mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Minchan Kim](/assets/img/avatar_default.png)
While I was doing zram testing, I found sometimes decompression failed
since the compression buffer was corrupted. With investigation, I found
below commit calls cond_resched unconditionally so it could make a
problem in atomic context if the task is reschedule.
BUG: sleeping function called from invalid context at mm/vmalloc.c:108
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog
3 locks held by memhog/946:
#0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160
#1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160
#2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0
CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
Call Trace:
unmap_kernel_range_noflush+0x2eb/0x350
unmap_kernel_range+0x14/0x30
zs_unmap_object+0xd5/0xe0
zram_bvec_rw.isra.0+0x38c/0x8e0
zram_rw_page+0x90/0x101
bdev_write_page+0x92/0xe0
__swap_writepage+0x94/0x4a0
pageout+0xe3/0x3a0
shrink_page_list+0xb94/0xd60
shrink_inactive_list+0x158/0x460
We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which
contains the offending calling code) from zsmalloc.
Even though this option showed some amount improvement(e.g., 30%) in
some arm32 platforms, it has been headache to maintain since it have
abused APIs[1](e.g., unmap_kernel_range in atomic context).
Since we are approaching to deprecate 32bit machines and already made
the config option available for only builtin build since v5.8, lastly it
has been not default option in zsmalloc, it's time to drop the option
for better maintenance.
[1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@kernel.org
Fixes: e47110e905
("mm/vunmap: add cond_resched() in vunmap_pmd_range")
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Harish Sriram <harish@linux.ibm.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201117202916.GA3856507@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
59 lines
1.6 KiB
C
59 lines
1.6 KiB
C
/*
|
|
* zsmalloc memory allocator
|
|
*
|
|
* Copyright (C) 2011 Nitin Gupta
|
|
* Copyright (C) 2012, 2013 Minchan Kim
|
|
*
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
* You can choose the license that better fits your requirements.
|
|
*
|
|
* Released under the terms of 3-clause BSD License
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
*/
|
|
|
|
#ifndef _ZS_MALLOC_H_
|
|
#define _ZS_MALLOC_H_
|
|
|
|
#include <linux/types.h>
|
|
|
|
/*
|
|
* zsmalloc mapping modes
|
|
*
|
|
* NOTE: These only make a difference when a mapped object spans pages.
|
|
*/
|
|
enum zs_mapmode {
|
|
ZS_MM_RW, /* normal read-write mapping */
|
|
ZS_MM_RO, /* read-only (no copy-out at unmap time) */
|
|
ZS_MM_WO /* write-only (no copy-in at map time) */
|
|
/*
|
|
* NOTE: ZS_MM_WO should only be used for initializing new
|
|
* (uninitialized) allocations. Partial writes to already
|
|
* initialized allocations should use ZS_MM_RW to preserve the
|
|
* existing data.
|
|
*/
|
|
};
|
|
|
|
struct zs_pool_stats {
|
|
/* How many pages were migrated (freed) */
|
|
unsigned long pages_compacted;
|
|
};
|
|
|
|
struct zs_pool;
|
|
|
|
struct zs_pool *zs_create_pool(const char *name);
|
|
void zs_destroy_pool(struct zs_pool *pool);
|
|
|
|
unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags);
|
|
void zs_free(struct zs_pool *pool, unsigned long obj);
|
|
|
|
size_t zs_huge_class_size(struct zs_pool *pool);
|
|
|
|
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
|
|
enum zs_mapmode mm);
|
|
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
|
|
|
|
unsigned long zs_get_total_pages(struct zs_pool *pool);
|
|
unsigned long zs_compact(struct zs_pool *pool);
|
|
|
|
void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats);
|
|
#endif
|