Quick vmalloc vs kmalloc fix to the case where array size is too large
Separates all pidlist allocation requests to a separate function that judges
based on the requested size whether or not the array needs to be vmalloced or
can be gotten via kmalloc, and similar for kfree/vfree. Should be replaced
entirely with a kernel-wide solution to this general problem.
Depends on cgroup-pidlist-namespace.patch, cgroup-procs.patch
Signed-off-by: Ben Blum <bb...@google.com>
---
kernel/cgroup.c | 47 ++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 42 insertions(+), 5 deletions(-)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cdd0112..f6d5969 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -48,6 +48,7 @@
#include <linux/namei.h>
#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
+#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <asm/atomic.h>
@@ -2123,6 +2124,42 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
*/
/*
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+ if (PIDLIST_TOO_LARGE(count))
+ return vmalloc(count * sizeof(pid_t));
+ else
+ return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+ if (is_vmalloc_addr(p))
+ vfree(p);
+ else
+ kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+ void *newlist;
+ /* note: if new alloc fails, old p will still be valid either way */
+ if (is_vmalloc_addr(p)) {
+ newlist = vmalloc(newcount * sizeof(pid_t));
+ if (!newlist)
+ return NULL;
+ memcpy(newlist, p, newcount * sizeof(pid_t));
+ vfree(p);
+ } else {
+ newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+ }
+ return newlist;
+}
+
+/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
* If the new stripped list is sufficiently smaller and there's enough memory
* to allocate a new buffer, will let go of the unneeded memory. Returns the
@@ -2161,7 +2198,7 @@ after:
* we'll just stay with what we've got.
*/
if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
- newlist = krealloc(list, dest * sizeof(pid_t), GFP_KERNEL);
+ newlist = pidlist_resize(list, dest);
if (newlist)
*p = newlist;
}
@@ -2242,7 +2279,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum
cgroup_filetype type,
* show up until sometime later on.
*/
length = cgroup_task_count(cgrp);
- array = kmalloc(length * sizeof(pid_t), GFP_KERNEL);
+ array = pidlist_allocate(length);
if (!array)
return -ENOMEM;
/* now, populate the array */
@@ -2266,11 +2303,11 @@ static int pidlist_array_load(struct cgroup *cgrp, enum
cgroup_filetype type,
length = pidlist_uniq(&array, length);
l = cgroup_pidlist_find(cgrp, type);
if (!l) {
- kfree(array);
+ pidlist_free(array);
return -ENOMEM;
}
/* store array, freeing old if necessary - lock already held */
- kfree(l->list);
+ pidlist_free(l->list);
l->list = array;
l->length = length;
l->use_count++;
@@ -2431,7 +2468,7 @@ static void cgroup_release_pid_array(struct
cgroup_pidlist *l)
/* we're the last user if refcount is 0; remove and free */
list_del(&l->links);
mutex_unlock(&l->owner->pidlist_mutex);
- kfree(l->list);
+ pidlist_free(l->list);
put_pid_ns(l->key.ns);
up_write(&l->mutex);
kfree(l);
_______________________________________________
Containers mailing list
contain...@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
_______________________________________________
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
