mirror of
https://github.com/torvalds/linux.git
synced 2024-11-29 23:51:37 +00:00
d0505e9f7d
In the current implementation of soft offline, if non-LRU page is met,
all the slab caches will be dropped to free the page then offline. But
if the page is not slab page all the effort is wasted in vain. Even
though it is a slab page, it is not guaranteed the page could be freed
at all.
However the side effect and cost is quite high. It does not only drop
the slab caches, but also may drop a significant amount of page caches
which are associated with inode caches. It could make the most
workingset gone in order to just offline a page. And the offline is not
guaranteed to succeed at all, actually I really doubt the success rate
for real life workload.
Furthermore the worse consequence is the system may be locked up and
unusable since the page cache release may incur huge amount of works
queued for memcg release.
Actually we ran into such unpleasant case in our production environment.
Firstly, the workqueue of memory_failure_work_func is locked up as
below:
BUG: workqueue lockup - pool cpus=1 node=0 flags=0x0 nice=0 stuck for 53s!
Showing busy workqueues and worker pools:
workqueue events: flags=0x0
pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=14/256 refcnt=15
in-flight: 409271:memory_failure_work_func
pending: kfree_rcu_work, kfree_rcu_monitor, kfree_rcu_work, rht_deferred_worker, rht_deferred_worker, rht_deferred_worker, rht_deferred_worker, kfree_rcu_work, kfree_rcu_work, kfree_rcu_work, kfree_rcu_work, drain_local_stock, kfree_rcu_work
workqueue mm_percpu_wq: flags=0x8
pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=1/256 refcnt=2
pending: vmstat_update
workqueue cgroup_destroy: flags=0x0
pwq 2: cpus=1 node=0 flags=0x0 nice=0 active=1/1 refcnt=12072
pending: css_release_work_fn
There were over 12K css_release_work_fn queued, and this caused a few
lockups due to the contention of worker pool lock with IRQ disabled, for
example:
NMI watchdog: Watchdog detected hard LOCKUP on cpu 1
Modules linked in: amd64_edac_mod edac_mce_amd crct10dif_pclmul crc32_pclmul ghash_clmulni_intel xt_DSCP iptable_mangle kvm_amd bpfilter vfat fat acpi_ipmi i2c_piix4 usb_storage ipmi_si k10temp i2c_core ipmi_devintf ipmi_msghandler acpi_cpufreq sch_fq_codel xfs libcrc32c crc32c_intel mlx5_core mlxfw nvme xhci_pci ptp nvme_core pps_core xhci_hcd
CPU: 1 PID: 205500 Comm: kworker/1:0 Tainted: G L 5.10.32-t1.el7.twitter.x86_64 #1
Hardware name: TYAN F5AMT /z /S8026GM2NRE-CGN, BIOS V8.030 03/30/2021
Workqueue: events memory_failure_work_func
RIP: 0010:queued_spin_lock_slowpath+0x41/0x1a0
Code: 41 f0 0f ba 2f 08 0f 92 c0 0f b6 c0 c1 e0 08 89 c2 8b 07 30 e4 09 d0 a9 00 01 ff ff 75 1b 85 c0 74 0e 8b 07 84 c0 74 08 f3 90 <8b> 07 84 c0 75 f8 b8 01 00 00 00 66 89 07 c3 f6 c4 01 75 04 c6 47
RSP: 0018:ffff9b2ac278f900 EFLAGS: 00000002
RAX: 0000000000480101 RBX: ffff8ce98ce71800 RCX: 0000000000000084
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8ce98ce6a140
RBP: 00000000000284c8 R08: ffffd7248dcb6808 R09: 0000000000000000
R10: 0000000000000003 R11: ffff9b2ac278f9b0 R12: 0000000000000001
R13: ffff8cb44dab9c00 R14: ffffffffbd1ce6a0 R15: ffff8cacaa37f068
FS: 0000000000000000(0000) GS:ffff8ce98ce40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fcf6e8cb000 CR3: 0000000a0c60a000 CR4: 0000000000350ee0
Call Trace:
__queue_work+0xd6/0x3c0
queue_work_on+0x1c/0x30
uncharge_batch+0x10e/0x110
mem_cgroup_uncharge_list+0x6d/0x80
release_pages+0x37f/0x3f0
__pagevec_release+0x1c/0x50
__invalidate_mapping_pages+0x348/0x380
inode_lru_isolate+0x10a/0x160
__list_lru_walk_one+0x7b/0x170
list_lru_walk_one+0x4a/0x60
prune_icache_sb+0x37/0x50
super_cache_scan+0x123/0x1a0
do_shrink_slab+0x10c/0x2c0
shrink_slab+0x1f1/0x290
drop_slab_node+0x4d/0x70
soft_offline_page+0x1ac/0x5b0
memory_failure_work_func+0x6a/0x90
process_one_work+0x19e/0x340
worker_thread+0x30/0x360
kthread+0x116/0x130
The lockup made the machine is quite unusable. And it also made the
most workingset gone, the reclaimabled slab caches were reduced from 12G
to 300MB, the page caches were decreased from 17G to 4G.
