summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorUladzislau Rezki (Sony) <urezki@gmail.com>2019-03-08 03:03:51 +0000
committerJohannes Weiner <hannes@cmpxchg.org>2019-03-08 03:03:51 +0000
commite0cf7749bade6da318e98e934a24d8b62fab512c (patch)
treecf4a7585fbbddff189b513df2d8e63620275eb2f
parent5b642de054ff054f1c22f5c15730c3052b1649af (diff)
mm/vmalloc.c: add priority threshold to __purge_vmap_area_lazy()
763b218ddfaf ("mm: add preempt points into __purge_vmap_area_lazy()") introduced some preempt points, one of those is making an allocation more prioritized over lazy free of vmap areas. Prioritizing an allocation over freeing does not work well all the time, i.e. it should be rather a compromise. 1) Number of lazy pages directly influences the busy list length thus on operations like: allocation, lookup, unmap, remove, etc. 2) Under heavy stress of vmalloc subsystem I run into a situation when memory usage gets increased hitting out_of_memory -> panic state due to completely blocking of logic that frees vmap areas in the __purge_vmap_area_lazy() function. Establish a threshold passing which the freeing is prioritized back over allocation creating a balance between each other. Using vmalloc test driver in "stress mode", i.e. When all available test cases are run simultaneously on all online CPUs applying a pressure on the vmalloc subsystem, my HiKey 960 board runs out of memory due to the fact that __purge_vmap_area_lazy() logic simply is not able to free pages in time. How I run it: 1) You should build your kernel with CONFIG_TEST_VMALLOC=m 2) ./tools/testing/selftests/vm/test_vmalloc.sh stress During this test "vmap_lazy_nr" pages will go far beyond acceptable lazy_max_pages() threshold, that will lead to enormous busy list size and other problems including allocation time and so on. Link: http://lkml.kernel.org/r/20190124115648.9433-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Cc: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--mm/vmalloc.c18
1 files changed, 12 insertions, 6 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e86ba6e74b50..00c688cb579a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -661,23 +661,27 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
struct llist_node *valist;
struct vmap_area *va;
struct vmap_area *n_va;
- bool do_free = false;
+ int resched_threshold;
lockdep_assert_held(&vmap_purge_lock);
valist = llist_del_all(&vmap_purge_list);
+ if (unlikely(valist == NULL))
+ return false;
+
+ /*
+ * TODO: to calculate a flush range without looping.
+ * The list can be up to lazy_max_pages() elements.
+ */
llist_for_each_entry(va, valist, purge_list) {
if (va->va_start < start)
start = va->va_start;
if (va->va_end > end)
end = va->va_end;
- do_free = true;
}
- if (!do_free)
- return false;
-
flush_tlb_kernel_range(start, end);
+ resched_threshold = (int) lazy_max_pages() << 1;
spin_lock(&vmap_area_lock);
llist_for_each_entry_safe(va, n_va, valist, purge_list) {
@@ -685,7 +689,9 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
__free_vmap_area(va);
atomic_sub(nr, &vmap_lazy_nr);
- cond_resched_lock(&vmap_area_lock);
+
+ if (atomic_read(&vmap_lazy_nr) < resched_threshold)
+ cond_resched_lock(&vmap_area_lock);
}
spin_unlock(&vmap_area_lock);
return true;