ACCESS
+
+ Only the initiator that owns the reservation can access the
+ device.
+
+ - PR_WRITE_EXCLUSIVE_REG_ONLY
+
+ Only initiators with a registered key can write to the device,
+ Any initiator can read from the device.
+
+ - PR_EXCLUSIVE_ACCESS_REG_ONLY
+
+ Only initiators with a registered key can access the device.
+
+ - PR_WRITE_EXCLUSIVE_ALL_REGS
+
+ Only initiators with a registered key can write to the device,
+ Any initiator can read from the device.
+ All initiators with a registered key are considered reservation
+ holders.
+ Please reference the SPC spec on the meaning of a reservation
+ holder if you want to use this type.
+
+ - PR_EXCLUSIVE_ACCESS_ALL_REGS
+
+ Only initiators with a registered key can access the device.
+ All initiators with a registered key are considered reservation
+ holders.
+ Please reference the SPC spec on the meaning of a reservation
+ holder if you want to use this type.
+
+
+The following ioctl are supported:
+----------------------------------
+
+1. IOC_PR_REGISTER
+
+This ioctl command registers a new reservation if the new_key argument
+is non-null. If no existing reservation exists old_key must be zero,
+if an existing reservation should be replaced old_key must contain
+the old reservation key.
+
+If the new_key argument is 0 it unregisters the existing reservation passed
+in old_key.
+
+
+2. IOC_PR_RESERVE
+
+This ioctl command reserves the device and thus restricts access for other
+devices based on the type argument. The key argument must be the existing
+reservation key for the device as acquired by the IOC_PR_REGISTER,
+IOC_PR_REGISTER_IGNORE, IOC_PR_PREEMPT or IOC_PR_PREEMPT_ABORT commands.
+
+
+3. IOC_PR_RELEASE
+
+This ioctl command releases the reservation specified by key and flags
+and thus removes any access restriction implied by it.
+
+
+4. IOC_PR_PREEMPT
+
+This ioctl command releases the existing reservation referred to by
+old_key and replaces it with a a new reservation of type for the
+reservation key new_key.
+
+
+5. IOC_PR_PREEMPT_ABORT
+
+This ioctl command works like IOC_PR_PREEMPT except that it also aborts
+any outstanding command sent over a connection identified by old_key.
+
+6. IOC_PR_CLEAR
+
+This ioctl command unregisters both key and any other reservation key
+registered with the device and drops any existing reservation.
+
+
+Flags
+-----
+
+All the ioctls have a flag field. Currently only one flag is supported:
+
+ - PR_FL_IGNORE_KEY
+
+ Ignore the existing reservation key. This is commonly supported for
+ IOC_PR_REGISTER, and some implementation may support the flag for
+ IOC_PR_RESERVE.
+
+For all unknown flags the kernel will return -EOPNOTSUPP.
diff --git a/block/ioctl.c b/block/ioctl.c
index df62b47..9c83e72 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -7,6 +7,7 @@
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/blktrace_api.h>
+#include <linux/pr.h>
#include <asm/uaccess.h>
static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
@@ -295,6 +296,86 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
*/
EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
+static int blkdev_pr_register(struct block_device *bdev,
+ struct pr_registration __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_registration reg;
+
+ if (!ops || !ops->pr_register)
+ return -EOPNOTSUPP;
+ if (copy_from_user(®, arg, sizeof(reg)))
+ return -EFAULT;
+
+ if (reg.flags & ~PR_FL_IGNORE_KEY)
+ return -EOPNOTSUPP;
+ return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);
+}
+
+static int blkdev_pr_reserve(struct block_device *bdev,
+ struct pr_reservation __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_reservation rsv;
+
+ if (!ops || !ops->pr_reserve)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&rsv, arg, sizeof(rsv)))
+ return -EFAULT;
+
+ if (rsv.flags & ~PR_FL_IGNORE_KEY)
+ return -EOPNOTSUPP;
+ return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);
+}
+
+static int blkdev_pr_release(struct block_device *bdev,
+ struct pr_reservation __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_reservation rsv;
+
+ if (!ops || !ops->pr_release)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&rsv, arg, sizeof(rsv)))
+ return -EFAULT;
+
+ if (rsv.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_release(bdev, rsv.key, rsv.type);
+}
+
+static int blkdev_pr_preempt(struct block_device *bdev,
+ struct pr_preempt __user *arg, bool abort)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_preempt p;
