mm/percpu.c: fix panic triggered by BUG_ON() falsely

As shown by pcpu_build_alloc_info(), the number of units within a percpu
group is deduced by rounding up the number of CPUs within the group to
@upa boundary/ Therefore, the number of CPUs isn't equal to the units's
if it isn't aligned to @upa normally.  However, pcpu_page_first_chunk()
uses BUG_ON() to assert that one number is equal to the other roughly,
so a panic is maybe triggered by the BUG_ON() incorrectly.

In order to fix this issue, the number of CPUs is rounded up then
compared with units's and the BUG_ON() is replaced with a warning and
return of an error code as well, to keep system alive as much as
possible.

Link: http://lkml.kernel.org/r/57FCF07C.2020103@zoho.com
Signed-off-by: zijun_hu <zijun_hu@htc.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/percpu.c b/mm/percpu.c
index 255714302394137e37e4d8bd5cf87d685732d9d6..f696385bcc44f8597440bab9b18d9440f0de8863 100644 (file)
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2093,6 +2093,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
        size_t pages_size;
        struct page **pages;
        int unit, i, j, rc;
+       int upa;
+       int nr_g0_units;
 
        snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);
 
@@ -2100,7 +2102,12 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
        if (IS_ERR(ai))
                return PTR_ERR(ai);
        BUG_ON(ai->nr_groups != 1);
-       BUG_ON(ai->groups[0].nr_units != num_possible_cpus());
+       upa = ai->alloc_size/ai->unit_size;
+       nr_g0_units = roundup(num_possible_cpus(), upa);
+       if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) {
+               pcpu_free_alloc_info(ai);
+               return -EINVAL;
+       }
 
        unit_pages = ai->unit_size >> PAGE_SHIFT;
 
@@ -2111,21 +2118,22 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 
        /* allocate pages */
        j = 0;
-       for (unit = 0; unit < num_possible_cpus(); unit++)
+       for (unit = 0; unit < num_possible_cpus(); unit++) {
+               unsigned int cpu = ai->groups[0].cpu_map[unit];
                for (i = 0; i < unit_pages; i++) {
-                       unsigned int cpu = ai->groups[0].cpu_map[unit];
                        void *ptr;
 
                        ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
                        if (!ptr) {
                                pr_warn("failed to allocate %s page for cpu%u\n",
-                                       psize_str, cpu);
+                                               psize_str, cpu);
                                goto enomem;
                        }
                        /* kmemleak tracks the percpu allocations separately */
                        kmemleak_free(ptr);
                        pages[j++] = virt_to_page(ptr);
                }
+       }
 
        /* allocate vm area, map the pages and copy static data */
        vm.flags = VM_ALLOC;