summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorPaul Jackson <pj@sgi.com>2006-01-08 12:01:59 +0300
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-09 07:13:44 +0300
commit4225399a66b315d4d1fb1cb61b75dda201c832e3 (patch)
treec8bd976bc6590c5fe859c6129abb93072d99cfa8 /include
parent202f72d5d1b5c2c084f63ef996c736d208b447b5 (diff)
downloadlinux-4225399a66b315d4d1fb1cb61b75dda201c832e3.tar.xz
[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cpuset_mems_generation is out-of-date with its cpusets mems_generation.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 'include')
-rw-r--r--include/linux/mempolicy.h18
1 files changed, 18 insertions, 0 deletions
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 74357cb9bc7c..c7ac77e873b3 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -150,6 +150,16 @@ extern void numa_policy_init(void);
extern void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *new);
extern void mpol_rebind_task(struct task_struct *tsk,
const nodemask_t *new);
+extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
+#define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x))
+
+#ifdef CONFIG_CPUSET
+#define current_cpuset_is_being_rebound() \
+ (cpuset_being_rebound == current->cpuset)
+#else
+#define current_cpuset_is_being_rebound() 0
+#endif
+
extern struct mempolicy default_policy;
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
unsigned long addr);
@@ -165,6 +175,8 @@ static inline void check_highest_zone(int k)
int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
+extern void *cpuset_being_rebound; /* Trigger mpol_copy vma rebind */
+
#else
struct mempolicy {};
@@ -234,6 +246,12 @@ static inline void mpol_rebind_task(struct task_struct *tsk,
{
}
+static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
+{
+}
+
+#define set_cpuset_being_rebound(x) do {} while (0)
+
static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
unsigned long addr)
{