Revision 082cd4ec240b8734a82a89ffb890216ac98fec68 authored by Ye Bin on 06 May 2021, 14:10:42 UTC, committed by Theodore Ts'o on 06 June 2021, 14:09:55 UTC
We got follow bug_on when run fsstress with injecting IO fault: [130747.323114] kernel BUG at fs/ext4/extents_status.c:762! [130747.323117] Internal error: Oops - BUG: 0 [#1] SMP ...... [130747.334329] Call trace: [130747.334553] ext4_es_cache_extent+0x150/0x168 [ext4] [130747.334975] ext4_cache_extents+0x64/0xe8 [ext4] [130747.335368] ext4_find_extent+0x300/0x330 [ext4] [130747.335759] ext4_ext_map_blocks+0x74/0x1178 [ext4] [130747.336179] ext4_map_blocks+0x2f4/0x5f0 [ext4] [130747.336567] ext4_mpage_readpages+0x4a8/0x7a8 [ext4] [130747.336995] ext4_readpage+0x54/0x100 [ext4] [130747.337359] generic_file_buffered_read+0x410/0xae8 [130747.337767] generic_file_read_iter+0x114/0x190 [130747.338152] ext4_file_read_iter+0x5c/0x140 [ext4] [130747.338556] __vfs_read+0x11c/0x188 [130747.338851] vfs_read+0x94/0x150 [130747.339110] ksys_read+0x74/0xf0 This patch's modification is according to Jan Kara's suggestion in: https://patchwork.ozlabs.org/project/linux-ext4/patch/20210428085158.3728201-1-yebin10@huawei.com/ "I see. Now I understand your patch. Honestly, seeing how fragile is trying to fix extent tree after split has failed in the middle, I would probably go even further and make sure we fix the tree properly in case of ENOSPC and EDQUOT (those are easily user triggerable). Anything else indicates a HW problem or fs corruption so I'd rather leave the extent tree as is and don't try to fix it (which also means we will not create overlapping extents)." Cc: stable@kernel.org Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210506141042.3298679-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
1 parent b45f189
shuffle.c
// SPDX-License-Identifier: GPL-2.0
// Copyright(c) 2018 Intel Corporation. All rights reserved.
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/mmzone.h>
#include <linux/random.h>
#include <linux/moduleparam.h>
#include "internal.h"
#include "shuffle.h"
DEFINE_STATIC_KEY_FALSE(page_alloc_shuffle_key);
static bool shuffle_param;
static int shuffle_show(char *buffer, const struct kernel_param *kp)
{
return sprintf(buffer, "%c\n", shuffle_param ? 'Y' : 'N');
}
static __meminit int shuffle_store(const char *val,
const struct kernel_param *kp)
{
int rc = param_set_bool(val, kp);
if (rc < 0)
return rc;
if (shuffle_param)
static_branch_enable(&page_alloc_shuffle_key);
return 0;
}
module_param_call(shuffle, shuffle_store, shuffle_show, &shuffle_param, 0400);
/*
* For two pages to be swapped in the shuffle, they must be free (on a
* 'free_area' lru), have the same order, and have the same migratetype.
*/
static struct page * __meminit shuffle_valid_page(struct zone *zone,
unsigned long pfn, int order)
{
struct page *page = pfn_to_online_page(pfn);
/*
* Given we're dealing with randomly selected pfns in a zone we
* need to ask questions like...
*/
/* ... is the page managed by the buddy? */
if (!page)
return NULL;
/* ... is the page assigned to the same zone? */
if (page_zone(page) != zone)
return NULL;
/* ...is the page free and currently on a free_area list? */
if (!PageBuddy(page))
return NULL;
/*
* ...is the page on the same list as the page we will
* shuffle it with?
*/
if (buddy_order(page) != order)
return NULL;
return page;
}
/*
* Fisher-Yates shuffle the freelist which prescribes iterating through an
* array, pfns in this case, and randomly swapping each entry with another in
* the span, end_pfn - start_pfn.
*
* To keep the implementation simple it does not attempt to correct for sources
* of bias in the distribution, like modulo bias or pseudo-random number
* generator bias. I.e. the expectation is that this shuffling raises the bar
* for attacks that exploit the predictability of page allocations, but need not
* be a perfect shuffle.
*/
#define SHUFFLE_RETRY 10
void __meminit __shuffle_zone(struct zone *z)
{
unsigned long i, flags;
unsigned long start_pfn = z->zone_start_pfn;
unsigned long end_pfn = zone_end_pfn(z);
const int order = SHUFFLE_ORDER;
const int order_pages = 1 << order;
spin_lock_irqsave(&z->lock, flags);
start_pfn = ALIGN(start_pfn, order_pages);
for (i = start_pfn; i < end_pfn; i += order_pages) {
unsigned long j;
int migratetype, retry;
struct page *page_i, *page_j;
/*
* We expect page_i, in the sub-range of a zone being added
* (@start_pfn to @end_pfn), to more likely be valid compared to
* page_j randomly selected in the span @zone_start_pfn to
* @spanned_pages.
*/
page_i = shuffle_valid_page(z, i, order);
if (!page_i)
continue;
for (retry = 0; retry < SHUFFLE_RETRY; retry++) {
/*
* Pick a random order aligned page in the zone span as
* a swap target. If the selected pfn is a hole, retry
* up to SHUFFLE_RETRY attempts find a random valid pfn
* in the zone.
*/
j = z->zone_start_pfn +
ALIGN_DOWN(get_random_long() % z->spanned_pages,
order_pages);
page_j = shuffle_valid_page(z, j, order);
if (page_j && page_j != page_i)
break;
}
if (retry >= SHUFFLE_RETRY) {
pr_debug("%s: failed to swap %#lx\n", __func__, i);
continue;
}
/*
* Each migratetype corresponds to its own list, make sure the
* types match otherwise we're moving pages to lists where they
* do not belong.
*/
migratetype = get_pageblock_migratetype(page_i);
if (get_pageblock_migratetype(page_j) != migratetype) {
pr_debug("%s: migratetype mismatch %#lx\n", __func__, i);
continue;
}
list_swap(&page_i->lru, &page_j->lru);
pr_debug("%s: swap: %#lx -> %#lx\n", __func__, i, j);
/* take it easy on the zone lock */
if ((i % (100 * order_pages)) == 0) {
spin_unlock_irqrestore(&z->lock, flags);
cond_resched();
spin_lock_irqsave(&z->lock, flags);
}
}
spin_unlock_irqrestore(&z->lock, flags);
}
/**
* shuffle_free_memory - reduce the predictability of the page allocator
* @pgdat: node page data
*/
void __meminit __shuffle_free_memory(pg_data_t *pgdat)
{
struct zone *z;
for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
shuffle_zone(z);
}
bool shuffle_pick_tail(void)
{
static u64 rand;
static u8 rand_bits;
bool ret;
/*
* The lack of locking is deliberate. If 2 threads race to
* update the rand state it just adds to the entropy.
*/
if (rand_bits == 0) {
rand_bits = 64;
rand = get_random_u64();
}
ret = rand & 1;
rand_bits--;
rand >>= 1;
return ret;
}
Computing file changes ...