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 <[email protected]> --- kernel/cgroup.c | 34 ++++++++++++++++++++++++++++------ 1 files changed, 28 insertions(+), 6 deletions(-) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 33d89be..0ed85fa 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> @@ -2121,6 +2122,27 @@ 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 inline 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 inline void pidlist_free(void *p) +{ + if (is_vmalloc_addr(p)) + vfree(p); + else + kfree(p); +} + +/* * 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 @@ -2160,10 +2182,10 @@ static int pidlist_uniq(pid_t **p, int length) * we'll just stay with what we've got. */ if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) { - newlist = kmalloc(dest * sizeof(pid_t), GFP_KERNEL); + newlist = pidlist_allocate(dest); if (newlist) { memcpy(newlist, list, dest * sizeof(pid_t)); - kfree(list); + pidlist_free(list); *p = newlist; } } @@ -2243,7 +2265,7 @@ 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 */ @@ -2268,11 +2290,11 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, } 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++; @@ -2433,7 +2455,7 @@ 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 [email protected] https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list [email protected] https://openvz.org/mailman/listinfo/devel