+
+ if (!ops || !ops->pr_preempt)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&p, arg, sizeof(p)))
+ return -EFAULT;
+
+ if (p.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);
+}
+
+static int blkdev_pr_clear(struct block_device *bdev,
+ struct pr_clear __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_clear c;
+
+ if (!ops || !ops->pr_clear)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&c, arg, sizeof(c)))
+ return -EFAULT;
+
+ if (c.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_clear(bdev, c.key);
+}
+
/*
* Is it an unrecognized ioctl? The correct returns are either
* ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a
@@ -477,6 +558,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
return blk_trace_ioctl(bdev, cmd, argp);
+ case IOC_PR_REGISTER:
+ return blkdev_pr_register(bdev, argp);
+ case IOC_PR_RESERVE:
+ return blkdev_pr_reserve(bdev, argp);
+ case IOC_PR_RELEASE:
+ return blkdev_pr_release(bdev, argp);
+ case IOC_PR_PREEMPT:
+ return blkdev_pr_preempt(bdev, argp, false);
+ case IOC_PR_PREEMPT_ABORT:
+ return blkdev_pr_preempt(bdev, argp, true);
+ case IOC_PR_CLEAR:
+ return blkdev_pr_clear(bdev, argp);
default:
return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a622f27..70b185e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -35,6 +35,7 @@ struct sg_io_hdr;
struct bsg_job;
struct blkcg_gq;
struct blk_flush_queue;
+struct pr_ops;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
@@ -1581,6 +1582,7 @@ struct block_device_operations {
/* this callback is with swap_lock and sometimes page table lock held */
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
struct module *owner;
+ const struct pr_ops *pr_ops;
};
extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
diff --git a/include/linux/pr.h b/include/linux/pr.h
new file mode 100644
index 0000000..65c01c1
--- /dev/null
+++ b/include/linux/pr.h
@@ -0,0 +1,18 @@
+#ifndef LINUX_PR_H
+#define LINUX_PR_H
+
+#include <uapi/linux/pr.h>
+
+struct pr_ops {
+ int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags);
+ int (*pr_reserve)(struct block_device *bdev, u64 key,
+ enum pr_type type, u32 flags);
+ int (*pr_release)(struct block_device *bdev, u64 key,
+ enum pr_type type);
+ int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort);
+ int (*pr_clear)(struct block_device *bdev, u64 key);
+};
+
+#endif /* LINUX_PR_H */
diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h
new file mode 100644
index 0000000..57d7c0f
--- /dev/null
+++ b/include/uapi/linux/pr.h
@@ -0,0 +1,48 @@
+#ifndef _UAPI_PR_H
+#define _UAPI_PR_H
+
+enum pr_type {
+ PR_WRITE_EXCLUSIVE = 1,
+ PR_EXCLUSIVE_ACCESS = 2,
+ PR_WRITE_EXCLUSIVE_REG_ONLY = 3,
+ PR_EXCLUSIVE_ACCESS_REG_ONLY = 4,
+ PR_WRITE_EXCLUSIVE_ALL_REGS = 5,
+ PR_EXCLUSIVE_ACCESS_ALL_REGS = 6,
+};
+
+struct pr_reservation {
+ __u64 key;
+ __u32 type;
+ __u32 flags;
+};
+
+struct pr_registration {
+ __u64 old_key;
+ __u64 new_key;
+ __u32 flags;
+ __u32 __pad;
+};
+
+struct pr_preempt {
+ __u64 old_key;
+ __u64 new_key;
+ __u32 type;
+ __u32 flags;
+};
+
+struct pr_clear {
+ __u64 key;
+ __u32 flags;
+ __u32 __pad;
+};
+
+#define PR_FL_IGNORE_KEY (1 << 0) /* ignore existing key */
+
+#define IOC_PR_REGISTER _IOW('p', 200, struct pr_registration)
+#define IOC_PR_RESERVE _IOW('p', 201, struct pr_reservation)
+#define IOC_PR_RELEASE _IOW('p', 202, struct pr_reservation)
+#define IOC_PR_PREEMPT _IOW('p', 203, struct pr_preempt)
+#define IOC_PR_PREEMPT_ABORT _IOW('p', 204, struct pr_preempt)
+#define IOC_PR_CLEAR _IOW('p', 205, struct pr_clear)
+
+#endif /* _UAPI_PR_H */
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 4/5] dm: refactor ioctl handling
2015-08-26 16:56 Persistent Reservation API V3 Christoph Hellwig
2015-08-26 16:56 ` [PATCH 1/5] block: cleanup blkdev_ioctl Christoph Hellwig
2015-08-26 16:56 ` [PATCH 2/5] block: add an API for Persistent Reservations Christoph Hellwig
@ 2015-08-26 16:56 ` Christoph Hellwig
2015-08-26 16:56 ` [PATCH 5/5] dm: add support for passing through persistent reservations Christoph Hellwig
[not found] ` <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
4 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
This moves the call to blkdev_ioctl and the argument checking to core code,
and only leaves a callout to find the block device to operate on it the
targets. This will simplifies the code and will allow us to pass through
ioctl-like command using other methods in the next patch.
