[PATCH 0/4] hugetlb: Disable huge pmd unshare for uffd-wp

[PATCH 0/4] hugetlb: Disable huge pmd unshare for uffd-wp

[Peter Xu]

This series tries to disable huge pmd unshare of hugetlbfs backed memory for
uffd-wp.  Although uffd-wp of hugetlbfs is still during rfc stage, the idea of
this series may be needed for multiple tasks (Axel's uffd minor fault series,
and Mike's soft dirty series), so I picked it out from the larger series.

References works:

Uffd shmem+hugetlbfs rfc:
https://lore.kernel.org/lkml/20210115170907.24498-1-peterx@redhat.com/

Uffd minor mode for hugetlbfs:
https://lore.kernel.org/lkml/20210212215403.3457686-1-axelrasmussen@google.com/

Soft dirty for hugetlbfs:
https://lore.kernel.org/lkml/20210211000322.159437-1-mike.kravetz@oracle.com/

Please review, thanks.

Peter Xu (4):
  hugetlb: Pass vma into huge_pte_alloc() and huge_pmd_share()
  hugetlb/userfaultfd: Forbid huge pmd sharing when uffd enabled
  mm/hugetlb: Move flush_hugetlb_tlb_range() into hugetlb.h
  hugetlb/userfaultfd: Unshare all pmds for hugetlbfs when register wp

 arch/arm64/mm/hugetlbpage.c   |  7 ++---
 arch/ia64/mm/hugetlbpage.c    |  3 +-
 arch/mips/mm/hugetlbpage.c    |  4 +--
 arch/parisc/mm/hugetlbpage.c  |  2 +-
 arch/powerpc/mm/hugetlbpage.c |  3 +-
 arch/s390/mm/hugetlbpage.c    |  2 +-
 arch/sh/mm/hugetlbpage.c      |  2 +-
 arch/sparc/mm/hugetlbpage.c   |  1 +
 fs/userfaultfd.c              | 57 +++++++++++++++++++++++++++++++++++
 include/linux/hugetlb.h       | 15 +++++++--
 include/linux/userfaultfd_k.h |  9 ++++++
 mm/hugetlb.c                  | 43 +++++++++++++-------------
 mm/userfaultfd.c              |  2 +-
 13 files changed, 115 insertions(+), 35 deletions(-)

-- 
2.26.2

[PATCH 1/4] hugetlb: Pass vma into huge_pte_alloc() and huge_pmd_share()

[Peter Xu]

It is a preparation work to be able to behave differently in the per
architecture huge_pte_alloc() according to different VMA attributes.

Pass it deeper into huge_pmd_share() so that we can avoid the find_vma() call.

Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 arch/arm64/mm/hugetlbpage.c   |  4 ++--
 arch/ia64/mm/hugetlbpage.c    |  3 ++-
 arch/mips/mm/hugetlbpage.c    |  4 ++--
 arch/parisc/mm/hugetlbpage.c  |  2 +-
 arch/powerpc/mm/hugetlbpage.c |  3 ++-
 arch/s390/mm/hugetlbpage.c    |  2 +-
 arch/sh/mm/hugetlbpage.c      |  2 +-
 arch/sparc/mm/hugetlbpage.c   |  1 +
 include/linux/hugetlb.h       |  5 +++--
 mm/hugetlb.c                  | 15 ++++++++-------
 mm/userfaultfd.c              |  2 +-
 11 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 55ecf6de9ff7..6e3bcffe2837 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -252,7 +252,7 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 		set_pte(ptep, pte);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
@@ -286,7 +286,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
 		    pud_none(READ_ONCE(*pudp)))
-			ptep = huge_pmd_share(mm, addr, pudp);
+			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (CONT_PMD_SIZE)) {
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index b331f94d20ac..f993cb36c062 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -25,7 +25,8 @@ unsigned int hpage_shift = HPAGE_SHIFT_DEFAULT;
 EXPORT_SYMBOL(hpage_shift);
 
 pte_t *
-huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+	       unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index b9f76f433617..7eaff5b07873 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -21,8 +21,8 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
-		      unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index d7ba014a7fbb..e141441bfa64 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -44,7 +44,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 }
 
