Unverified Commit d25aa47f authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!6588 Add hugetlb MADV_DONTNEED support 

Merge Pull Request from: @ci-robot 
 
PR sync from: Ze Zuo <zuoze1@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/YMMAHOTCHL5MMEMR4G2E56QEGR5STD2M/ 
MADV_DONTNEED is currently disabled for hugetlb mappings.  This certainly
makes sense in shared file mappings as the pagecache maintains a reference
to the page and it will never be freed.  However, it could be useful to
unmap and free pages in private mappings.

Mike Kravetz (3):
  mm: enable MADV_DONTNEED for hugetlb mappings
  madvise: use zap_page_range_single for madvise dontneed
  hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing

Rik van Riel (1):
  mm,madvise,hugetlb: fix unexpected data loss with MADV_DONTNEED on
    hugetlbfs


-- 
2.25.1
 
https://gitee.com/openeuler/kernel/issues/I9GVYW 
 
Link:https://gitee.com/openeuler/kernel/pulls/6588

 

Reviewed-by: default avatarKefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: default avatarJialin Zhang <zhangjialin11@huawei.com>
parents b8e86304 5d4b821d

include/linux/hugetlb.h

+3 −2
Original line number Diff line number Diff line
@@ -142,7 +142,7 @@ void unmap_hugepage_range(struct vm_area_struct *, 
void __unmap_hugepage_range_final(struct mmu_gather *tlb,

			  struct vm_area_struct *vma,

			  unsigned long start, unsigned long end,

			  struct page *ref_page);

			  struct page *ref_page, zap_flags_t zap_flags);

void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,

				unsigned long start, unsigned long end,

				struct page *ref_page);
@@ -371,7 +371,8 @@ static inline unsigned long hugetlb_change_protection( 


static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,

			struct vm_area_struct *vma, unsigned long start,

			unsigned long end, struct page *ref_page)

			unsigned long end, struct page *ref_page,

			zap_flags_t zap_flags)

{

	BUG();

}

include/linux/mm.h

+6 −0
Original line number Diff line number Diff line
@@ -1706,8 +1706,12 @@ struct zap_details { 
	pgoff_t	first_index;			/* Lowest page->index to unmap */

	pgoff_t last_index;			/* Highest page->index to unmap */

	struct page *single_page;		/* Locked page to be unmapped */

	zap_flags_t zap_flags;			/* Extra flags for zapping */

};



/* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */

#define  ZAP_FLAG_UNMAP		((__force zap_flags_t) BIT(1))



struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,

			     pte_t pte);

struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -1717,6 +1721,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, 
		  unsigned long size);

void zap_page_range(struct vm_area_struct *vma, unsigned long address,

		    unsigned long size);

void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,

		unsigned long size, struct zap_details *details);

void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,

		unsigned long start, unsigned long end);

include/linux/mm_types.h

+2 −0
Original line number Diff line number Diff line
@@ -898,4 +898,6 @@ typedef struct { 
	unsigned long val;

} swp_entry_t;



typedef unsigned int __bitwise zap_flags_t;



#endif /* _LINUX_MM_TYPES_H */

mm/hugetlb.c

+16 −12
Original line number Diff line number Diff line
@@ -4512,22 +4512,26 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, 


void __unmap_hugepage_range_final(struct mmu_gather *tlb,

			  struct vm_area_struct *vma, unsigned long start,

			  unsigned long end, struct page *ref_page)

			  unsigned long end, struct page *ref_page,

			  zap_flags_t zap_flags)

{

	__unmap_hugepage_range(tlb, vma, start, end, ref_page);



	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */

		/*

	 * Clear this flag so that x86's huge_pmd_share page_table_shareable

	 * test will fail on a vma being torn down, and not grab a page table

	 * on its way out.  We're lucky that the flag has such an appropriate

	 * name, and can in fact be safely cleared here. We could clear it

	 * before the __unmap_hugepage_range above, but all that's necessary

		 * Clear this flag so that x86's huge_pmd_share

		 * page_table_shareable test will fail on a vma being torn

		 * down, and not grab a page table on its way out.  We're lucky

		 * that the flag has such an appropriate name, and can in fact

		 * be safely cleared here. We could clear it before the

		 * __unmap_hugepage_range above, but all that's necessary

		 * is to clear it before releasing the i_mmap_rwsem. This works

	 * because in the context this is called, the VMA is about to be

	 * destroyed and the i_mmap_rwsem is held.

		 * because in the context this is called, the VMA is about to

		 * be destroyed and the i_mmap_rwsem is held.

		 */

		vma->vm_flags &= ~VM_MAYSHARE;

	}

}



void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,

			  unsigned long end, struct page *ref_page)

mm/madvise.c

+42 −5
Original line number Diff line number Diff line
@@ -525,6 +525,11 @@ static void madvise_cold_page_range(struct mmu_gather *tlb, 
	tlb_end_vma(tlb, vma);

}



static inline bool can_madv_lru_non_huge_vma(struct vm_area_struct *vma)

{

	return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP));

}



static long madvise_cold(struct vm_area_struct *vma,

			struct vm_area_struct **prev,

			unsigned long start_addr, unsigned long end_addr)
@@ -772,8 +777,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, 
 * Application no longer needs these pages.  If the pages are dirty,

 * it's OK to just throw them away.  The app will be more careful about

 * data it wants to keep.  Be sure to free swap resources too.  The

 * zap_page_range call sets things up for shrink_active_list to actually free

 * these pages later if no one else has touched them in the meantime,

 * zap_page_range_single call sets things up for shrink_active_list to actually

 * free these pages later if no one else has touched them in the meantime,

 * although we could add these pages to a global reuse list for

 * shrink_active_list to pick up before reclaiming other pages.

 *
@@ -790,10 +795,34 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, 
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,

					unsigned long start, unsigned long end)

{

	zap_page_range(vma, start, end - start);

	zap_page_range_single(vma, start, end - start, NULL);

	return 0;

}



static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,

					    unsigned long start,

					    unsigned long *end,

					    int behavior)

{

	if (!is_vm_hugetlb_page(vma))

		return can_madv_lru_non_huge_vma(vma);



	if (behavior != MADV_DONTNEED)

		return false;

	if (start & ~huge_page_mask(hstate_vma(vma)))

		return false;



	/*

	 * Madvise callers expect the length to be rounded up to PAGE_SIZE

	 * boundaries, and may be unaware that this VMA uses huge pages.

	 * Avoid unexpected data loss by rounding down the number of

	 * huge pages freed.

	 */

	*end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma)));



	return true;

}



static long madvise_dontneed_free(struct vm_area_struct *vma,

				  struct vm_area_struct **prev,

				  unsigned long start, unsigned long end,
@@ -802,9 +831,12 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, 
	struct mm_struct *mm = vma->vm_mm;



	*prev = vma;

	if (!can_madv_lru_vma(vma))

	if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior))

		return -EINVAL;



	if (start == end)

		return 0;



	if (!userfaultfd_remove(vma, start, end)) {

		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
@@ -824,7 +856,12 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, 
			 */

			return -ENOMEM;

		}

		if (!can_madv_lru_vma(vma))

		/*

		 * Potential end adjustment for hugetlb vma is OK as

		 * the check below keeps end within vma.

		 */

		if (!madvise_dontneed_free_valid_vma(vma, start, &end,

						     behavior))

			return -EINVAL;

		if (end > vma->vm_end) {

			/*