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
blk-ioprio.c
// SPDX-License-Identifier: GPL-2.0
/*
* Block rq-qos policy for assigning an I/O priority class to requests.
*
* Using an rq-qos policy for assigning I/O priority class has two advantages
* over using the ioprio_set() system call:
*
* - This policy is cgroup based so it has all the advantages of cgroups.
* - While ioprio_set() does not affect page cache writeback I/O, this rq-qos
* controller affects page cache writeback I/O for filesystems that support
* assiociating a cgroup with writeback I/O. See also
* Documentation/admin-guide/cgroup-v2.rst.
*/
#include <linux/blk-cgroup.h>
#include <linux/blk-mq.h>
#include <linux/blk_types.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include "blk-ioprio.h"
#include "blk-rq-qos.h"
/**
* enum prio_policy - I/O priority class policy.
* @POLICY_NO_CHANGE: (default) do not modify the I/O priority class.
* @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT.
* @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into
* IOPRIO_CLASS_BE.
* @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE.
*
* See also <linux/ioprio.h>.
*/
enum prio_policy {
POLICY_NO_CHANGE = 0,
POLICY_NONE_TO_RT = 1,
POLICY_RESTRICT_TO_BE = 2,
POLICY_ALL_TO_IDLE = 3,
};
static const char *policy_name[] = {
[POLICY_NO_CHANGE] = "no-change",
[POLICY_NONE_TO_RT] = "none-to-rt",
[POLICY_RESTRICT_TO_BE] = "restrict-to-be",
[POLICY_ALL_TO_IDLE] = "idle",
};
static struct blkcg_policy ioprio_policy;
/**
* struct ioprio_blkg - Per (cgroup, request queue) data.
* @pd: blkg_policy_data structure.
*/
struct ioprio_blkg {
struct blkg_policy_data pd;
};
/**
* struct ioprio_blkcg - Per cgroup data.
* @cpd: blkcg_policy_data structure.
* @prio_policy: One of the IOPRIO_CLASS_* values. See also <linux/ioprio.h>.
*/
struct ioprio_blkcg {
struct blkcg_policy_data cpd;
enum prio_policy prio_policy;
};
static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd)
{
return pd ? container_of(pd, struct ioprio_blkg, pd) : NULL;
}
static struct ioprio_blkcg *blkcg_to_ioprio_blkcg(struct blkcg *blkcg)
{
return container_of(blkcg_to_cpd(blkcg, &ioprio_policy),
struct ioprio_blkcg, cpd);
}
static struct ioprio_blkcg *
ioprio_blkcg_from_css(struct cgroup_subsys_state *css)
{
return blkcg_to_ioprio_blkcg(css_to_blkcg(css));
}
static struct ioprio_blkcg *ioprio_blkcg_from_bio(struct bio *bio)
{
struct blkg_policy_data *pd = blkg_to_pd(bio->bi_blkg, &ioprio_policy);
if (!pd)
return NULL;
return blkcg_to_ioprio_blkcg(pd->blkg->blkcg);
}
static int ioprio_show_prio_policy(struct seq_file *sf, void *v)
{
struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(seq_css(sf));
seq_printf(sf, "%s\n", policy_name[blkcg->prio_policy]);
return 0;
}
static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(of_css(of));
int ret;
if (off != 0)
return -EIO;
/* kernfs_fop_write_iter() terminates 'buf' with '\0'. */
ret = sysfs_match_string(policy_name, buf);
if (ret < 0)
return ret;
blkcg->prio_policy = ret;
return nbytes;
}
static struct blkg_policy_data *
ioprio_alloc_pd(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg)
{
struct ioprio_blkg *ioprio_blkg;
ioprio_blkg = kzalloc(sizeof(*ioprio_blkg), gfp);
if (!ioprio_blkg)
return NULL;
return &ioprio_blkg->pd;
}
static void ioprio_free_pd(struct blkg_policy_data *pd)
{
struct ioprio_blkg *ioprio_blkg = pd_to_ioprio(pd);
kfree(ioprio_blkg);
}
static struct blkcg_policy_data *ioprio_alloc_cpd(gfp_t gfp)
{
struct ioprio_blkcg *blkcg;
blkcg = kzalloc(sizeof(*blkcg), gfp);
if (!blkcg)
return NULL;
blkcg->prio_policy = POLICY_NO_CHANGE;
return &blkcg->cpd;
}
static void ioprio_free_cpd(struct blkcg_policy_data *cpd)
{
struct ioprio_blkcg *blkcg = container_of(cpd, typeof(*blkcg), cpd);
kfree(blkcg);
}
#define IOPRIO_ATTRS \
{ \
.name = "prio.class", \
.seq_show = ioprio_show_prio_policy, \
.write = ioprio_set_prio_policy, \
}, \
{ } /* sentinel */
/* cgroup v2 attributes */
static struct cftype ioprio_files[] = {
IOPRIO_ATTRS
};
/* cgroup v1 attributes */
static struct cftype ioprio_legacy_files[] = {
IOPRIO_ATTRS
};
static struct blkcg_policy ioprio_policy = {
.dfl_cftypes = ioprio_files,
.legacy_cftypes = ioprio_legacy_files,
.cpd_alloc_fn = ioprio_alloc_cpd,
.cpd_free_fn = ioprio_free_cpd,
.pd_alloc_fn = ioprio_alloc_pd,
.pd_free_fn = ioprio_free_pd,
};
struct blk_ioprio {
struct rq_qos rqos;
};
static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq,
struct bio *bio)
{
struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio);
/*
* Except for IOPRIO_CLASS_NONE, higher I/O priority numbers
* correspond to a lower priority. Hence, the max_t() below selects
* the lower priority of bi_ioprio and the cgroup I/O priority class.
* If the cgroup policy has been set to POLICY_NO_CHANGE == 0, the
* bio I/O priority is not modified. If the bio I/O priority equals
* IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio.
*/
bio->bi_ioprio = max_t(u16, bio->bi_ioprio,
IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0));
}
static void blkcg_ioprio_exit(struct rq_qos *rqos)
{
struct blk_ioprio *blkioprio_blkg =
container_of(rqos, typeof(*blkioprio_blkg), rqos);
blkcg_deactivate_policy(rqos->q, &ioprio_policy);
kfree(blkioprio_blkg);
}
static struct rq_qos_ops blkcg_ioprio_ops = {
.track = blkcg_ioprio_track,
.exit = blkcg_ioprio_exit,
};
int blk_ioprio_init(struct request_queue *q)
{
struct blk_ioprio *blkioprio_blkg;
struct rq_qos *rqos;
int ret;
blkioprio_blkg = kzalloc(sizeof(*blkioprio_blkg), GFP_KERNEL);
if (!blkioprio_blkg)
return -ENOMEM;
ret = blkcg_activate_policy(q, &ioprio_policy);
if (ret) {
kfree(blkioprio_blkg);
return ret;
}
rqos = &blkioprio_blkg->rqos;
rqos->id = RQ_QOS_IOPRIO;
rqos->ops = &blkcg_ioprio_ops;
rqos->q = q;
/*
* Registering the rq-qos policy after activating the blk-cgroup
* policy guarantees that ioprio_blkcg_from_bio(bio) != NULL in the
* rq-qos callbacks.
*/
rq_qos_add(q, rqos);
return 0;
}
static int __init ioprio_init(void)
{
return blkcg_policy_register(&ioprio_policy);
}
static void __exit ioprio_exit(void)
{
blkcg_policy_unregister(&ioprio_policy);
}
module_init(ioprio_init);
module_exit(ioprio_exit);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...