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
Raw File
fs_struct.c
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/path.h>
#include <linux/slab.h>
#include <linux/fs_struct.h>
#include "internal.h"

/*
 * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
 * It can block.
 */
void set_fs_root(struct fs_struct *fs, const struct path *path)
{
	struct path old_root;

	path_get(path);
	spin_lock(&fs->lock);
	write_seqcount_begin(&fs->seq);
	old_root = fs->root;
	fs->root = *path;
	write_seqcount_end(&fs->seq);
	spin_unlock(&fs->lock);
	if (old_root.dentry)
		path_put(&old_root);
}

/*
 * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
 * It can block.
 */
void set_fs_pwd(struct fs_struct *fs, const struct path *path)
{
	struct path old_pwd;

	path_get(path);
	spin_lock(&fs->lock);
	write_seqcount_begin(&fs->seq);
	old_pwd = fs->pwd;
	fs->pwd = *path;
	write_seqcount_end(&fs->seq);
	spin_unlock(&fs->lock);

	if (old_pwd.dentry)
		path_put(&old_pwd);
}

static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
{
	if (likely(p->dentry != old->dentry || p->mnt != old->mnt))
		return 0;
	*p = *new;
	return 1;
}

void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
{
	struct task_struct *g, *p;
	struct fs_struct *fs;
	int count = 0;

	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		task_lock(p);
		fs = p->fs;
		if (fs) {
			int hits = 0;
			spin_lock(&fs->lock);
			write_seqcount_begin(&fs->seq);
			hits += replace_path(&fs->root, old_root, new_root);
			hits += replace_path(&fs->pwd, old_root, new_root);
			write_seqcount_end(&fs->seq);
			while (hits--) {
				count++;
				path_get(new_root);
			}
			spin_unlock(&fs->lock);
		}
		task_unlock(p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);
	while (count--)
		path_put(old_root);
}

void free_fs_struct(struct fs_struct *fs)
{
	path_put(&fs->root);
	path_put(&fs->pwd);
	kmem_cache_free(fs_cachep, fs);
}

void exit_fs(struct task_struct *tsk)
{
	struct fs_struct *fs = tsk->fs;

	if (fs) {
		int kill;
		task_lock(tsk);
		spin_lock(&fs->lock);
		tsk->fs = NULL;
		kill = !--fs->users;
		spin_unlock(&fs->lock);
		task_unlock(tsk);
		if (kill)
			free_fs_struct(fs);
	}
}

struct fs_struct *copy_fs_struct(struct fs_struct *old)
{
	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
	/* We don't need to lock fs - think why ;-) */
	if (fs) {
		fs->users = 1;
		fs->in_exec = 0;
		spin_lock_init(&fs->lock);
		seqcount_init(&fs->seq);
		fs->umask = old->umask;

		spin_lock(&old->lock);
		fs->root = old->root;
		path_get(&fs->root);
		fs->pwd = old->pwd;
		path_get(&fs->pwd);
		spin_unlock(&old->lock);
	}
	return fs;
}

int unshare_fs_struct(void)
{
	struct fs_struct *fs = current->fs;
	struct fs_struct *new_fs = copy_fs_struct(fs);
	int kill;

	if (!new_fs)
		return -ENOMEM;

	task_lock(current);
	spin_lock(&fs->lock);
	kill = !--fs->users;
	current->fs = new_fs;
	spin_unlock(&fs->lock);
	task_unlock(current);

	if (kill)
		free_fs_struct(fs);

	return 0;
}
EXPORT_SYMBOL_GPL(unshare_fs_struct);

int current_umask(void)
{
	return current->fs->umask;
}
EXPORT_SYMBOL(current_umask);

/* to be mentioned only in INIT_TASK */
struct fs_struct init_fs = {
	.users		= 1,
	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
	.seq		= SEQCNT_ZERO(init_fs.seq),
	.umask		= 0022,
};
back to top