Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-24 Thread Mike Kravetz
On 11/23/2015 09:32 PM, Naoya Horiguchi wrote: > On Fri, Nov 20, 2015 at 01:56:18PM -0800, Mike Kravetz wrote: >> On 11/19/2015 11:57 PM, Hillf Danton wrote: When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to alloc_buddy_huge_page() to directly create a

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-24 Thread Mike Kravetz
On 11/23/2015 09:32 PM, Naoya Horiguchi wrote: > On Fri, Nov 20, 2015 at 01:56:18PM -0800, Mike Kravetz wrote: >> On 11/19/2015 11:57 PM, Hillf Danton wrote: When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to alloc_buddy_huge_page() to directly create a

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-23 Thread Naoya Horiguchi
On Fri, Nov 20, 2015 at 01:56:18PM -0800, Mike Kravetz wrote: > On 11/19/2015 11:57 PM, Hillf Danton wrote: > >> > >> When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > >> alloc_buddy_huge_page() to directly create a hugepage from the buddy > >> allocator. > >> In that

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-23 Thread Naoya Horiguchi
On Fri, Nov 20, 2015 at 02:26:38PM -0800, Andrew Morton wrote: > On Fri, 20 Nov 2015 15:57:21 +0800 "Hillf Danton" > wrote: > > > > > > > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > > > alloc_buddy_huge_page() to directly create a hugepage from the buddy > > >

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-23 Thread Naoya Horiguchi
On Fri, Nov 20, 2015 at 02:26:38PM -0800, Andrew Morton wrote: > On Fri, 20 Nov 2015 15:57:21 +0800 "Hillf Danton" > wrote: > > > > > > > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > > > alloc_buddy_huge_page() to directly create a

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-23 Thread Naoya Horiguchi
On Fri, Nov 20, 2015 at 01:56:18PM -0800, Mike Kravetz wrote: > On 11/19/2015 11:57 PM, Hillf Danton wrote: > >> > >> When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > >> alloc_buddy_huge_page() to directly create a hugepage from the buddy > >> allocator. > >> In that

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Andrew Morton
On Fri, 20 Nov 2015 15:57:21 +0800 "Hillf Danton" wrote: > > > > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > > alloc_buddy_huge_page() to directly create a hugepage from the buddy > > allocator. > > In that case, however, if alloc_buddy_huge_page() succeeds we

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Mike Kravetz
On 11/19/2015 11:57 PM, Hillf Danton wrote: >> >> When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to >> alloc_buddy_huge_page() to directly create a hugepage from the buddy >> allocator. >> In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement >>

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Hillf Danton
> > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > alloc_buddy_huge_page() to directly create a hugepage from the buddy > allocator. > In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement > h->resv_huge_pages, which means that successful

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Mike Kravetz
On 11/19/2015 11:57 PM, Hillf Danton wrote: >> >> When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to >> alloc_buddy_huge_page() to directly create a hugepage from the buddy >> allocator. >> In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement >>

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Andrew Morton
On Fri, 20 Nov 2015 15:57:21 +0800 "Hillf Danton" wrote: > > > > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > > alloc_buddy_huge_page() to directly create a hugepage from the buddy > > allocator. > > In that case, however, if

Re: [PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-20 Thread Hillf Danton
> > When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to > alloc_buddy_huge_page() to directly create a hugepage from the buddy > allocator. > In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement > h->resv_huge_pages, which means that successful

[PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-19 Thread Naoya Horiguchi
When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to alloc_buddy_huge_page() to directly create a hugepage from the buddy allocator. In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement h->resv_huge_pages, which means that successful hugetlb_fault()

[PATCH v1] mm: hugetlb: fix hugepage memory leak caused by wrong reserve count

2015-11-19 Thread Naoya Horiguchi
When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back to alloc_buddy_huge_page() to directly create a hugepage from the buddy allocator. In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement h->resv_huge_pages, which means that successful hugetlb_fault()