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8b3cc4d688e8..d57276b8791c 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -106,7 +106,8 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
  * At this point we do the placement change only for BOOK3S 64. This would
  * possibly work on other subarchs.
  */
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pg;
 	p4d_t *p4;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 3b5a4d25ca9b..da36d13ffc16 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -189,7 +189,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 220d7bc43d2b..999ab5916e69 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -21,7 +21,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ad4b42f04988..97e0824fdbe7 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -280,6 +280,7 @@ unsigned long pmd_leaf_size(pmd_t pmd) { return 1UL << tte_to_shift(*(pte_t *)&p
 unsigned long pte_leaf_size(pte_t pte) { return 1UL << tte_to_shift(pte); }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b5807f23caf8..a6113fa6d21d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -152,7 +152,8 @@ void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
 u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
 
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud);
 
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);
 
@@ -161,7 +162,7 @@ extern struct list_head huge_boot_pages;
 
 /* arch callbacks */
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4bdb58ab14cb..07bb9bdc3282 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3807,7 +3807,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, addr, sz);
+		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4544,7 +4544,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	mapping = vma->vm_file->f_mapping;
 	i_mmap_lock_read(mapping);
-	ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+	ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h));
 	if (!ptep) {
 		i_mmap_unlock_read(mapping);
 		return VM_FAULT_OOM;
@@ -5334,9 +5334,9 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
  * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is
  * only required for subsequent processing.
  */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud)
 {
-	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
 			vma->vm_pgoff;
@@ -5414,7 +5414,8 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 #define want_pmd_share()	(1)
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
-pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
+		      unsigned long addr, pud_t *pud)
 {
 	return NULL;
 }
@@ -5433,7 +5434,7 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
@@ -5452,7 +5453,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (want_pmd_share() && pud_none(*pud))
-				pte = huge_pmd_share(mm, addr, pud);
+				pte = huge_pmd_share(mm, vma, addr, pud);
 			else
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9a3d451402d7..063cbb17e8d8 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -290,7 +290,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		err = -ENOMEM;
-		dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize);
+		dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize);
 		if (!dst_pte) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);
-- 
2.26.2

[PATCH 2/4] hugetlb/userfaultfd: Forbid huge pmd sharing when uffd enabled

[Peter Xu]

Huge pmd sharing could bring problem to userfaultfd.  The thing is that
userfaultfd is running its logic based on the special bits on page table
entries, however the huge pmd sharing could potentially share page table
entries for different address ranges.  That could cause issues on either:

  - When sharing huge pmd page tables for an uffd write protected range, the
    newly mapped huge pmd range will also be write protected unexpectedly, or,

  - When we try to write protect a range of huge pmd shared range, we'll first
    do huge_pmd_unshare() in hugetlb_change_protection(), however that also
    means the UFFDIO_WRITEPROTECT could be silently skipped for the shared
    region, which could lead to data loss.

Since at it, a few other things are done altogether:

  - Move want_pmd_share() from mm/hugetlb.c into linux/hugetlb.h, because
    that's definitely something that arch code would like to use too

  - ARM64 currently directly check against CONFIG_ARCH_WANT_HUGE_PMD_SHARE when
    trying to share huge pmd.  Switch to the want_pmd_share() helper.

Since at it, move vma_shareable() from huge_pmd_share() into want_pmd_share().

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 arch/arm64/mm/hugetlbpage.c   |  3 +--
 include/linux/hugetlb.h       |  2 ++
 include/linux/userfaultfd_k.h |  9 +++++++++
 mm/hugetlb.c                  | 20 ++++++++++++++------
 4 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 6e3bcffe2837..58987a98e179 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -284,8 +284,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		ptep = pte_alloc_map(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
-		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
-		    pud_none(READ_ONCE(*pudp)))
+		if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp)))
 			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index a6113fa6d21d..bc86f2f516e7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -950,4 +950,6 @@ static inline __init void hugetlb_cma_check(void)
 }
 #endif
 
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
+
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index a8e5f3ea9bb2..c63ccdae3eab 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -52,6 +52,15 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 	return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx;
 }
 
+/*
+ * Never enable huge pmd sharing on uffd-wp registered vmas, because uffd-wp
+ * protect information is per pgtable entry.
+ */
+static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_UFFD_WP;
+}
+
 static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_UFFD_MISSING;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 07bb9bdc3282..8e8e2f3dfe06 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5292,6 +5292,18 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	return false;
 }
 