Also split out a helper around calling the prepare_ioctl method that will
be reused for persistent reservation handling.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/dm-flakey.c | 16 +++++++-------
drivers/md/dm-linear.c | 14 ++++++------
drivers/md/dm-log-writes.c | 13 ++++++-----
drivers/md/dm-mpath.c | 32 +++++++++++----------------
drivers/md/dm-switch.c | 21 ++++++++----------
drivers/md/dm-verity.c | 15 ++++++-------
drivers/md/dm.c | 50 ++++++++++++++++++++++++++++++++-----------
include/linux/device-mapper.h | 6 +++---
8 files changed, 89 insertions(+), 78 deletions(-)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index afab13b..c177d88 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -371,20 +371,20 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
}
}
-static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long arg)
+static int flakey_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct flakey_c *fc = ti->private;
- struct dm_dev *dev = fc->dev;
- int r = 0;
+
+ *bdev = fc->dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (fc->start ||
- ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return 0;
}
static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
@@ -403,7 +403,7 @@ static struct target_type flakey_target = {
.map = flakey_map,
.end_io = flakey_end_io,
.status = flakey_status,
- .ioctl = flakey_ioctl,
+ .prepare_ioctl = flakey_prepare_ioctl,
.iterate_devices = flakey_iterate_devices,
};
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 7dd5fc8..0986baa 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -113,21 +113,21 @@ static void linear_status(struct dm_target *ti, status_type_t type,
}
}
-static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int linear_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct linear_c *lc = (struct linear_c *) ti->private;
struct dm_dev *dev = lc->dev;
- int r = 0;
+
+ *bdev = dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (lc->start ||
ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ return 1;
+ return 0;
}
static int linear_iterate_devices(struct dm_target *ti,
@@ -146,7 +146,7 @@ static struct target_type linear_target = {
.dtr = linear_dtr,
.map = linear_map,
.status = linear_status,
- .ioctl = linear_ioctl,
+ .prepare_ioctl = linear_prepare_ioctl,
.iterate_devices = linear_iterate_devices,
};
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 316cc3f..bc57ad1 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -709,20 +709,19 @@ static void log_writes_status(struct dm_target *ti, status_type_t type,
}
}
-static int log_writes_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int log_writes_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct log_writes_c *lc = ti->private;
struct dm_dev *dev = lc->dev;
- int r = 0;
+ *bdev = dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ return 1;
+ return 0;
}
static int log_writes_iterate_devices(struct dm_target *ti,
@@ -777,7 +776,7 @@ static struct target_type log_writes_target = {
.map = log_writes_map,
.end_io = normal_end_io,
.status = log_writes_status,
- .ioctl = log_writes_ioctl,
+ .prepare_ioctl = log_writes_prepare_ioctl,
.message = log_writes_message,
.iterate_devices = log_writes_iterate_devices,
.io_hints = log_writes_io_hints,
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index eff7bdd..97cf835 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1548,18 +1548,14 @@ out:
return r;
}
-static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int multipath_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct multipath *m = ti->private;
struct pgpath *pgpath;
- struct block_device *bdev;
- fmode_t mode;
unsigned long flags;
int r;
- bdev = NULL;
- mode = 0;
r = 0;
spin_lock_irqsave(&m->lock, flags);
@@ -1570,26 +1566,17 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
pgpath = m->current_pgpath;
if (pgpath) {
- bdev = pgpath->path.dev->bdev;
- mode = pgpath->path.dev->mode;
+ *bdev = pgpath->path.dev->bdev;
+ *mode = pgpath->path.dev->mode;
}
if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
r = -ENOTCONN;
- else if (!bdev)
+ else if (!*bdev)
r = -EIO;
spin_unlock_irqrestore(&m->lock, flags);
- /*
- * Only pass ioctls through if the device sizes match exactly.
- */
- if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
- int err = scsi_verify_blk_ioctl(NULL, cmd);
- if (err)
- r = err;
- }
-
if (r == -ENOTCONN && !fatal_signal_pending(current)) {
spin_lock_irqsave(&m->lock, flags);
if (!m->current_pg) {
@@ -1602,7 +1589,12 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
dm_table_run_md_queue_async(m->ti->table);
}
- return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ /*
+ * Only pass ioctls through if the device sizes match exactly.
