mm, vmalloc: iterate vmap_area_list, instead of vmlist, in vmallocinfo()
This patch is a preparatory step for removing vmlist entirely. For
above purpose, we change iterating a vmap_list codes to iterating a
vmap_area_list. It is somewhat trivial change, but just one thing
should be noticed.
Using vmap_area_list in vmallocinfo() introduce ordering problem in SMP
system. In s_show(), we retrieve some values from vm_struct.
vm_struct's values is not fully setup when va->vm is assigned. Full
setup is notified by removing VM_UNLIST flag without holding a lock.
When we see that VM_UNLIST is removed, it is not ensured that vm_struct
has proper values in view of other CPUs. So we need smp_[rw]mb for
ensuring that proper values is assigned when we see that VM_UNLIST is
removed.
Therefore, this patch not only change a iteration list, but also add a
appropriate smp_[rw]mb to right places.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Atsushi Kumagai <kumagai-atsushi@mxc.nes.nec.co.jp>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Dave Anderson <anderson@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index aee1f61..bda6cef 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1304,7 +1304,14 @@
{
struct vm_struct *tmp, **p;
+ /*
+ * Before removing VM_UNLIST,
+ * we should make sure that vm has proper values.
+ * Pair with smp_rmb() in show_numa_info().
+ */
+ smp_wmb();
vm->flags &= ~VM_UNLIST;
+
write_lock(&vmlist_lock);
for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
if (tmp->addr >= vm->addr)
@@ -2542,19 +2549,19 @@
#ifdef CONFIG_PROC_FS
static void *s_start(struct seq_file *m, loff_t *pos)
- __acquires(&vmlist_lock)
+ __acquires(&vmap_area_lock)
{
loff_t n = *pos;
- struct vm_struct *v;
+ struct vmap_area *va;
- read_lock(&vmlist_lock);
- v = vmlist;
- while (n > 0 && v) {
+ spin_lock(&vmap_area_lock);
+ va = list_entry((&vmap_area_list)->next, typeof(*va), list);
+ while (n > 0 && &va->list != &vmap_area_list) {
n--;
- v = v->next;
+ va = list_entry(va->list.next, typeof(*va), list);
}
- if (!n)
- return v;
+ if (!n && &va->list != &vmap_area_list)
+ return va;
return NULL;
@@ -2562,16 +2569,20 @@
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
- struct vm_struct *v = p;
+ struct vmap_area *va = p, *next;
++*pos;
- return v->next;
+ next = list_entry(va->list.next, typeof(*va), list);
+ if (&next->list != &vmap_area_list)
+ return next;
+
+ return NULL;
}
static void s_stop(struct seq_file *m, void *p)
- __releases(&vmlist_lock)
+ __releases(&vmap_area_lock)
{
- read_unlock(&vmlist_lock);
+ spin_unlock(&vmap_area_lock);
}
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
@@ -2582,6 +2593,11 @@
if (!counters)
return;
+ /* Pair with smp_wmb() in insert_vmalloc_vmlist() */
+ smp_rmb();
+ if (v->flags & VM_UNLIST)
+ return;
+
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr++)
@@ -2595,7 +2611,20 @@
static int s_show(struct seq_file *m, void *p)
{
- struct vm_struct *v = p;
+ struct vmap_area *va = p;
+ struct vm_struct *v;
+
+ if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
+ return 0;
+
+ if (!(va->flags & VM_VM_AREA)) {
+ seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
+ (void *)va->va_start, (void *)va->va_end,
+ va->va_end - va->va_start);
+ return 0;
+ }
+
+ v = va->vm;
seq_printf(m, "0x%pK-0x%pK %7ld",
v->addr, v->addr + v->size, v->size);