Linux 6.5 compat: blkdev changes

Multiple changes to the blkdev API were introduced in Linux 6.5. This
includes passing (void* holder) to blkdev_put, adding a new
blk_holder_ops* arg to blkdev_get_by_path, adding a new blk_mode_t type
that replaces uses of fmode_t, and removing an argument from the release
handler on block_device_operations that we weren't using. The open
function definition has also changed to take gendisk* and blk_mode_t, so
update it accordingly, too.

Implement local wrappers for blkdev_get_by_path() and
vdev_blkdev_put() so that the in-line calls are cleaner, and place the
conditionally-compiled implementation details inside of both of these
local wrappers. Both calls are exclusively used within vdev_disk.c, at
this time.

Add blk_mode_is_open_write() to test FMODE_WRITE / BLK_OPEN_WRITE
The wrapper function is now used for testing using the appropriate
method for the kernel, whether the open mode is writable or not.

Emphasize fmode_t arg in zvol_release is not used

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #15099
This commit is contained in:
Coleman Kane 2023-08-01 11:37:20 -04:00 committed by Brian Behlendorf
parent c0f075c06b
commit d76de9fb17
7 changed files with 203 additions and 19 deletions

View File

@ -16,12 +16,63 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH], [
])
])
dnl #
dnl # 6.5.x API change,
dnl # blkdev_get_by_path() takes 4 args
dnl #
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG], [
ZFS_LINUX_TEST_SRC([blkdev_get_by_path_4arg], [
#include <linux/fs.h>
#include <linux/blkdev.h>
], [
struct block_device *bdev __attribute__ ((unused)) = NULL;
const char *path = "path";
fmode_t mode = 0;
void *holder = NULL;
struct blk_holder_ops h;
bdev = blkdev_get_by_path(path, mode, holder, &h);
])
])
AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_GET_BY_PATH], [
AC_MSG_CHECKING([whether blkdev_get_by_path() exists])
AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 3 args])
ZFS_LINUX_TEST_RESULT([blkdev_get_by_path], [
AC_MSG_RESULT(yes)
], [
ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
AC_MSG_RESULT(no)
AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 4 args])
ZFS_LINUX_TEST_RESULT([blkdev_get_by_path_4arg], [
AC_DEFINE(HAVE_BLKDEV_GET_BY_PATH_4ARG, 1,
[blkdev_get_by_path() exists and takes 4 args])
AC_MSG_RESULT(yes)
], [
ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
])
])
])
dnl #
dnl # 6.5.x API change
dnl # blk_mode_t was added as a type to supercede some places where fmode_t
dnl # is used
dnl #
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T], [
ZFS_LINUX_TEST_SRC([blk_mode_t], [
#include <linux/fs.h>
#include <linux/blkdev.h>
], [
blk_mode_t m __attribute((unused)) = (blk_mode_t)0;
])
])
AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T], [
AC_MSG_CHECKING([whether blk_mode_t is defined])
ZFS_LINUX_TEST_RESULT([blk_mode_t], [
AC_MSG_RESULT(yes)
AC_DEFINE(HAVE_BLK_MODE_T, 1, [blk_mode_t is defined])
], [
AC_MSG_RESULT(no)
])
])
@ -41,12 +92,35 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT], [
])
])
dnl #
dnl # 6.5.x API change.
dnl # blkdev_put() takes (void* holder) as arg 2
dnl #
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER], [
ZFS_LINUX_TEST_SRC([blkdev_put_holder], [
#include <linux/fs.h>
#include <linux/blkdev.h>
], [
struct block_device *bdev = NULL;
void *holder = NULL;
blkdev_put(bdev, holder);
])
])
AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_PUT], [
AC_MSG_CHECKING([whether blkdev_put() exists])
ZFS_LINUX_TEST_RESULT([blkdev_put], [
AC_MSG_RESULT(yes)
], [
ZFS_LINUX_TEST_ERROR([blkdev_put()])
AC_MSG_CHECKING([whether blkdev_put() accepts void* as arg 2])
ZFS_LINUX_TEST_RESULT([blkdev_put_holder], [
AC_MSG_RESULT(yes)
AC_DEFINE(HAVE_BLKDEV_PUT_HOLDER, 1,
[blkdev_put() accepts void* as arg 2])
], [
ZFS_LINUX_TEST_ERROR([blkdev_put()])
])
])
])
@ -495,7 +569,9 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT], [
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH
ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG
ZFS_AC_KERNEL_SRC_BLKDEV_PUT
ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER
ZFS_AC_KERNEL_SRC_BLKDEV_REREAD_PART
ZFS_AC_KERNEL_SRC_BLKDEV_INVALIDATE_BDEV
ZFS_AC_KERNEL_SRC_BLKDEV_LOOKUP_BDEV
@ -510,6 +586,7 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
ZFS_AC_KERNEL_SRC_BLKDEV_PART_TO_DEV
ZFS_AC_KERNEL_SRC_BLKDEV_DISK_CHECK_MEDIA_CHANGE
ZFS_AC_KERNEL_SRC_BLKDEV_BLK_STS_RESV_CONFLICT
ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T
])
AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
@ -530,4 +607,5 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
ZFS_AC_KERNEL_BLKDEV_PART_TO_DEV
ZFS_AC_KERNEL_BLKDEV_DISK_CHECK_MEDIA_CHANGE
ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT
ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T
])