+ */
+ if (!r && ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return r;
}
static int multipath_iterate_devices(struct dm_target *ti,
@@ -1718,7 +1710,7 @@ static struct target_type multipath_target = {
.resume = multipath_resume,
.status = multipath_status,
.message = multipath_message,
- .ioctl = multipath_ioctl,
+ .prepare_ioctl = multipath_prepare_ioctl,
.iterate_devices = multipath_iterate_devices,
.busy = multipath_busy,
};
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index 50fca46..b128575 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -511,27 +511,24 @@ static void switch_status(struct dm_target *ti, status_type_t type,
*
* Passthrough all ioctls to the path for sector 0
*/
-static int switch_ioctl(struct dm_target *ti, unsigned cmd,
- unsigned long arg)
+static int switch_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct switch_ctx *sctx = ti->private;
- struct block_device *bdev;
- fmode_t mode;
unsigned path_nr;
- int r = 0;
path_nr = switch_get_path_nr(sctx, 0);
- bdev = sctx->path_list[path_nr].dmdev->bdev;
- mode = sctx->path_list[path_nr].dmdev->mode;
+ *bdev = sctx->path_list[path_nr].dmdev->bdev;
+ *mode = sctx->path_list[path_nr].dmdev->mode;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (ti->len + sctx->path_list[path_nr].start != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (ti->len + sctx->path_list[path_nr].start !=
+ i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return 0;
}
static int switch_iterate_devices(struct dm_target *ti,
@@ -560,7 +557,7 @@ static struct target_type switch_target = {
.map = switch_map,
.message = switch_message,
.status = switch_status,
- .ioctl = switch_ioctl,
+ .prepare_ioctl = switch_prepare_ioctl,
.iterate_devices = switch_iterate_devices,
};
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index c137dcb..509fa05 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -635,18 +635,17 @@ static void verity_status(struct dm_target *ti, status_type_t type,
}
}
-static int verity_ioctl(struct dm_target *ti, unsigned cmd,
- unsigned long arg)
+static int verity_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct dm_verity *v = ti->private;
- int r = 0;
+
+ *bdev = v->data_dev->bdev;
if (v->data_start ||
ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(v->data_dev->bdev, v->data_dev->mode,
- cmd, arg);
+ return 1;
+ return 0;
}
static int verity_iterate_devices(struct dm_target *ti,
@@ -980,7 +979,7 @@ static struct target_type verity_target = {
.dtr = verity_dtr,
.map = verity_map,
.status = verity_status,
- .ioctl = verity_ioctl,
+ .prepare_ioctl = verity_prepare_ioctl,
.iterate_devices = verity_iterate_devices,
.io_hints = verity_io_hints,
};
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6ffc01b..85dc14c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -555,18 +555,16 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
return dm_get_geometry(md, geo);
}
-static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
- unsigned int cmd, unsigned long arg)
+static int dm_get_live_table_for_ioctl(struct mapped_device *md,
+ struct dm_target **tgt, struct block_device **bdev,
+ fmode_t *mode, int *srcu_idx)
{
- struct mapped_device *md = bdev->bd_disk->private_data;
- int srcu_idx;
struct dm_table *map;
- struct dm_target *tgt;
- int r = -ENOTTY;
+ int r;
retry:
- map = dm_get_live_table(md, &srcu_idx);
-
+ r = -ENOTTY;
+ map = dm_get_live_table(md, srcu_idx);
if (!map || !dm_table_get_size(map))
goto out;
@@ -574,8 +572,9 @@ retry:
if (dm_table_get_num_targets(map) != 1)
goto out;
- tgt = dm_table_get_target(map, 0);
- if (!tgt->type->ioctl)
+ *tgt = dm_table_get_target(map, 0);
+
+ if (!(*tgt)->type->prepare_ioctl)
goto out;
if (dm_suspended_md(md)) {
@@ -583,16 +582,41 @@ retry:
goto out;
}
- r = tgt->type->ioctl(tgt, cmd, arg);
+ r = (*tgt)->type->prepare_ioctl(*tgt, bdev, mode);
+ if (r < 0)
+ goto out;
-out:
- dm_put_live_table(md, srcu_idx);
+ return r;
+out:
+ dm_put_live_table(md, *srcu_idx);
if (r == -ENOTCONN) {
msleep(10);
goto retry;
}
+ return r;
+}
+
+static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned int cmd, unsigned long arg)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ struct dm_target *tgt;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ if (r > 0) {
+ r = scsi_verify_blk_ioctl(NULL, cmd);
+ if (r)
+ goto out;
+ }
+ r = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+out:
+ dm_put_live_table(md, srcu_idx);
return r;
}
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 76d23fa..ec1c61c 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -79,8 +79,8 @@ typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
-typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
- unsigned long arg);
+typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode);
/*
* These iteration functions are typically used to check (and combine)
@@ -156,7 +156,7 @@ struct target_type {
dm_resume_fn resume;
dm_status_fn status;
dm_message_fn message;
- dm_ioctl_fn ioctl;
+ dm_prepare_ioctl_fn prepare_ioctl;
dm_busy_fn busy;
dm_iterate_devices_fn iterate_devices;
dm_io_hints_fn io_hints;
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 5/5] dm: add support for passing through persistent reservations
2015-08-26 16:56 Persistent Reservation API V3 Christoph Hellwig
` (2 preceding siblings ...)
2015-08-26 16:56 ` [PATCH 4/5] dm: refactor ioctl handling Christoph Hellwig
@ 2015-08-26 16:56 ` Christoph Hellwig
[not found] ` <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
4 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
This adds support to pass through persistent reservation requests
similar to the existing ioctl handling, and with the same limitations,
e.g. devices may only have a single target attached.
