On Fri 19-03-21 15:42:02, Mike Kravetz wrote:
> The number of hugetlb pages can be adjusted by writing to the
> sysps/proc files nr_hugepages, nr_hugepages_mempolicy or
> nr_overcommit_hugepages. There is nothing to prevent two
> concurrent modifications via these files. The underlying routine
> set_max_huge_pages() makes assumptions that only one occurrence is
> running at a time. Specifically, alloc_pool_huge_page uses a
> hstate specific variable without any synchronization.
>From the above it is not really clear whether the unsynchronized nature
of set_max_huge_pages is really a problem or a mere annoynce. I suspect
the later because counters are properly synchronized with the
hugetlb_lock. It would be great to clarify that.
> Add a mutex to the hstate and use it to only allow one hugetlb
> page adjustment at a time.
>
> Signed-off-by: Mike Kravetz <mike.krav...@oracle.com>
> ---
> include/linux/hugetlb.h | 1 +
> mm/hugetlb.c | 5 +++++
> 2 files changed, 6 insertions(+)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index cccd1aab69dd..f42d44050548 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -555,6 +555,7 @@ HPAGEFLAG(Freed, freed)
> #define HSTATE_NAME_LEN 32
> /* Defines one hugetlb page size */
> struct hstate {
> + struct mutex mutex;
> int next_nid_to_alloc;
> int next_nid_to_free;
> unsigned int order;
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 5b1ab1f427c5..d5be25f910e8 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2601,6 +2601,8 @@ static int set_max_huge_pages(struct hstate *h,
> unsigned long count, int nid,
> else
> return -ENOMEM;
>
> + /* mutex prevents concurrent adjustments for the same hstate */
> + mutex_lock(&h->mutex);
> spin_lock(&hugetlb_lock);
>
> /*
> @@ -2633,6 +2635,7 @@ static int set_max_huge_pages(struct hstate *h,
> unsigned long count, int nid,
> if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
> if (count > persistent_huge_pages(h)) {
> spin_unlock(&hugetlb_lock);
> + mutex_unlock(&h->mutex);
> NODEMASK_FREE(node_alloc_noretry);
> return -EINVAL;
> }
> @@ -2707,6 +2710,7 @@ static int set_max_huge_pages(struct hstate *h,
> unsigned long count, int nid,
> out:
> h->max_huge_pages = persistent_huge_pages(h);
> spin_unlock(&hugetlb_lock);
> + mutex_unlock(&h->mutex);
>
> NODEMASK_FREE(node_alloc_noretry);
>
> @@ -3194,6 +3198,7 @@ void __init hugetlb_add_hstate(unsigned int order)
> BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
> BUG_ON(order == 0);
> h = &hstates[hugetlb_max_hstate++];
> + mutex_init(&h->mutex);
> h->order = order;
> h->mask = ~(huge_page_size(h) - 1);
> for (i = 0; i < MAX_NUMNODES; ++i)
> --
> 2.30.2
>
--
Michal Hocko
SUSE Labs
