mm: move migrate_prep out from under mmap_sem

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>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 36f42573a3352fa6ba452eea2d76ed2021c8605c..e9493b1c1117a4090fa8998b9ea2e29c1239ebbc 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -489,12 +489,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
        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)
@@ -809,9 +803,13 @@ int do_migrate_pages(struct mm_struct *mm,
        const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
 {
        int busy = 0;
-       int err = 0;
+       int err;
        nodemask_t tmp;
 
+       err = migrate_prep();
+       if (err)
+               return err;
+
        down_read(&mm->mmap_sem);
 
        err = migrate_vmas(mm, from_nodes, to_nodes, flags);
@@ -974,6 +972,12 @@ static long do_mbind(unsigned long start, unsigned long len,
                 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);

diff --git a/mm/migrate.c b/mm/migrate.c
index 6602941bfab0b03607f9bce6dd8e3f9ce1046bfe..385db89f0c33e48a421b8adf63e63b60b0e4881e 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -841,12 +841,12 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
        struct page_to_node *pp;
        LIST_HEAD(pagelist);
 
+       migrate_prep();
        down_read(&mm->mmap_sem);
 
        /*
         * Build a list of pages to migrate
         */
-       migrate_prep();
        for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
                struct vm_area_struct *vma;
                struct page *page;