This is mostly intended for multipathing.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/dm.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 85dc14c..c3eadbe 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -24,6 +24,7 @@
#include <linux/ktime.h>
#include <linux/elevator.h> /* for rq_end_sector() */
#include <linux/blk-mq.h>
+#include <linux/pr.h>
#include <trace/events/block.h>
@@ -3544,11 +3545,133 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
kfree(pools);
}
+static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_register)
+ r = ops->pr_register(bdev, old_key, new_key, flags);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
+ u32 flags)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_reserve)
+ r = ops->pr_reserve(bdev, key, type, flags);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_release)
+ r = ops->pr_release(bdev, key, type);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_preempt)
+ r = ops->pr_preempt(bdev, old_key, new_key, type, abort);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_clear(struct block_device *bdev, u64 key)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_clear)
+ r = ops->pr_clear(bdev, key);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static const struct pr_ops dm_pr_ops = {
+ .pr_register = dm_pr_register,
+ .pr_reserve = dm_pr_reserve,
+ .pr_release = dm_pr_release,
+ .pr_preempt = dm_pr_preempt,
+ .pr_clear = dm_pr_clear,
+};
+
static const struct block_device_operations dm_blk_dops = {
.open = dm_blk_open,
.release = dm_blk_close,
.ioctl = dm_blk_ioctl,
.getgeo = dm_blk_getgeo,
+ .pr_ops = &dm_pr_ops,
.owner = THIS_MODULE
};
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread[parent not found: <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>]
* [PATCH 3/5] sd: implement the Persistent Reservation API
[not found] ` <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
@ 2015-08-26 16:56 ` Christoph Hellwig
2015-08-29 1:33 ` Persistent Reservation API V3 Jeremy Linton
1 sibling, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA,
linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
This is a mostly trivial mapping to the PERSISTENT RESERVE IN/OUT
commands.
Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
drivers/scsi/sd.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 94 insertions(+)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 160e44e..df8e667 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -51,6 +51,7 @@
#include <linux/async.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
+#include <linux/pr.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
@@ -1535,6 +1536,98 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
}
#endif
+static char sd_pr_type(enum pr_type type)
+{
+ switch (type) {
+ case PR_WRITE_EXCLUSIVE:
+ return 0x01;
+ case PR_EXCLUSIVE_ACCESS:
+ return 0x03;
+ case PR_WRITE_EXCLUSIVE_REG_ONLY:
+ return 0x05;
+ case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+ return 0x06;
+ case PR_WRITE_EXCLUSIVE_ALL_REGS:
+ return 0x07;
+ case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+ return 0x08;
+ default:
+ return 0;
+ }
+};
+
+static int sd_pr_command(struct block_device *bdev, u8 sa,
+ u64 key, u64 sa_key, u8 type, u8 flags)
+{
+ struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
+ struct scsi_sense_hdr sshdr;
+ int result;
+ u8 cmd[16] = { 0, };
+ u8 data[24] = { 0, };
+
+ cmd[0] = PERSISTENT_RESERVE_OUT;
+ cmd[1] = sa;
+ cmd[2] = type;
+ put_unaligned_be32(sizeof(data), &cmd[5]);
+
+ put_unaligned_be64(key, &data[0]);
+ put_unaligned_be64(sa_key, &data[8]);
+ data[20] = flags;
+
+ result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
+ &sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
+
+ if ((driver_byte(result) & DRIVER_SENSE) &&
+ (scsi_sense_valid(&sshdr))) {
+ sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
+ scsi_print_sense_hdr(sdev, NULL, &sshdr);
+ }
+
+ return result;
+}
+
+static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags)
+{
+ return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
+ old_key, new_key, 0,
+ (1 << 0) /* APTPL */ |
+ (1 << 2) /* ALL_TG_PT */);
+}
+
+static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
+ u32 flags)
+{
+ if (flags)
+ return -EOPNOTSUPP;
+ return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+ return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort)
+{
+ return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
+ sd_pr_type(type), 0);
+}
+
+static int sd_pr_clear(struct block_device *bdev, u64 key)
+{
+ return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
+}
+
+static const struct pr_ops sd_pr_ops = {
+ .pr_register = sd_pr_register,
+ .pr_reserve = sd_pr_reserve,
+ .pr_release = sd_pr_release,
+ .pr_preempt = sd_pr_preempt,
+ .pr_clear = sd_pr_clear,
+};
+
static const struct block_device_operations sd_fops = {
.owner = THIS_MODULE,
.open = sd_open,
@@ -1547,6 +1640,7 @@ static const struct block_device_operations sd_fops = {
.check_events = sd_check_events,
.revalidate_disk = sd_revalidate_disk,
.unlock_native_capacity = sd_unlock_native_capacity,
+ .pr_ops = &sd_pr_ops,
};
/**
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: Persistent Reservation API V3
[not found] ` <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2015-08-26 16:56 ` [PATCH 3/5] sd: implement the Persistent Reservation API Christoph Hellwig
@ 2015-08-29 1:33 ` Jeremy Linton
2015-08-29 13:52 ` Christoph Hellwig
1 sibling, 1 reply; 10+ messages in thread
From: Jeremy Linton @ 2015-08-29 1:33 UTC (permalink / raw)
To: Christoph Hellwig, Jens Axboe
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA,
linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
Hello,
So, looking at this, I don't see how it supports the algorithm I've been using
for years. For that algorithm to successfully migrate PRs across multiple paths
on a single machine without affecting other possible users (who may legitimately
have PR'ed the same device) I need PR_IN SA 1, READ RESERVATIONS to assure the
current node owns the reservation before attempting to preempt it on another
path. This can also assure that the device hasn't been reserved with a legacy
reservation.
