From f4e53d910b7dde2685b177f1e7c3e3e0b4a42f7b Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 28 Apr 2008 02:13:10 -0700 Subject: [PATCH] mempolicy: write lock mmap_sem while changing task mempolicy A read of /proc//numa_maps holds the target task's mmap_sem for read while examining each vma's mempolicy. A vma's mempolicy can fall back to the task's policy. However, the task could be changing it's task policy and free the one that the show_numa_maps() is examining. To prevent this, grab the mmap_sem for write when updating task mempolicy. Pointed out to me by Christoph Lameter and extracted and reworked from Christoph's alternative mempol reference counting patch. This is analogous to the way that do_mbind() and do_get_mempolicy() prevent races between task's sharing an mm_struct [a.k.a. threads] setting and querying a mempolicy for a particular address. Note: this is necessary, but not sufficient, to allow us to stop taking an extra reference on "other task's mempolicy" in get_vma_policy. Subsequent patches will complete this update, allowing us to simplify the tests for whether we need to unref a mempolicy at various points in the code. Signed-off-by: Lee Schermerhorn Cc: Christoph Lameter Cc: David Rientjes Cc: Mel Gorman Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e9fc1c1ae66c..c6c61ea6bb8c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -591,16 +591,29 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new; + struct mm_struct *mm = current->mm; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) return PTR_ERR(new); + + /* + * prevent changing our mempolicy while show_numa_maps() + * is using it. + * Note: do_set_mempolicy() can be called at init time + * with no 'mm'. + */ + if (mm) + down_write(&mm->mmap_sem); mpol_put(current->mempolicy); current->mempolicy = new; mpol_set_task_struct_flag(); if (new && new->policy == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); + if (mm) + up_write(&mm->mmap_sem); + return 0; }