Merge branch 'for-4.4/reservations' of git://git.kernel.dk/linux-block
Merge commit. Changes below are compared with the first parent: 527d1529.
Changes
7 files changed · +608 −100
| File | Status | Add | Del | Content |
|---|---|---|---|---|
| Documentation/block/pr.txt | added | +119 | −0 | View file |
| block/ioctl.c | modified | +230 | −100 | View file |
| drivers/nvme/host/pci.c | modified | +95 | −0 | View file |
| drivers/scsi/sd.c | modified | +96 | −0 | View file |
| include/linux/blkdev.h | modified | +2 | −0 | View file |
| include/linux/pr.h | added | +18 | −0 | View file |
| include/uapi/linux/pr.h | added | +48 | −0 | View file |
Only the first 600 diff lines are shown. Download the complete patch.
Documentation/block/pr.txt
View filediff --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.
block/ioctl.c
View filediff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..0918aed 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)
@@ -193,10 +194,20 @@ 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 +218,24 @@ 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)
@@ -275,6 +296,96 @@ 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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ 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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ 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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ 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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ 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 (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ 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
@@ -295,89 +406,115 @@ 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 +551,11 @@ 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 +567,21 @@ 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);
+ 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:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
drivers/nvme/host/pci.c
View filediff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 381d2a0..e878590 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -39,8 +39,10 @@
#include <linux/slab.h>
#include <linux/t10-pi.h>
#include <linux/types.h>
+#include <linux/pr.h>
#include <scsi/sg.h>
#include <asm-generic/io-64-nonatomic-lo-hi.h>
+#include <asm/unaligned.h>
#include <uapi/linux/nvme_ioctl.h>
#include "nvme.h"
@@ -2064,6 +2066,98 @@ static int nvme_revalidate_disk(struct gendisk *disk)
return 0;
}
+static char nvme_pr_type(enum pr_type type)
+{
+ switch (type) {
+ case PR_WRITE_EXCLUSIVE:
+ return 1;
+ case PR_EXCLUSIVE_ACCESS:
+ return 2;
+ case PR_WRITE_EXCLUSIVE_REG_ONLY:
+ return 3;
+ case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+ return 4;
+ case PR_WRITE_EXCLUSIVE_ALL_REGS:
+ return 5;
+ case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+ return 6;
+ default:
+ return 0;
+ }
+};
+
+static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
+ u64 key, u64 sa_key, u8 op)
+{
+ struct nvme_ns *ns = bdev->bd_disk->private_data;
+ struct nvme_command c;
+ u8 data[16] = { 0, };
+
+ put_unaligned_le64(key, &data[0]);
+ put_unaligned_le64(sa_key, &data[8]);
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = op;
+ c.common.nsid = cpu_to_le32(ns->ns_id);
+ c.common.cdw10[0] = cpu_to_le32(cdw10);
+
+ return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
+}
+
+static int nvme_pr_register(struct block_device *bdev, u64 old,
+ u64 new, unsigned flags)
+{
+ u32 cdw10;
+
+ if (flags & ~PR_FL_IGNORE_KEY)
+ return -EOPNOTSUPP;
+
+ cdw10 = old ? 2 : 0;
+ cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
+ cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
+ return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
+}
This diff is incomplete. Download the complete patch.
drivers/scsi/sd.c
View fileThis diff is incomplete. Download the complete patch.
include/linux/blkdev.h
View fileThis diff is incomplete. Download the complete patch.
include/linux/pr.h
View fileThis diff is incomplete. Download the complete patch.
include/uapi/linux/pr.h
View fileThis diff is incomplete. Download the complete patch.