Revision c9d398fa237882ea07167e23bcfc5e6847066518 authored by Naoya Horiguchi on 31 March 2017, 22:11:55 UTC, committed by Linus Torvalds on 01 April 2017, 00:13:30 UTC
I found the race condition which triggers the following bug when move_pages() and soft offline are called on a single hugetlb page concurrently. Soft offlining page 0x119400 at 0x700000000000 BUG: unable to handle kernel paging request at ffffea0011943820 IP: follow_huge_pmd+0x143/0x190 PGD 7ffd2067 PUD 7ffd1067 PMD 0 [61163.582052] Oops: 0000 [#1] SMP Modules linked in: binfmt_misc ppdev virtio_balloon parport_pc pcspkr i2c_piix4 parport i2c_core acpi_cpufreq ip_tables xfs libcrc32c ata_generic pata_acpi virtio_blk 8139too crc32c_intel ata_piix serio_raw libata virtio_pci 8139cp virtio_ring virtio mii floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: cap_check] CPU: 0 PID: 22573 Comm: iterate_numa_mo Tainted: P OE 4.11.0-rc2-mm1+ #2 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:follow_huge_pmd+0x143/0x190 RSP: 0018:ffffc90004bdbcd0 EFLAGS: 00010202 RAX: 0000000465003e80 RBX: ffffea0004e34d30 RCX: 00003ffffffff000 RDX: 0000000011943800 RSI: 0000000000080001 RDI: 0000000465003e80 RBP: ffffc90004bdbd18 R08: 0000000000000000 R09: ffff880138d34000 R10: ffffea0004650000 R11: 0000000000c363b0 R12: ffffea0011943800 R13: ffff8801b8d34000 R14: ffffea0000000000 R15: 000077ff80000000 FS: 00007fc977710740(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffea0011943820 CR3: 000000007a746000 CR4: 00000000001406f0 Call Trace: follow_page_mask+0x270/0x550 SYSC_move_pages+0x4ea/0x8f0 SyS_move_pages+0xe/0x10 do_syscall_64+0x67/0x180 entry_SYSCALL64_slow_path+0x25/0x25 RIP: 0033:0x7fc976e03949 RSP: 002b:00007ffe72221d88 EFLAGS: 00000246 ORIG_RAX: 0000000000000117 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc976e03949 RDX: 0000000000c22390 RSI: 0000000000001400 RDI: 0000000000005827 RBP: 00007ffe72221e00 R08: 0000000000c2c3a0 R09: 0000000000000004 R10: 0000000000c363b0 R11: 0000000000000246 R12: 0000000000400650 R13: 00007ffe72221ee0 R14: 0000000000000000 R15: 0000000000000000 Code: 81 e4 ff ff 1f 00 48 21 c2 49 c1 ec 0c 48 c1 ea 0c 4c 01 e2 49 bc 00 00 00 00 00 ea ff ff 48 c1 e2 06 49 01 d4 f6 45 bc 04 74 90 <49> 8b 7c 24 20 40 f6 c7 01 75 2b 4c 89 e7 8b 47 1c 85 c0 7e 2a RIP: follow_huge_pmd+0x143/0x190 RSP: ffffc90004bdbcd0 CR2: ffffea0011943820 ---[ end trace e4f81353a2d23232 ]--- Kernel panic - not syncing: Fatal exception Kernel Offset: disabled This bug is triggered when pmd_present() returns true for non-present hugetlb, so fixing the present check in follow_huge_pmd() prevents it. Using pmd_present() to determine present/non-present for hugetlb is not correct, because pmd_present() checks multiple bits (not only _PAGE_PRESENT) for historical reason and it can misjudge hugetlb state. Fixes: e66f17ff7177 ("mm/hugetlb: take page table lock in follow_huge_pmd()") Link: http://lkml.kernel.org/r/1490149898-20231-1-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Hugh Dickins <hughd@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: <stable@vger.kernel.org> [4.0+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 0cefabd
nsproxy.c
/*
* Copyright (C) 2006 IBM Corporation
*
* Author: Serge Hallyn <serue@us.ibm.com>
*
* 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, version 2 of the
* License.
*
* Jun 2006 - namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*/
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/init_task.h>
#include <linux/mnt_namespace.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <net/net_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/proc_ns.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/cgroup.h>
static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = {
.count = ATOMIC_INIT(1),
.uts_ns = &init_uts_ns,
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
.ipc_ns = &init_ipc_ns,
#endif
.mnt_ns = NULL,
.pid_ns_for_children = &init_pid_ns,
#ifdef CONFIG_NET
.net_ns = &init_net,
#endif
#ifdef CONFIG_CGROUPS
.cgroup_ns = &init_cgroup_ns,
#endif
};
static inline struct nsproxy *create_nsproxy(void)
{
struct nsproxy *nsproxy;
nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
if (nsproxy)
atomic_set(&nsproxy->count, 1);
return nsproxy;
}
/*
* Create new nsproxy and all of its the associated namespaces.
