summaryrefslogtreecommitdiff
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorPaul Jackson <pj@sgi.com>2006-01-08 01:01:59 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-08 20:13:44 -0800
commit4225399a66b315d4d1fb1cb61b75dda201c832e3 (patch)
treec8bd976bc6590c5fe859c6129abb93072d99cfa8 /mm/mempolicy.c
parent202f72d5d1b5c2c084f63ef996c736d208b447b5 (diff)
[PATCH] cpuset: rebind vma mempolicies fix
Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c29
1 files changed, 29 insertions, 0 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c39bd86f4ea..1850d0aef4a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1131,6 +1131,15 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
}
EXPORT_SYMBOL(alloc_pages_current);
+/*
+ * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * rebinds the mempolicy its copying by calling mpol_rebind_policy()
+ * with the mems_allowed returned by cpuset_mems_allowed(). This
+ * keeps mempolicies cpuset relative after its cpuset moves. See
+ * further kernel/cpuset.c update_nodemask().
+ */
+void *cpuset_being_rebound;
+
/* Slow path of a mempolicy copy */
struct mempolicy *__mpol_copy(struct mempolicy *old)
{
@@ -1138,6 +1147,10 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
if (!new)
return ERR_PTR(-ENOMEM);
+ if (current_cpuset_is_being_rebound()) {
+ nodemask_t mems = cpuset_mems_allowed(current);
+ mpol_rebind_policy(old, &mems);
+ }
*new = *old;
atomic_set(&new->refcnt, 1);
if (new->policy == MPOL_BIND) {
@@ -1481,6 +1494,22 @@ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
}
/*
+ * Rebind each vma in mm to new nodemask.
+ *
+ * Call holding a reference to mm. Takes mm->mmap_sem during call.
+ */
+
+void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
+{
+ struct vm_area_struct *vma;
+
+ down_write(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next)
+ mpol_rebind_policy(vma->vm_policy, new);
+ up_write(&mm->mmap_sem);
+}
+
+/*
* Display pages allocated per node and memory policy via /proc.
*/