[v4,3/8] hugetlb: add per-hstate mutex to synchronize user adjustments

Commit Message

Mike Kravetz April 5, 2021, 11 p.m. UTC

The helper routine hstate_next_node_to_alloc accesses and modifies the
hstate variable next_nid_to_alloc.  The helper is used by the routines
alloc_pool_huge_page and adjust_pool_surplus.  adjust_pool_surplus is
called with hugetlb_lock held.  However, alloc_pool_huge_page can not
be called with the hugetlb lock held as it will call the page allocator.
Two instances of alloc_pool_huge_page could be run in parallel or
alloc_pool_huge_page could run in parallel with adjust_pool_surplus
which may result in the variable next_nid_to_alloc becoming invalid
for the caller and pages being allocated on the wrong node.

Both alloc_pool_huge_page and adjust_pool_surplus are only called from
the routine set_max_huge_pages after boot.  set_max_huge_pages is only
called as the reusult of a user writing to the proc/sysfs nr_hugepages,
or nr_hugepages_mempolicy file to adjust the number of hugetlb pages.

It makes little sense to allow multiple adjustment to the number of
hugetlb pages in parallel.  Add a mutex to the hstate and use it to only
allow one hugetlb page adjustment at a time.  This will synchronize
modifications to the next_nid_to_alloc variable.

Signed-off-by: Mike Kravetz <[e-mail]>
Acked-by: Michal Hocko <[e-mail]>
Reviewed-by: Oscar Salvador <[e-mail]>
Reviewed-by: Miaohe Lin <[e-mail]>
Reviewed-by: Muchun Song <[e-mail]>
---
 include/linux/hugetlb.h | 1 +
 mm/hugetlb.c            | 8 ++++++++
 2 files changed, 9 insertions(+)

Comments

David Hildenbrand April 7, 2021, 9:28 a.m. UTC | #1

On 06.04.21 01:00, Mike Kravetz wrote:
> The helper routine hstate_next_node_to_alloc accesses and modifies the
> hstate variable next_nid_to_alloc.  The helper is used by the routines
> alloc_pool_huge_page and adjust_pool_surplus.  adjust_pool_surplus is
> called with hugetlb_lock held.  However, alloc_pool_huge_page can not
> be called with the hugetlb lock held as it will call the page allocator.
> Two instances of alloc_pool_huge_page could be run in parallel or
> alloc_pool_huge_page could run in parallel with adjust_pool_surplus
> which may result in the variable next_nid_to_alloc becoming invalid
> for the caller and pages being allocated on the wrong node.
> 
> Both alloc_pool_huge_page and adjust_pool_surplus are only called from
> the routine set_max_huge_pages after boot.  set_max_huge_pages is only
> called as the reusult of a user writing to the proc/sysfs nr_hugepages,
> or nr_hugepages_mempolicy file to adjust the number of hugetlb pages.
> 
> It makes little sense to allow multiple adjustment to the number of
> hugetlb pages in parallel.  Add a mutex to the hstate and use it to only
> allow one hugetlb page adjustment at a time.  This will synchronize
> modifications to the next_nid_to_alloc variable.
> 
> Signed-off-by: Mike Kravetz <[e-mail]>
> Acked-by: Michal Hocko <[e-mail]>
> Reviewed-by: Oscar Salvador <[e-mail]>
> Reviewed-by: Miaohe Lin <[e-mail]>
> Reviewed-by: Muchun Song <[e-mail]>
> ---
>   include/linux/hugetlb.h | 1 +
>   mm/hugetlb.c            | 8 ++++++++
>   2 files changed, 9 insertions(+)
> 
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index d9b78e82652f..b92f25ccef58 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -566,6 +566,7 @@ HPAGEFLAG(Freed, freed)
>   #define HSTATE_NAME_LEN 32
>   /* Defines one hugetlb page size */
>   struct hstate {
> +	struct mutex resize_lock;
>   	int next_nid_to_alloc;
>   	int next_nid_to_free;
>   	unsigned int order;
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 1d62f0492e7b..8497a3598c86 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2730,6 +2730,11 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
>   	else
>   		return -ENOMEM;
>   
> +	/*
> +	 * resize_lock mutex prevents concurrent adjustments to number of
> +	 * pages in hstate via the proc/sysfs interfaces.
> +	 */
> +	mutex_lock(&h->resize_lock);
>   	spin_lock(&hugetlb_lock);
>   
>   	/*
> @@ -2762,6 +2767,7 @@ 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->resize_lock);
>   			NODEMASK_FREE(node_alloc_noretry);
>   			return -EINVAL;
>   		}
> @@ -2836,6 +2842,7 @@ 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->resize_lock);
>   
>   	NODEMASK_FREE(node_alloc_noretry);
>   
> @@ -3323,6 +3330,7 @@ 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->resize_lock);
>   	h->order = order;
>   	h->mask = ~(huge_page_size(h) - 1);
>   	for (i = 0; i < MAX_NUMNODES; ++i)
> 

Reviewed-by: David Hildenbrand <[e-mail]>

Patch

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d9b78e82652f..b92f25ccef58 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -566,6 +566,7 @@  HPAGEFLAG(Freed, freed)
 #define HSTATE_NAME_LEN 32
 /* Defines one hugetlb page size */
 struct hstate {
+	struct mutex resize_lock;
 	int next_nid_to_alloc;
 	int next_nid_to_free;
 	unsigned int order;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1d62f0492e7b..8497a3598c86 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2730,6 +2730,11 @@  static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	else
 		return -ENOMEM;
 
+	/*
+	 * resize_lock mutex prevents concurrent adjustments to number of
+	 * pages in hstate via the proc/sysfs interfaces.
+	 */
+	mutex_lock(&h->resize_lock);
 	spin_lock(&hugetlb_lock);
 
 	/*
@@ -2762,6 +2767,7 @@  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->resize_lock);
 			NODEMASK_FREE(node_alloc_noretry);
 			return -EINVAL;
 		}
@@ -2836,6 +2842,7 @@  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->resize_lock);
 
 	NODEMASK_FREE(node_alloc_noretry);
 
@@ -3323,6 +3330,7 @@  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->resize_lock);
 	h->order = order;
 	h->mask = ~(huge_page_size(h) - 1);
 	for (i = 0; i < MAX_NUMNODES; ++i)