percpu: make embedding first chunk allocator check vmalloc space size

Embedding first chunk allocator maintains the distances between units
in the vmalloc area and thus needs vmalloc space to be larger than the
maximum distances between units; otherwise, it wouldn't be able to
create any dynamic chunks.  This patch makes the embedding first chunk
allocator check vmalloc space size and if the maximum distance between
units is larger than 75% of it, print warning and, if page mapping
allocator is available, fail initialization so that the system falls
back onto it.

This should work around percpu allocation failure problems on certain
sparc64 configurations where distances between NUMA nodes are larger
than the vmalloc area and makes percpu allocator more robust for
future configurations.

Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/mm/percpu.c b/mm/percpu.c
index a64133f..c43da8c 100644 (file)
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1786,7 +1786,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
        void *base = (void *)ULONG_MAX;
        void **areas = NULL;
        struct pcpu_alloc_info *ai;
        void *base = (void *)ULONG_MAX;
        void **areas = NULL;
        struct pcpu_alloc_info *ai;

-       size_t size_sum, areas_size;
+       size_t size_sum, areas_size, max_distance;

        int group, i, rc;
 
        ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
        int group, i, rc;
 
        ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,


@@ -1836,8 +1836,24 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
        }
 
        /* base address is now known, determine group base offsets */
        }
 
        /* base address is now known, determine group base offsets */

-       for (group = 0; group < ai->nr_groups; group++)
+       max_distance = 0;
+       for (group = 0; group < ai->nr_groups; group++) {

                ai->groups[group].base_offset = areas[group] - base;
                ai->groups[group].base_offset = areas[group] - base;

+               max_distance = max(max_distance, ai->groups[group].base_offset);
+       }
+       max_distance += ai->unit_size;
+
+       /* warn if maximum distance is further than 75% of vmalloc space */
+       if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
+               pr_warning("PERCPU: max_distance=0x%lx too large for vmalloc "
+                          "space 0x%lx\n",
+                          max_distance, VMALLOC_END - VMALLOC_START);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+               /* and fail if we have fallback */
+               rc = -EINVAL;
+               goto out_free;
+#endif
+       }

 
        pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
                PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
 
        pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
                PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,