| Message ID | 20210325002835.216118-4-mike.kravetz@oracle.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | make hugetlb put_page safe for all calling contexts | expand |
On Wed 24-03-21 17:28:30, 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 <mike.kravetz@oracle.com> Acked-by: Michal Hocko <mhocko@suse.com> I would just recommend s@mutex@resize_lock@ so that the intention is more clear from the name. > --- > 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 a7f7d5f328dc..8817ec987d68 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 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 f9ba63fc1747..404b0b1c5258 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -2616,6 +2616,8 @@ 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); > > /* > @@ -2648,6 +2650,7 @@ 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; > } > @@ -2722,6 +2725,7 @@ 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); > > @@ -3209,6 +3213,7 @@ 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 >
On Wed, Mar 24, 2021 at 05:28:30PM -0700, 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. Is this something you have seen happening? If so, it is easier to trigger? I doubt so as I have not seen any bug report, but just wondering whether a Fixes tag is needed, or probably not worth, right? > --- 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 mutex; I am also with Michal here, renaming the mutex to something closer to its function might be better to understand it without diving too much in the code. > int next_nid_to_alloc; > int next_nid_to_free; > unsigned int order; > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index f9ba63fc1747..404b0b1c5258 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -2616,6 +2616,8 @@ 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); I find above comment a bit misleading. AFAIK, hugetlb_lock also protects from concurrent adjustments for the same hstate (hugepage_activelist, free_huge_pages, surplus_huge_pages, etc...). Would it be more apropiate saying that mutex_lock() only prevents from simultaneously sysfs/proc operations? Reviewed-by: Oscar Salvador <osalvador@suse.e>
On 2021/3/25 8:28, 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 <mike.kravetz@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 a7f7d5f328dc..8817ec987d68 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 mutex; I am also with Michal and Oscar here, renaming the mutex to something closer to its function. Reviewed-by: Miaohe Lin <linmiaohe@huawei.com> > int next_nid_to_alloc; > int next_nid_to_free; > unsigned int order; > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index f9ba63fc1747..404b0b1c5258 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -2616,6 +2616,8 @@ 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); > > /* > @@ -2648,6 +2650,7 @@ 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; > } > @@ -2722,6 +2725,7 @@ 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); > > @@ -3209,6 +3213,7 @@ 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) >
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a7f7d5f328dc..8817ec987d68 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 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 f9ba63fc1747..404b0b1c5258 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2616,6 +2616,8 @@ 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); /* @@ -2648,6 +2650,7 @@ 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; } @@ -2722,6 +2725,7 @@ 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); @@ -3209,6 +3213,7 @@ 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)
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 <mike.kravetz@oracle.com> --- include/linux/hugetlb.h | 1 + mm/hugetlb.c | 5 +++++ 2 files changed, 6 insertions(+)