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-mq-cpumap.c
// SPDX-License-Identifier: GPL-2.0
/*
* CPU <-> hardware queue mapping helpers
*
* Copyright (C) 2013-2014 Jens Axboe
*/
#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
static int queue_index(struct blk_mq_queue_map *qmap,
unsigned int nr_queues, const int q)
{
return qmap->queue_offset + (q % nr_queues);
}
static int get_first_sibling(unsigned int cpu)
{
unsigned int ret;
ret = cpumask_first(topology_sibling_cpumask(cpu));
if (ret < nr_cpu_ids)
return ret;
return cpu;
}
int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
{
unsigned int *map = qmap->mq_map;
unsigned int nr_queues = qmap->nr_queues;
unsigned int cpu, first_sibling, q = 0;
for_each_possible_cpu(cpu)
map[cpu] = -1;
/*
* Spread queues among present CPUs first for minimizing
* count of dead queues which are mapped by all un-present CPUs
*/
for_each_present_cpu(cpu) {
if (q >= nr_queues)
break;
map[cpu] = queue_index(qmap, nr_queues, q++);
}
for_each_possible_cpu(cpu) {
if (map[cpu] != -1)
continue;
/*
* First do sequential mapping between CPUs and queues.
* In case we still have CPUs to map, and we have some number of
* threads per cores then map sibling threads to the same queue
* for performance optimizations.
*/
if (q < nr_queues) {
map[cpu] = queue_index(qmap, nr_queues, q++);
} else {
first_sibling = get_first_sibling(cpu);
if (first_sibling == cpu)
map[cpu] = queue_index(qmap, nr_queues, q++);
else
map[cpu] = map[first_sibling];
}
}
return 0;
}
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
/**
* blk_mq_hw_queue_to_node - Look up the memory node for a hardware queue index
* @qmap: CPU to hardware queue map.
* @index: hardware queue index.
*
* We have no quick way of doing reverse lookups. This is only used at
* queue init time, so runtime isn't important.
*/
int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
{
int i;
for_each_possible_cpu(i) {
if (index == qmap->mq_map[i])
return cpu_to_node(i);
}
return NUMA_NO_NODE;
}
Computing file changes ...