So, this leads me to two more general questions. The first is why isn't the PR
API simply exported to filesystems as a general reserve/release so that the PR
happens during mount/dismount. Then DM and friends can be setup to transparently
migrate or share the reservation, rather than depending on userspace to handle
these operations...
Also, it seems to me the use of CLEAR is extremely dangerous in any environment
where actual arbitration or sharing of the resource is taking place.
thanks,
On 8/26/2015 11:56 AM, Christoph Hellwig wrote:
> This series adds support for a simplified Persistent Reservation API
> to the block layer. The intent is that both in-kernel and userspace
> consumers can use the API instead of having to hand craft SCSI or NVMe
> command through the various pass through interfaces. It also adds
> DM support as getting reservations through dm-multipath is a major
> pain with the current scheme.
>
> NVMe support currently isn't included as I don't have a multihost
> NVMe setup to test on, but Keith offered to test it and I'll have
> a patch for it shortly.
>
> The ioctl API is documented in Documentation/block/pr.txt, but to
> fully understand the concept you'll have to read up the SPC spec,
> PRs are too complicated that trying to rephrase them into different
> terminology is just going to create confusion.
>
> Note that Mike wants to include the DM patches so through the DM
> tree, so they are only included for reference.
>
> I also have a set of simple test tools available at:
>
> git://git.infradead.org/users/hch/pr-tests.git
>
> Changes since V2:
> - added an ignore flag to the reserve opertion as well, and redid
> the ioctl API to have general flags fields
> - rebased on top of the latest block layer tree updates
> Changes since V1:
> - rename DM ->ioctl to ->prepare_ioctl
> - rename dm_get_ioctl_table to dm_get_live_table_for_ioctl
> - merge two DM patches into one
> - various spelling fixes
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> .
>
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: Persistent Reservation API V3
2015-08-29 1:33 ` Persistent Reservation API V3 Jeremy Linton
@ 2015-08-29 13:52 ` Christoph Hellwig
0 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-29 13:52 UTC (permalink / raw)
To: Jeremy Linton
Cc: Christoph Hellwig, Jens Axboe, linux-scsi, linux-nvme, dm-devel,
linux-api, linux-kernel
On Fri, Aug 28, 2015 at 08:33:24PM -0500, Jeremy Linton wrote:
> Hello,
> So, looking at this, I don't see how it supports the algorithm I've been using
> for years. For that algorithm to successfully migrate PRs across multiple paths
> on a single machine without affecting other possible users (who may legitimately
> have PR'ed the same device) I need PR_IN SA 1, READ RESERVATIONS to assure the
> current node owns the reservation before attempting to preempt it on another
> path. This can also assure that the device hasn't been reserved with a legacy
> reservation.
Do you have any code describing this in more detail? We could add the
read side as well if there is strong interest.
> So, this leads me to two more general questions. The first is why isn't the PR
> API simply exported to filesystems as a general reserve/release so that the PR
> happens during mount/dismount. Then DM and friends can be setup to transparently
> migrate or share the reservation, rather than depending on userspace to handle
> these operations...
The API can be used by file systems, and my upcoming NFS SCSI layout
support was the main reason to write this.
> Also, it seems to me the use of CLEAR is extremely dangerous in any environment
> where actual arbitration or sharing of the resource is taking place.
Yes, but having it as a specific API isn't any less dangerous than
having it issued using SG_IO. Reservations really only make sense if
you assume every user of a LU is actually cooperating in some way
and not actively hostile.