View File

@ -49,12 +49,42 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
], [], [])
])
dnl #
dnl # 5.9.x API change
dnl #
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [
ZFS_LINUX_TEST_SRC([block_device_operations_release_void_1arg], [
#include <linux/blkdev.h>
void blk_release(struct gendisk *g) {
(void) g;
return;
}
static const struct block_device_operations
bops __attribute__ ((unused)) = {
.open = NULL,
.release = blk_release,
.ioctl = NULL,
.compat_ioctl = NULL,
};
], [], [])
])
AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
AC_MSG_CHECKING([whether bops->release() is void])
AC_MSG_CHECKING([whether bops->release() is void and takes 2 args])
ZFS_LINUX_TEST_RESULT([block_device_operations_release_void], [
AC_MSG_RESULT(yes)
],[
ZFS_LINUX_TEST_ERROR([bops->release()])
AC_MSG_RESULT(no)
AC_MSG_CHECKING([whether bops->release() is void and takes 1 arg])
ZFS_LINUX_TEST_RESULT([block_device_operations_release_void_1arg], [
AC_MSG_RESULT(yes)
AC_DEFINE([HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [1],
[Define if release() in block_device_operations takes 1 arg])
],[
ZFS_LINUX_TEST_ERROR([bops->release()])
])
])
])
@ -92,6 +122,7 @@ AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK], [
AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS], [
ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_CHECK_EVENTS
ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID
ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK
])

View File

@ -398,6 +398,12 @@ vdev_lookup_bdev(const char *path, dev_t *dev)
#endif
}
#if defined(HAVE_BLK_MODE_T)
#define blk_mode_is_open_write(flag) ((flag) & BLK_OPEN_WRITE)
#else
#define blk_mode_is_open_write(flag) ((flag) & FMODE_WRITE)
#endif
/*
* Kernels without bio_set_op_attrs use bi_rw for the bio flags.
*/

View File

@ -80,9 +80,22 @@ typedef struct dio_request {
static unsigned int zfs_vdev_failfast_mask = 1;
#ifdef HAVE_BLK_MODE_T
static blk_mode_t
#else
static fmode_t
#endif
vdev_bdev_mode(spa_mode_t spa_mode)
{
#ifdef HAVE_BLK_MODE_T
blk_mode_t mode = 0;
if (spa_mode & SPA_MODE_READ)
mode |= BLK_OPEN_READ;
if (spa_mode & SPA_MODE_WRITE)
mode |= BLK_OPEN_WRITE;
#else
fmode_t mode = 0;
if (spa_mode & SPA_MODE_READ)
@ -90,6 +103,7 @@ vdev_bdev_mode(spa_mode_t spa_mode)
if (spa_mode & SPA_MODE_WRITE)
mode |= FMODE_WRITE;
#endif
return (mode);
}
@ -197,12 +211,47 @@ vdev_disk_kobj_evt_post(vdev_t *v)
}
}
#if !defined(HAVE_BLKDEV_GET_BY_PATH_4ARG)
/*
* Define a dummy struct blk_holder_ops for kernel versions
* prior to 6.5.
*/
struct blk_holder_ops {};
#endif
static struct block_device *
vdev_blkdev_get_by_path(const char *path, spa_mode_t mode, void *holder,
const struct blk_holder_ops *hops)
{
#ifdef HAVE_BLKDEV_GET_BY_PATH_4ARG
return (blkdev_get_by_path(path,
vdev_bdev_mode(mode) | BLK_OPEN_EXCL, holder, hops));
#else
return (blkdev_get_by_path(path,
vdev_bdev_mode(mode) | FMODE_EXCL, holder));
#endif
}
static void
vdev_blkdev_put(struct block_device *bdev, spa_mode_t mode, void *holder)
{
#ifdef HAVE_BLKDEV_PUT_HOLDER
return (blkdev_put(bdev, holder));
#else
return (blkdev_put(bdev, vdev_bdev_mode(mode) | FMODE_EXCL));
#endif
}
static int
vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
uint64_t *logical_ashift, uint64_t *physical_ashift)
{
struct block_device *bdev;
#ifdef HAVE_BLK_MODE_T
blk_mode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
#else
fmode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
#endif
hrtime_t timeout = MSEC2NSEC(zfs_vdev_open_timeout_ms);
vdev_disk_t *vd;
@ -252,15 +301,15 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
reread_part = B_TRUE;
}
blkdev_put(bdev, mode | FMODE_EXCL);
vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
}
if (reread_part) {
bdev = blkdev_get_by_path(disk_name, mode | FMODE_EXCL,
zfs_vdev_holder);
bdev = vdev_blkdev_get_by_path(disk_name, mode,
zfs_vdev_holder, NULL);
if (!IS_ERR(bdev)) {
int error = vdev_bdev_reread_part(bdev);
blkdev_put(bdev, mode | FMODE_EXCL);
vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
if (error == 0) {
timeout = MSEC2NSEC(
zfs_vdev_open_timeout_ms * 2);
@ -305,8 +354,8 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
hrtime_t start = gethrtime();
bdev = ERR_PTR(-ENXIO);
while (IS_ERR(bdev) && ((gethrtime() - start) < timeout)) {
bdev = blkdev_get_by_path(v->vdev_path, mode | FMODE_EXCL,
zfs_vdev_holder);
bdev = vdev_blkdev_get_by_path(v->vdev_path, mode,
zfs_vdev_holder, NULL);
if (unlikely(PTR_ERR(bdev) == -ENOENT)) {
/*
* There is no point of waiting since device is removed
@ -382,8 +431,8 @@ vdev_disk_close(vdev_t *v)
return;
if (vd->vd_bdev != NULL) {
blkdev_put(vd->vd_bdev,
vdev_bdev_mode(spa_mode(v->vdev_spa)) | FMODE_EXCL);
vdev_blkdev_put(vd->vd_bdev, spa_mode(v->vdev_spa),
zfs_vdev_holder);
}
rw_destroy(&vd->vd_lock);