* Return the newly created nsproxy. Do not attach this to the task,
* leave it to the caller to do proper locking and attach it to task.
*/
static struct nsproxy *create_new_namespaces(unsigned long flags,
struct task_struct *tsk, struct user_namespace *user_ns,
struct fs_struct *new_fs)
{
struct nsproxy *new_nsp;
int err;
new_nsp = create_nsproxy();
if (!new_nsp)
return ERR_PTR(-ENOMEM);
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
if (IS_ERR(new_nsp->mnt_ns)) {
err = PTR_ERR(new_nsp->mnt_ns);
goto out_ns;
}
new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
if (IS_ERR(new_nsp->uts_ns)) {
err = PTR_ERR(new_nsp->uts_ns);
goto out_uts;
}
new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
if (IS_ERR(new_nsp->ipc_ns)) {
err = PTR_ERR(new_nsp->ipc_ns);
goto out_ipc;
}
new_nsp->pid_ns_for_children =
copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
if (IS_ERR(new_nsp->pid_ns_for_children)) {
err = PTR_ERR(new_nsp->pid_ns_for_children);
goto out_pid;
}
new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
tsk->nsproxy->cgroup_ns);
if (IS_ERR(new_nsp->cgroup_ns)) {
err = PTR_ERR(new_nsp->cgroup_ns);
goto out_cgroup;
}
new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
goto out_net;
}
return new_nsp;
out_net:
put_cgroup_ns(new_nsp->cgroup_ns);
out_cgroup:
if (new_nsp->pid_ns_for_children)
put_pid_ns(new_nsp->pid_ns_for_children);
out_pid:
if (new_nsp->ipc_ns)
put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
if (new_nsp->uts_ns)
put_uts_ns(new_nsp->uts_ns);
out_uts:
if (new_nsp->mnt_ns)
put_mnt_ns(new_nsp->mnt_ns);
out_ns:
kmem_cache_free(nsproxy_cachep, new_nsp);
return ERR_PTR(err);
}
/*
* called from clone. This now handles copy for nsproxy and all
* namespaces therein.
*/
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
{
struct nsproxy *old_ns = tsk->nsproxy;
struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
struct nsproxy *new_ns;
if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWPID | CLONE_NEWNET |
CLONE_NEWCGROUP)))) {
get_nsproxy(old_ns);
return 0;
}
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
/*
* CLONE_NEWIPC must detach from the undolist: after switching
* to a new ipc namespace, the semaphore arrays from the old
* namespace are unreachable. In clone parlance, CLONE_SYSVSEM
* means share undolist with parent, so we must forbid using
* it along with CLONE_NEWIPC.
*/
if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
(CLONE_NEWIPC | CLONE_SYSVSEM))
return -EINVAL;
new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
if (IS_ERR(new_ns))
return PTR_ERR(new_ns);
tsk->nsproxy = new_ns;
return 0;
}
void free_nsproxy(struct nsproxy *ns)
{
if (ns->mnt_ns)
put_mnt_ns(ns->mnt_ns);
if (ns->uts_ns)
put_uts_ns(ns->uts_ns);
if (ns->ipc_ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns_for_children)
put_pid_ns(ns->pid_ns_for_children);
put_cgroup_ns(ns->cgroup_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
/*
* Called from unshare. Unshare all the namespaces part of nsproxy.
* On success, returns the new nsproxy.
*/
int unshare_nsproxy_namespaces(unsigned long unshare_flags,
struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
{
struct user_namespace *user_ns;
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP)))
return 0;
user_ns = new_cred ? new_cred->user_ns : current_user_ns();
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
new_fs ? new_fs : current->fs);
if (IS_ERR(*new_nsp)) {
err = PTR_ERR(*new_nsp);
goto out;
}
out:
return err;
}
void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
{
struct nsproxy *ns;
might_sleep();
task_lock(p);
ns = p->nsproxy;
p->nsproxy = new;
task_unlock(p);
if (ns && atomic_dec_and_test(&ns->count))
free_nsproxy(ns);
}
void exit_task_namespaces(struct task_struct *p)
{
switch_task_namespaces(p, NULL);
}
SYSCALL_DEFINE2(setns, int, fd, int, nstype)
{
struct task_struct *tsk = current;
struct nsproxy *new_nsproxy;
struct file *file;
struct ns_common *ns;
int err;
file = proc_ns_fget(fd);
if (IS_ERR(file))
return PTR_ERR(file);
err = -EINVAL;
ns = get_proc_ns(file_inode(file));
if (nstype && (ns->ops->type != nstype))
goto out;
new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
if (IS_ERR(new_nsproxy)) {
err = PTR_ERR(new_nsproxy);
goto out;
}
err = ns->ops->install(new_nsproxy, ns);
if (err) {
free_nsproxy(new_nsproxy);
goto out;
}
switch_task_namespaces(tsk, new_nsproxy);
out:
fput(file);
return err;
}
int __init nsproxy_cache_init(void)
{
nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
return 0;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...