Revision 74c42e1baacf206338b1dd6b6199ac964512b5bb authored by Rongwei Wang on 28 October 2021, 21:36:27 UTC, committed by Linus Torvalds on 29 October 2021, 00:18:55 UTC
Currently collapse_file does not explicitly check PG_writeback, instead, page_has_private and try_to_release_page are used to filter writeback pages. This does not work for xfs with blocksize equal to or larger than pagesize, because in such case xfs has no page->private. This makes collapse_file bail out early for writeback page. Otherwise, xfs end_page_writeback will panic as follows. page:fffffe00201bcc80 refcount:0 mapcount:0 mapping:ffff0003f88c86a8 index:0x0 pfn:0x84ef32 aops:xfs_address_space_operations [xfs] ino:30000b7 dentry name:"libtest.so" flags: 0x57fffe0000008027(locked|referenced|uptodate|active|writeback) raw: 57fffe0000008027 ffff80001b48bc28 ffff80001b48bc28 ffff0003f88c86a8 raw: 0000000000000000 0000000000000000 00000000ffffffff ffff0000c3e9a000 page dumped because: VM_BUG_ON_PAGE(((unsigned int) page_ref_count(page) + 127u <= 127u)) page->mem_cgroup:ffff0000c3e9a000 ------------[ cut here ]------------ kernel BUG at include/linux/mm.h:1212! Internal error: Oops - BUG: 0 [#1] SMP Modules linked in: BUG: Bad page state in process khugepaged pfn:84ef32 xfs(E) page:fffffe00201bcc80 refcount:0 mapcount:0 mapping:0 index:0x0 pfn:0x84ef32 libcrc32c(E) rfkill(E) aes_ce_blk(E) crypto_simd(E) ... CPU: 25 PID: 0 Comm: swapper/25 Kdump: loaded Tainted: ... pstate: 60400005 (nZCv daif +PAN -UAO -TCO BTYPE=--) Call trace: end_page_writeback+0x1c0/0x214 iomap_finish_page_writeback+0x13c/0x204 iomap_finish_ioend+0xe8/0x19c iomap_writepage_end_bio+0x38/0x50 bio_endio+0x168/0x1ec blk_update_request+0x278/0x3f0 blk_mq_end_request+0x34/0x15c virtblk_request_done+0x38/0x74 [virtio_blk] blk_done_softirq+0xc4/0x110 __do_softirq+0x128/0x38c __irq_exit_rcu+0x118/0x150 irq_exit+0x1c/0x30 __handle_domain_irq+0x8c/0xf0 gic_handle_irq+0x84/0x108 el1_irq+0xcc/0x180 arch_cpu_idle+0x18/0x40 default_idle_call+0x4c/0x1a0 cpuidle_idle_call+0x168/0x1e0 do_idle+0xb4/0x104 cpu_startup_entry+0x30/0x9c secondary_start_kernel+0x104/0x180 Code: d4210000 b0006161 910c8021 94013f4d (d4210000) ---[ end trace 4a88c6a074082f8c ]--- Kernel panic - not syncing: Oops - BUG: Fatal exception in interrupt Link: https://lkml.kernel.org/r/20211022023052.33114-1-rongwei.wang@linux.alibaba.com Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS") Signed-off-by: Rongwei Wang <rongwei.wang@linux.alibaba.com> Signed-off-by: Xu Yu <xuyu@linux.alibaba.com> Suggested-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Yang Shi <shy828301@gmail.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Song Liu <song@kernel.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent ffb29b1
holder.c
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/genhd.h>
struct bd_holder_disk {
struct list_head list;
struct block_device *bdev;
int refcnt;
};
static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
struct gendisk *disk)
{
struct bd_holder_disk *holder;
list_for_each_entry(holder, &disk->slave_bdevs, list)
if (holder->bdev == bdev)
return holder;
return NULL;
}
static int add_symlink(struct kobject *from, struct kobject *to)
{
return sysfs_create_link(from, to, kobject_name(to));
}
static void del_symlink(struct kobject *from, struct kobject *to)
{
sysfs_remove_link(from, kobject_name(to));
}
static int __link_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
int ret;
ret = add_symlink(disk->slave_dir, bdev_kobj(bdev));
if (ret)
return ret;
ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
if (ret)
del_symlink(disk->slave_dir, bdev_kobj(bdev));
return ret;
}
/**
* bd_link_disk_holder - create symlinks between holding disk and slave bdev
* @bdev: the claimed slave bdev
* @disk: the holding disk
*
* DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
*
* This functions creates the following sysfs symlinks.
*
* - from "slaves" directory of the holder @disk to the claimed @bdev
* - from "holders" directory of the @bdev to the holder @disk
*
* For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
* passed to bd_link_disk_holder(), then:
*
* /sys/block/dm-0/slaves/sda --> /sys/block/sda
* /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
*
* The caller must have claimed @bdev before calling this function and
* ensure that both @bdev and @disk are valid during the creation and
* lifetime of these symlinks.
*
* CONTEXT:
* Might sleep.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
struct bd_holder_disk *holder;
int ret = 0;
mutex_lock(&disk->open_mutex);
WARN_ON_ONCE(!bdev->bd_holder);
/* FIXME: remove the following once add_disk() handles errors */
if (WARN_ON(!bdev->bd_holder_dir))
goto out_unlock;
holder = bd_find_holder_disk(bdev, disk);
if (holder) {
holder->refcnt++;
goto out_unlock;
}
holder = kzalloc(sizeof(*holder), GFP_KERNEL);
if (!holder) {
ret = -ENOMEM;
goto out_unlock;
}
INIT_LIST_HEAD(&holder->list);
holder->bdev = bdev;
holder->refcnt = 1;
if (disk->slave_dir) {
ret = __link_disk_holder(bdev, disk);
if (ret) {
kfree(holder);
goto out_unlock;
}
}
list_add(&holder->list, &disk->slave_bdevs);
/*
* del_gendisk drops the initial reference to bd_holder_dir, so we need
* to keep our own here to allow for cleanup past that point.
*/
kobject_get(bdev->bd_holder_dir);
out_unlock:
mutex_unlock(&disk->open_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(bd_link_disk_holder);
static void __unlink_disk_holder(struct block_device *bdev,
struct gendisk *disk)
{
del_symlink(disk->slave_dir, bdev_kobj(bdev));
del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
}
/**
* bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder()
* @bdev: the calimed slave bdev
* @disk: the holding disk
*
* DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
*
* CONTEXT:
* Might sleep.
*/
void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
struct bd_holder_disk *holder;
mutex_lock(&disk->open_mutex);
holder = bd_find_holder_disk(bdev, disk);
if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
if (disk->slave_dir)
__unlink_disk_holder(bdev, disk);
kobject_put(bdev->bd_holder_dir);
list_del_init(&holder->list);
kfree(holder);
}
mutex_unlock(&disk->open_mutex);
}
EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
int bd_register_pending_holders(struct gendisk *disk)
{
struct bd_holder_disk *holder;
int ret;
mutex_lock(&disk->open_mutex);
list_for_each_entry(holder, &disk->slave_bdevs, list) {
ret = __link_disk_holder(holder->bdev, disk);
if (ret)
goto out_undo;
}
mutex_unlock(&disk->open_mutex);
return 0;
out_undo:
list_for_each_entry_continue_reverse(holder, &disk->slave_bdevs, list)
__unlink_disk_holder(holder->bdev, disk);
mutex_unlock(&disk->open_mutex);
return ret;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...