| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 25 Nov 2015 21:50:06 +0900
From: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
To: Minchan Kim <minchan@...nel.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Kyeongdon Kim <kyeongdon.kim@....com>,
linux-kernel@...r.kernel.org,
Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
Sergey Senozhatsky <sergey.senozhatsky.work@...il.com>
Subject: [PATCH 2/2] zram: try vmalloc() after kmalloc()
From: Kyeongdon Kim <kyeongdon.kim@....com>
When we're using LZ4 multi compression streams for zram swap,
we found out page allocation failure message in system running test.
That was not only once, but a few(2 - 5 times per test).
Also, some failure cases were continually occurring to try allocation
order 3.
In order to make parallel compression private data, we should call
kzalloc() with order 2/3 in runtime(lzo/lz4). But if there is no order
2/3 size memory to allocate in that time, page allocation fails.
This patch makes to use vmalloc() as fallback of kmalloc(), this
prevents page alloc failure warning.
After using this, we never found warning message in running test, also
It could reduce process startup latency about 60-120ms in each case.
For reference a call trace :
Binder_1: page allocation failure: order:3, mode:0x10c0d0
CPU: 0 PID: 424 Comm: Binder_1 Tainted: GW 3.10.49-perf-g991d02b-dirty #20
Call trace:
[<ffffffc0002069c8>] dump_backtrace+0x0/0x270
[<ffffffc000206c48>] show_stack+0x10/0x1c
[<ffffffc000cb51c8>] dump_stack+0x1c/0x28
[<ffffffc0002bbfc8>] warn_alloc_failed+0xfc/0x11c
[<ffffffc0002bf518>] __alloc_pages_nodemask+0x724/0x7f0
[<ffffffc0002bf5f8>] __get_free_pages+0x14/0x5c
[<ffffffc0002ed6a4>] kmalloc_order_trace+0x38/0xd8
[<ffffffc0005d9738>] zcomp_lz4_create+0x2c/0x38
[<ffffffc0005d78f0>] zcomp_strm_alloc+0x34/0x78
[<ffffffc0005d7a58>] zcomp_strm_multi_find+0x124/0x1ec
[<ffffffc0005d7c14>] zcomp_strm_find+0xc/0x18
[<ffffffc0005d8fa0>] zram_bvec_rw+0x2fc/0x780
[<ffffffc0005d9680>] zram_make_request+0x25c/0x2d4
[<ffffffc00040f8ac>] generic_make_request+0x80/0xbc
[<ffffffc00040f98c>] submit_bio+0xa4/0x15c
[<ffffffc0002e8bb0>] __swap_writepage+0x218/0x230
[<ffffffc0002e8c04>] swap_writepage+0x3c/0x4c
[<ffffffc0002c7384>] shrink_page_list+0x51c/0x8d0
[<ffffffc0002c7e88>] shrink_inactive_list+0x3f8/0x60c
[<ffffffc0002c86c8>] shrink_lruvec+0x33c/0x4cc
[<ffffffc0002c8894>] shrink_zone+0x3c/0x100
[<ffffffc0002c8c10>] try_to_free_pages+0x2b8/0x54c
[<ffffffc0002bf308>] __alloc_pages_nodemask+0x514/0x7f0
[<ffffffc0002bf5f8>] __get_free_pages+0x14/0x5c
[<ffffffc0003446cc>] proc_info_read+0x50/0xe4
[<ffffffc0002f5204>] vfs_read+0xa0/0x12c
[<ffffffc0002f59c8>] SyS_read+0x44/0x74
DMA: 3397*4kB (MC) 26*8kB (RC) 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB
0*512kB 0*1024kB 0*2048kB 0*4096kB = 13796kB
[minchan: change vmalloc gfp and adding comment about gfp]
Signed-off-by: Kyeongdon Kim <kyeongdon.kim@....com>
Signed-off-by: Minchan Kim <minchan@...nel.org>
---
drivers/block/zram/zcomp.c | 12 ++++++++++--
drivers/block/zram/zcomp_lz4.c | 13 +++++++++++--
drivers/block/zram/zcomp_lzo.c | 13 +++++++++++--
3 files changed, 32 insertions(+), 6 deletions(-)
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 27e4472..8beb3d2 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -120,8 +120,16 @@ static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
/* allocate new zstrm stream */
zs->avail_strm++;
spin_unlock(&zs->strm_lock);
-
- zstrm = zcomp_strm_alloc(comp, GFP_NOIO);
+ /*
+ * This function could be called in swapout/fs write path
+ * so we couldn't use GFP_FS|IO. And it assumes we already
+ * have at least one stream in zram initialization so we
+ * don't do best effort to allocate more stream in here.
+ * A default stream will work well without further multiple
+ * stream. That's why we use __GFP_NORETRY|NOWARN|NOMEMALLOC.
+ */
+ zstrm = zcomp_strm_alloc(comp, GFP_NOIO | __GFP_NORETRY |
+ __GFP_NOWARN | __GFP_NOMEMALLOC);
if (!zstrm) {
spin_lock(&zs->strm_lock);
zs->avail_strm--;
diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c
index 47ab233..3fef593a 100644
--- a/drivers/block/zram/zcomp_lz4.c
+++ b/drivers/block/zram/zcomp_lz4.c
@@ -10,17 +10,26 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/lz4.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
#include "zcomp_lz4.h"
static void *zcomp_lz4_create(gfp_t flags)
{
- return kzalloc(LZ4_MEM_COMPRESS, flags);
+ void *ret;
+
+ ret = kzalloc(LZ4_MEM_COMPRESS, flags);
+ if (!ret)
+ ret = __vmalloc(LZ4_MEM_COMPRESS,
+ flags | __GFP_HIGHMEM,
+ PAGE_KERNEL);
+ return ret;
}
static void zcomp_lz4_destroy(void *private)
{
- kfree(private);
+ kvfree(private);
}
static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst,
diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c
index 3c6e506..25e588f 100644
--- a/drivers/block/zram/zcomp_lzo.c
+++ b/drivers/block/zram/zcomp_lzo.c
@@ -10,17 +10,26 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/lzo.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
#include "zcomp_lzo.h"
static void *lzo_create(gfp_t flags)
{
- return kzalloc(LZO1X_MEM_COMPRESS, flags);
+ void *ret;
+
+ ret = kzalloc(LZO1X_MEM_COMPRESS, flags);
+ if (!ret)
+ ret = __vmalloc(LZO1X_MEM_COMPRESS,
+ flags | __GFP_HIGHMEM,
+ PAGE_KERNEL);
+ return ret;
}
static void lzo_destroy(void *private)
{
- kfree(private);
+ kvfree(private);
}
static int lzo_compress(const unsigned char *src, unsigned char *dst,
--
2.6.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists