Move the migrate_prep outside the mmap_sem for the following system calls
1. sys_move_pages
2. sys_migrate_pages
3. sys_mbind()
It really does not matter when we flush the lru. The system is free to
add pages onto the lru even during migration which will make the page
migration either skip the page (mbind, migrate_pages) or return a busy
state (move_pages).
Fixes this lockdep warning (and potential deadlock):
Some VM place has
mmap_sem -> kevent_wq via lru_add_drain_all()
net/core/dev.c::dev_ioctl() has
rtnl_lock -> mmap_sem (*) the ioctl has copy_from_user() and it can do page fault.
linkwatch_event has
kevent_wq -> rtnl_lock
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
int err;
struct vm_area_struct *first, *vma, *prev;
int err;
struct vm_area_struct *first, *vma, *prev;
- if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-
- err = migrate_prep();
- if (err)
- return ERR_PTR(err);
- }
first = find_vma(mm, start);
if (!first)
first = find_vma(mm, start);
if (!first)
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
int busy = 0;
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
int busy = 0;
+ err = migrate_prep();
+ if (err)
+ return err;
+
down_read(&mm->mmap_sem);
err = migrate_vmas(mm, from_nodes, to_nodes, flags);
down_read(&mm->mmap_sem);
err = migrate_vmas(mm, from_nodes, to_nodes, flags);
start, start + len, mode, mode_flags,
nmask ? nodes_addr(*nmask)[0] : -1);
start, start + len, mode, mode_flags,
nmask ? nodes_addr(*nmask)[0] : -1);
+ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+
+ err = migrate_prep();
+ if (err)
+ return err;
+ }
down_write(&mm->mmap_sem);
vma = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
down_write(&mm->mmap_sem);
vma = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
struct page_to_node *pp;
LIST_HEAD(pagelist);
struct page_to_node *pp;
LIST_HEAD(pagelist);
down_read(&mm->mmap_sem);
/*
* Build a list of pages to migrate
*/
down_read(&mm->mmap_sem);
/*
* Build a list of pages to migrate
*/
for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
struct vm_area_struct *vma;
struct page *page;
for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
struct vm_area_struct *vma;
struct page *page;