Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node: BUG: unable to handle kernel paging request at ffffc90008963690 IP: __wake_up_bit+0x20/0x70 Oops: 0000 [#1] SMP CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80 Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015 task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000 RIP: 0010:[<ffffffff810dff80>] [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP: 0018:ffff880017b97be8 EFLAGS: 00010246 RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9 RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648 RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800 R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000 FS: 00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0 Call Trace: unlock_page+0x6d/0x70 generic_write_end+0x53/0xb0 xfs_vm_write_end+0x29/0x80 [xfs] generic_perform_write+0x10a/0x1e0 xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs] xfs_file_write_iter+0x79/0x120 [xfs] __vfs_write+0xd4/0x110 vfs_write+0xac/0x1c0 SyS_write+0x58/0xd0 system_call_fastpath+0x12/0x76 Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48 RIP [<ffffffff810dff80>] __wake_up_bit+0x20/0x70 RSP <ffff880017b97be8> CR2: ffffc90008963690 Reproduce method (re-add a node):: Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic) This seems an use-after-free problem, and the root cause is zone->wait_table was not set to *NULL* after free it in try_offline_node. When hot re-add a node, we will reuse the pgdat of it, so does the zone struct, and when add pages to the target zone, it will init the zone first (including the wait_table) if the zone is not initialized. The judgement of zone initialized is based on zone->wait_table: static inline bool zone_is_initialized(struct zone *zone) { return !!zone->wait_table; } so if we do not set the zone->wait_table to *NULL* after free it, the memory hotplug routine will skip the init of new zone when hot re-add the node, and the wait_table still points to the freed memory, then we will access the invalid address when trying to wake up the waiting people after the i/o operation with the page is done, such as mentioned above. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com> Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.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 5879ae5
proc.c
/*
* Scatterlist Cryptographic API.
*
* Procfs information.
*
* Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
* Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
*/
#include <linux/atomic.h>
#include <linux/init.h>
#include <linux/crypto.h>
#include <linux/module.h> /* for module_name() */
#include <linux/rwsem.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include "internal.h"
#ifdef CONFIG_CRYPTO_FIPS
static struct ctl_table crypto_sysctl_table[] = {
{
.procname = "fips_enabled",
.data = &fips_enabled,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec
},
{}
};
static struct ctl_table crypto_dir_table[] = {
{
.procname = "crypto",
.mode = 0555,
.child = crypto_sysctl_table
},
{}
};
static struct ctl_table_header *crypto_sysctls;
static void crypto_proc_fips_init(void)
{
crypto_sysctls = register_sysctl_table(crypto_dir_table);
}
static void crypto_proc_fips_exit(void)
{
if (crypto_sysctls)
unregister_sysctl_table(crypto_sysctls);
}
#else
#define crypto_proc_fips_init()
#define crypto_proc_fips_exit()
#endif
static void *c_start(struct seq_file *m, loff_t *pos)
{
down_read(&crypto_alg_sem);
return seq_list_start(&crypto_alg_list, *pos);
}
static void *c_next(struct seq_file *m, void *p, loff_t *pos)
{
return seq_list_next(p, &crypto_alg_list, pos);
}
static void c_stop(struct seq_file *m, void *p)
{
up_read(&crypto_alg_sem);
}
static int c_show(struct seq_file *m, void *p)
{
struct crypto_alg *alg = list_entry(p, struct crypto_alg, cra_list);
seq_printf(m, "name : %s\n", alg->cra_name);
seq_printf(m, "driver : %s\n", alg->cra_driver_name);
seq_printf(m, "module : %s\n", module_name(alg->cra_module));
seq_printf(m, "priority : %d\n", alg->cra_priority);
seq_printf(m, "refcnt : %d\n", atomic_read(&alg->cra_refcnt));
seq_printf(m, "selftest : %s\n",
(alg->cra_flags & CRYPTO_ALG_TESTED) ?
"passed" : "unknown");
seq_printf(m, "internal : %s\n",
(alg->cra_flags & CRYPTO_ALG_INTERNAL) ?
"yes" : "no");
if (alg->cra_flags & CRYPTO_ALG_LARVAL) {
seq_printf(m, "type : larval\n");
seq_printf(m, "flags : 0x%x\n", alg->cra_flags);
goto out;
}
if (alg->cra_type && alg->cra_type->show) {
alg->cra_type->show(m, alg);
goto out;
}
switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) {
case CRYPTO_ALG_TYPE_CIPHER:
seq_printf(m, "type : cipher\n");
seq_printf(m, "blocksize : %u\n", alg->cra_blocksize);
seq_printf(m, "min keysize : %u\n",
alg->cra_cipher.cia_min_keysize);
seq_printf(m, "max keysize : %u\n",
alg->cra_cipher.cia_max_keysize);
break;
case CRYPTO_ALG_TYPE_COMPRESS:
seq_printf(m, "type : compression\n");
break;
default:
seq_printf(m, "type : unknown\n");
break;
}
out:
seq_putc(m, '\n');
return 0;
}
static const struct seq_operations crypto_seq_ops = {
.start = c_start,
.next = c_next,
.stop = c_stop,
.show = c_show
};
static int crypto_info_open(struct inode *inode, struct file *file)
{
return seq_open(file, &crypto_seq_ops);
}
static const struct file_operations proc_crypto_ops = {
.open = crypto_info_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
};
void __init crypto_init_proc(void)
{
proc_create("crypto", 0, NULL, &proc_crypto_ops);
crypto_proc_fips_init();
}
void __exit crypto_exit_proc(void)
{
crypto_proc_fips_exit();
remove_proc_entry("crypto", NULL);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...