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH 1/5] block: cleanup blkdev_ioctl
2015-08-26 16:03 Christoph Hellwig
@ 2015-08-26 16:03 ` Christoph Hellwig
0 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-26 16:03 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
Split out helpers for all non-trivial ioctls to make this function simpler,
and also start passing around a pointer version of the argument, as that's
what most ioctl handlers actually need.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/ioctl.c | 227 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..df62b47 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -193,10 +193,20 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
-static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
- uint64_t len, int secure)
+static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
{
- unsigned long flags = 0;
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
if (start & 511)
return -EINVAL;
@@ -207,14 +217,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
- if (secure)
- flags |= BLKDEV_DISCARD_SECURE;
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
-static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
- uint64_t len)
+static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+ unsigned long arg)
{
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
+
if (start & 511)
return -EINVAL;
if (len & 511)
@@ -295,89 +315,115 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}
-/*
- * always keep this in sync with compat_blkdev_ioctl()
- */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
{
- struct gendisk *disk = bdev->bd_disk;
- struct backing_dev_info *bdi;
- loff_t size;
- int ret, n;
- unsigned int max_sectors;
+ int ret;
- switch(cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
- fsync_bdev(bdev);
- invalidate_bdev(bdev);
- return 0;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
- case BLKROSET:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (get_user(n, (int __user *)(arg)))
- return -EFAULT;
- set_device_ro(bdev, n);
- return 0;
+ fsync_bdev(bdev);
+ invalidate_bdev(bdev);
+ return 0;
+}
- case BLKDISCARD:
- case BLKSECDISCARD: {
- uint64_t range[2];
+static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
+{
+ int ret, n;
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (get_user(n, (int __user *)arg))
+ return -EFAULT;
+ set_device_ro(bdev, n);
+ return 0;
+}
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+static int blkdev_getgeo(struct block_device *bdev,
+ struct hd_geometry __user *argp)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct hd_geometry geo;
+ int ret;
- return blk_ioctl_discard(bdev, range[0], range[1],
- cmd == BLKSECDISCARD);
- }
- case BLKZEROOUT: {
- uint64_t range[2];
+ if (!argp)
+ return -EINVAL;
+ if (!disk->fops->getgeo)
+ return -ENOTTY;
+
+ /*
+ * We need to set the startsect first, the driver may
+ * want to override it.
+ */
+ memset(&geo, 0, sizeof(geo));
+ geo.start = get_start_sect(bdev);
+ ret = disk->fops->getgeo(bdev, &geo);
+ if (ret)
+ return ret;
+ if (copy_to_user(argp, &geo, sizeof(geo)))
+ return -EFAULT;
+ return 0;
+}
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+/* set the logical block size */
+static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+ int __user *argp)
+{
+ int ret, n;
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (!argp)
+ return -EINVAL;
+ if (get_user(n, argp))
+ return -EFAULT;
- return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
}
- case HDIO_GETGEO: {
- struct hd_geometry geo;
+ ret = set_blocksize(bdev, n);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
+ return ret;
+}
- if (!arg)
- return -EINVAL;
- if (!disk->fops->getgeo)
- return -ENOTTY;
-
- /*
- * We need to set the startsect first, the driver may
- * want to override it.
- */
- memset(&geo, 0, sizeof(geo));
- geo.start = get_start_sect(bdev);
- ret = disk->fops->getgeo(bdev, &geo);
- if (ret)
- return ret;
- if (copy_to_user((struct hd_geometry __user *)arg, &geo,
- sizeof(geo)))
- return -EFAULT;
- return 0;
- }
+/*
+ * always keep this in sync with compat_blkdev_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+ unsigned long arg)
+{
+ struct backing_dev_info *bdi;
+ void __user *argp = (void __user *)arg;
+ loff_t size;
+ unsigned int max_sectors;
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ return blkdev_flushbuf(bdev, mode, cmd, arg);
+ case BLKROSET:
+ return blkdev_roset(bdev, mode, cmd, arg);
+ case BLKDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg, 0);
+ case BLKSECDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg,
+ BLKDEV_DISCARD_SECURE);
+ case BLKZEROOUT:
+ return blk_ioctl_zeroout(bdev, mode, arg);
+ case HDIO_GETGEO:
+ return blkdev_getgeo(bdev, argp);
case BLKRAGET:
case BLKFRAGET:
if (!arg)
@@ -414,28 +460,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
- /* set the logical block size */
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (!arg)
- return -EINVAL;
- if (get_user(n, (int __user *) arg))
- return -EFAULT;
- if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
- }
- ret = set_blocksize(bdev, n);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
- return ret;
+ return blkdev_bszset(bdev, mode, argp);
case BLKPG:
- ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
- break;
+ return blkpg_ioctl(bdev, argp);
case BLKRRPART:
- ret = blkdev_reread_part(bdev);
- break;
+ return blkdev_reread_part(bdev);
case BLKGETSIZE:
size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
@@ -447,11 +476,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
- ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
- break;
+ return blk_trace_ioctl(bdev, cmd, argp);
default:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH 1/5] block: cleanup blkdev_ioctl
2015-08-12 6:23 Persistent Reservation API V2 Christoph Hellwig
@ 2015-08-12 6:23 ` Christoph Hellwig
0 siblings, 0 replies; 10+ messages in thread
From: Christoph Hellwig @ 2015-08-12 6:23 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
Split out helpers for all non-trivial ioctls to make this function simpler,
and also start passing around a pointer version of the argument, as that's
what most ioctl handlers actually need.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/ioctl.c | 227 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..df62b47 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -193,10 +193,20 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
-static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
- uint64_t len, int secure)
+static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
{
- unsigned long flags = 0;
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
if (start & 511)
return -EINVAL;
@@ -207,14 +217,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
- if (secure)
- flags |= BLKDEV_DISCARD_SECURE;
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
-static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
- uint64_t len)
+static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+ unsigned long arg)
{
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
+
if (start & 511)
return -EINVAL;
if (len & 511)
@@ -295,89 +315,115 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}
-/*
- * always keep this in sync with compat_blkdev_ioctl()
- */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
{
- struct gendisk *disk = bdev->bd_disk;
- struct backing_dev_info *bdi;
- loff_t size;
- int ret, n;
- unsigned int max_sectors;
+ int ret;
- switch(cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
- fsync_bdev(bdev);
- invalidate_bdev(bdev);
- return 0;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
- case BLKROSET:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (get_user(n, (int __user *)(arg)))
- return -EFAULT;
- set_device_ro(bdev, n);
- return 0;
+ fsync_bdev(bdev);
+ invalidate_bdev(bdev);
+ return 0;
+}
- case BLKDISCARD:
- case BLKSECDISCARD: {
- uint64_t range[2];
+static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
+{
+ int ret, n;
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (get_user(n, (int __user *)arg))
+ return -EFAULT;
+ set_device_ro(bdev, n);
+ return 0;
+}
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+static int blkdev_getgeo(struct block_device *bdev,
+ struct hd_geometry __user *argp)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct hd_geometry geo;
+ int ret;
- return blk_ioctl_discard(bdev, range[0], range[1],
- cmd == BLKSECDISCARD);
- }
- case BLKZEROOUT: {
- uint64_t range[2];
+ if (!argp)
+ return -EINVAL;
+ if (!disk->fops->getgeo)
+ return -ENOTTY;
+
+ /*
+ * We need to set the startsect first, the driver may
+ * want to override it.
+ */
+ memset(&geo, 0, sizeof(geo));
+ geo.start = get_start_sect(bdev);
+ ret = disk->fops->getgeo(bdev, &geo);
+ if (ret)
+ return ret;
+ if (copy_to_user(argp, &geo, sizeof(geo)))
+ return -EFAULT;
+ return 0;
+}
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+/* set the logical block size */
+static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+ int __user *argp)
+{
+ int ret, n;
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (!argp)
+ return -EINVAL;
+ if (get_user(n, argp))
+ return -EFAULT;
- return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
}
- case HDIO_GETGEO: {
- struct hd_geometry geo;
+ ret = set_blocksize(bdev, n);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
+ return ret;
+}
- if (!arg)
- return -EINVAL;
- if (!disk->fops->getgeo)
- return -ENOTTY;
-
- /*
- * We need to set the startsect first, the driver may
- * want to override it.
- */
- memset(&geo, 0, sizeof(geo));
- geo.start = get_start_sect(bdev);
- ret = disk->fops->getgeo(bdev, &geo);
- if (ret)
- return ret;
- if (copy_to_user((struct hd_geometry __user *)arg, &geo,
- sizeof(geo)))
- return -EFAULT;
- return 0;
- }
+/*
+ * always keep this in sync with compat_blkdev_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+ unsigned long arg)
+{
+ struct backing_dev_info *bdi;
+ void __user *argp = (void __user *)arg;
+ loff_t size;
+ unsigned int max_sectors;
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ return blkdev_flushbuf(bdev, mode, cmd, arg);
+ case BLKROSET:
+ return blkdev_roset(bdev, mode, cmd, arg);
+ case BLKDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg, 0);
+ case BLKSECDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg,
+ BLKDEV_DISCARD_SECURE);
+ case BLKZEROOUT:
+ return blk_ioctl_zeroout(bdev, mode, arg);
+ case HDIO_GETGEO:
+ return blkdev_getgeo(bdev, argp);
case BLKRAGET:
case BLKFRAGET:
if (!arg)
@@ -414,28 +460,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
- /* set the logical block size */
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (!arg)
- return -EINVAL;
- if (get_user(n, (int __user *) arg))
- return -EFAULT;
- if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
- }
- ret = set_blocksize(bdev, n);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
- return ret;
+ return blkdev_bszset(bdev, mode, argp);
case BLKPG:
- ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
- break;
+ return blkpg_ioctl(bdev, argp);
case BLKRRPART:
- ret = blkdev_reread_part(bdev);
- break;
+ return blkdev_reread_part(bdev);
case BLKGETSIZE:
size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
@@ -447,11 +476,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
- ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
- break;
+ return blk_trace_ioctl(bdev, cmd, argp);
default:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
--
1.9.1
^ permalink raw reply related [flat|nested] 10+ messages in thread