On 2019/2/26 3:17, David Rientjes wrote:
> On Mon, 25 Feb 2019, Mike Kravetz wrote:
>
>> Ok, what about just moving the calculation/check inside the lock as in the
>> untested patch below?
>>
>> Signed-off-by: Mike Kravetz <mike.krav...@oracle.com>
>> ---
>> mm/hugetlb.c | 34 ++++++++++++++++++++++++++--------
>> 1 file changed, 26 insertions(+), 8 deletions(-)
>>
>> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
>> index 1c5219193b9e..5afa77dc7bc8 100644
>> --- a/mm/hugetlb.c
>> +++ b/mm/hugetlb.c
>> @@ -2274,7 +2274,7 @@ static int adjust_pool_surplus(struct hstate *h,
>> nodemask_t *nodes_allowed,
>> }
>>
>> #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
>> -static int set_max_huge_pages(struct hstate *h, unsigned long count,
>> +static int set_max_huge_pages(struct hstate *h, unsigned long count, int
>> nid,
>> nodemask_t *nodes_allowed)
>> {
>> unsigned long min_count, ret;
>> @@ -2289,6 +2289,23 @@ static int set_max_huge_pages(struct hstate *h,
>> unsigned
>> long count,
>> goto decrease_pool;
>> }
>>
>> + spin_lock(&hugetlb_lock);
>> +
>> + /*
>> + * Check for a node specific request. Adjust global count, but
>> + * restrict alloc/free to the specified node.
>> + */
>> + if (nid != NUMA_NO_NODE) {
>> + unsigned long old_count = count;
>> + count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
>> + /*
>> + * If user specified count causes overflow, set to
>> + * largest possible value.
>> + */
>> + if (count < old_count)
>> + count = ULONG_MAX;
>> + }
>> +
>> /*
>> * Increase the pool size
>> * First take pages out of surplus state. Then make up the
>> @@ -2300,7 +2317,6 @@ static int set_max_huge_pages(struct hstate *h,
>> unsigned
>> long count,
>> * pool might be one hugepage larger than it needs to be, but
>> * within all the constraints specified by the sysctls.
>> */
>> - spin_lock(&hugetlb_lock);
>> while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
>> if (!adjust_pool_surplus(h, nodes_allowed, -1))
>> break;
>> @@ -2421,16 +2437,18 @@ static ssize_t __nr_hugepages_store_common(bool
>> obey_mempolicy,
>> nodes_allowed = &node_states[N_MEMORY];
>> }
>> } else if (nodes_allowed) {
>> + /* Node specific request */
>> + init_nodemask_of_node(nodes_allowed, nid);
>> + } else {
>> /*
>> - * per node hstate attribute: adjust count to global,
>> - * but restrict alloc/free to the specified node.
>> + * Node specific request, but we could not allocate
>> + * node mask. Pass in ALL nodes, and clear nid.
>> */
>> - count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
>> - init_nodemask_of_node(nodes_allowed, nid);
>> - } else
>> + nid = NUMA_NO_NODE;
>> nodes_allowed = &node_states[N_MEMORY];
>> + }
>>
>> - err = set_max_huge_pages(h, count, nodes_allowed);
>> + err = set_max_huge_pages(h, count, nid, nodes_allowed);
>> if (err)
>> goto out;
>>
>
> Looks good; Jing, could you test that this fixes your case?
Yes, I have tested this patch, it can also fix my case.
>
> .
>