View File

@ -186,7 +186,7 @@ zfs_open(struct inode *ip, int mode, int flag, cred_t *cr)
return (error);
/* Honor ZFS_APPENDONLY file attribute */
if ((mode & FMODE_WRITE) && (zp->z_pflags & ZFS_APPENDONLY) &&
if (blk_mode_is_open_write(mode) && (zp->z_pflags & ZFS_APPENDONLY) &&
((flag & O_APPEND) == 0)) {
zfs_exit(zfsvfs, FTAG);
return (SET_ERROR(EPERM));

View File

@ -42,7 +42,7 @@
static int
zpl_common_open(struct inode *ip, struct file *filp)
{
if (filp->f_mode & FMODE_WRITE)
if (blk_mode_is_open_write(filp->f_mode))
return (-EACCES);
return (generic_file_open(ip, filp));

View File

@ -671,7 +671,11 @@ zvol_request(struct request_queue *q, struct bio *bio)
}
static int
#ifdef HAVE_BLK_MODE_T
zvol_open(struct gendisk *disk, blk_mode_t flag)
#else
zvol_open(struct block_device *bdev, fmode_t flag)
#endif
{
zvol_state_t *zv;
int error = 0;
@ -686,10 +690,14 @@ retry:
/*
* Obtain a copy of private_data under the zvol_state_lock to make
* sure that either the result of zvol free code path setting
* bdev->bd_disk->private_data to NULL is observed, or zvol_os_free()
* disk->private_data to NULL is observed, or zvol_os_free()
* is not called on this zv because of the positive zv_open_count.
*/
#ifdef HAVE_BLK_MODE_T
zv = disk->private_data;
#else
zv = bdev->bd_disk->private_data;
#endif
if (zv == NULL) {
rw_exit(&zvol_state_lock);
return (SET_ERROR(-ENXIO));
@ -769,14 +777,15 @@ retry:
}
}
error = -zvol_first_open(zv, !(flag & FMODE_WRITE));
error = -zvol_first_open(zv, !(blk_mode_is_open_write(flag)));
if (drop_namespace)
mutex_exit(&spa_namespace_lock);
}
if (error == 0) {
if ((flag & FMODE_WRITE) && (zv->zv_flags & ZVOL_RDONLY)) {
if ((blk_mode_is_open_write(flag)) &&
(zv->zv_flags & ZVOL_RDONLY)) {
if (zv->zv_open_count == 0)
zvol_last_close(zv);
@ -791,14 +800,25 @@ retry:
rw_exit(&zv->zv_suspend_lock);
if (error == 0)
#ifdef HAVE_BLK_MODE_T
disk_check_media_change(disk);
#else
zfs_check_media_change(bdev);
#endif
return (error);
}
static void
zvol_release(struct gendisk *disk, fmode_t mode)
#ifdef HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
zvol_release(struct gendisk *disk)
#else
zvol_release(struct gendisk *disk, fmode_t unused)
#endif
{
#if !defined(HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG)
(void) unused;
#endif
zvol_state_t *zv;
boolean_t drop_suspend = B_TRUE;