But the most disappointing thing is all the effort doesn't make the page
offline, it just returns:
soft_offline: 0x1469f2: unknown non LRU page type 5ffff0000000000 ()
It seems the aggressive behavior for non-LRU page didn't pay back, so it
doesn't make too much sense to keep it considering the terrible side
effect.
Link: https://lkml.kernel.org/r/20210819054116.266126-1-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Reported-by: David Mackey <tdmackey@twitter.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
111 lines
2.6 KiB
C
111 lines
2.6 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Inject a hwpoison memory failure on a arbitrary pfn */
|
|
#include <linux/module.h>
|
|
#include <linux/debugfs.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/hugetlb.h>
|
|
#include "internal.h"
|
|
|
|
static struct dentry *hwpoison_dir;
|
|
|
|
static int hwpoison_inject(void *data, u64 val)
|
|
{
|
|
unsigned long pfn = val;
|
|
struct page *p;
|
|
struct page *hpage;
|
|
int err;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
if (!pfn_valid(pfn))
|
|
return -ENXIO;
|
|
|
|
p = pfn_to_page(pfn);
|
|
hpage = compound_head(p);
|
|
|
|
if (!hwpoison_filter_enable)
|
|
goto inject;
|
|
|
|
shake_page(hpage);
|
|
/*
|
|
* This implies unable to support non-LRU pages.
|
|
*/
|
|
if (!PageLRU(hpage) && !PageHuge(p))
|
|
return 0;
|
|
|
|
/*
|
|
* do a racy check to make sure PG_hwpoison will only be set for
|
|
* the targeted owner (or on a free page).
|
|
* memory_failure() will redo the check reliably inside page lock.
|
|
*/
|
|
err = hwpoison_filter(hpage);
|
|
if (err)
|
|
return 0;
|
|
|
|
inject:
|
|
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
|
|
return memory_failure(pfn, 0);
|
|
}
|
|
|
|
static int hwpoison_unpoison(void *data, u64 val)
|
|
{
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
return unpoison_memory(val);
|
|
}
|
|
|
|
DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
|
|
DEFINE_DEBUGFS_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");
|
|
|
|
static void pfn_inject_exit(void)
|
|
{
|
|
debugfs_remove_recursive(hwpoison_dir);
|
|
}
|
|
|
|
static int pfn_inject_init(void)
|
|
{
|
|
hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
|
|
|
|
/*
|
|
* Note that the below poison/unpoison interfaces do not involve
|
|
* hardware status change, hence do not require hardware support.
|
|
* They are mainly for testing hwpoison in software level.
|
|
*/
|
|
debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir, NULL,
|
|
&hwpoison_fops);
|
|
|
|
debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir, NULL,
|
|
&unpoison_fops);
|
|
|
|
debugfs_create_u32("corrupt-filter-enable", 0600, hwpoison_dir,
|
|
&hwpoison_filter_enable);
|
|
|
|
debugfs_create_u32("corrupt-filter-dev-major", 0600, hwpoison_dir,
|
|
&hwpoison_filter_dev_major);
|
|
|
|
debugfs_create_u32("corrupt-filter-dev-minor", 0600, hwpoison_dir,
|
|
&hwpoison_filter_dev_minor);
|
|
|
|
debugfs_create_u64("corrupt-filter-flags-mask", 0600, hwpoison_dir,
|
|
&hwpoison_filter_flags_mask);
|
|
|
|
debugfs_create_u64("corrupt-filter-flags-value", 0600, hwpoison_dir,
|
|
&hwpoison_filter_flags_value);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir,
|
|
&hwpoison_filter_memcg);
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
|
|
module_init(pfn_inject_init);
|
|
module_exit(pfn_inject_exit);
|
|
MODULE_LICENSE("GPL");
|