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr)
+{
+#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+	return false;
+#endif
+#ifdef CONFIG_USERFAULTFD
+	if (uffd_disable_huge_pmd_share(vma))
+		return false;
+#endif
+	return vma_shareable(vma, addr);
+}
+
 /*
  * Determine if start,end range within vma could be mapped by shared pmd.
  * If yes, adjust start and end to cover range associated with possible
@@ -5346,9 +5358,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (!vma_shareable(vma, addr))
-		return (pte_t *)pmd_alloc(mm, pud, addr);
-
 	i_mmap_assert_locked(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
@@ -5412,7 +5421,7 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
 	return 1;
 }
-#define want_pmd_share()	(1)
+
 #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct vma,
 		      unsigned long addr, pud_t *pud)
@@ -5430,7 +5439,6 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
 }
-#define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
 #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
@@ -5452,7 +5460,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			pte = (pte_t *)pud;
 		} else {
 			BUG_ON(sz != PMD_SIZE);
-			if (want_pmd_share() && pud_none(*pud))
+			if (want_pmd_share(vma, addr) && pud_none(*pud))
 				pte = huge_pmd_share(mm, vma, addr, pud);
 			else
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
-- 
2.26.2

[PATCH 3/4] mm/hugetlb: Move flush_hugetlb_tlb_range() into hugetlb.h

[Peter Xu]

Prepare for it to be called outside of mm/hugetlb.c.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/linux/hugetlb.h | 8 ++++++++
 mm/hugetlb.c            | 8 --------
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bc86f2f516e7..3b4104021dd3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -952,4 +952,12 @@ static inline __init void hugetlb_cma_check(void)
 
 bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
 
+#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+/*
+ * ARCHes with special requirements for evicting HUGETLB backing TLB entries can
+ * implement this.
+ */
+#define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
+#endif
+
 #endif /* _LINUX_HUGETLB_H */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8e8e2f3dfe06..f53a0b852ed8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4965,14 +4965,6 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	return i ? i : err;
 }
 
-#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
-/*
- * ARCHes with special requirements for evicting HUGETLB backing TLB entries can
- * implement this.
- */
-#define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
-#endif
-
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot)
 {
-- 
2.26.2

[PATCH 4/4] hugetlb/userfaultfd: Unshare all pmds for hugetlbfs when register wp

[Peter Xu]

Huge pmd sharing for hugetlbfs is racy with userfaultfd-wp because
userfaultfd-wp is always based on pgtable entries, so they cannot be shared.

Walk the hugetlb range and unshare all such mappings if there is, right before
UFFDIO_REGISTER will succeed and return to userspace.

This will pair with want_pmd_share() in hugetlb code so that huge pmd sharing
is completely disabled for userfaultfd-wp registered range.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 fs/userfaultfd.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 894cc28142e7..3fbdacc25ff4 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
+#include <linux/mmu_notifier.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
@@ -1190,6 +1191,59 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf,
 	}
 }
 
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+static void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_notifier_range range;
+	unsigned long address, start, end;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	start = ALIGN(vma->vm_start, PUD_SIZE);
+	end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
+
+	if (start >= end)
+		return;
+
+	/*
+	 * No need to call adjust_range_if_pmd_sharing_possible(), because
+	 * we're going to operate on the whole vma
+	 */
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+				vma->vm_start, vma->vm_end);
+	mmu_notifier_invalidate_range_start(&range);
+	i_mmap_lock_write(vma->vm_file->f_mapping);
+	for (address = start; address < end; address += PUD_SIZE) {
+		unsigned long tmp = address;
+
+		ptep = huge_pte_offset(mm, address, sz);
+		if (!ptep)
+			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
+		/* We don't want 'address' to be changed */
+		huge_pmd_unshare(mm, vma, &tmp, ptep);
+		spin_unlock(ptl);
+	}
+	flush_hugetlb_tlb_range(vma, vma->vm_start, vma->vm_end);
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	/*
+	 * No need to call mmu_notifier_invalidate_range(), see
+	 * Documentation/vm/mmu_notifier.rst.
+	 */
+	mmu_notifier_invalidate_range_end(&range);
+#endif
+}
+
 static void __wake_userfault(struct userfaultfd_ctx *ctx,
 			     struct userfaultfd_wake_range *range)
 {
@@ -1448,6 +1502,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx.ctx = ctx;
 
+		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+			hugetlb_unshare_all_pmds(vma);
+
 	skip:
 		prev = vma;
 		start = vma->vm_end;
-- 
2.26.2

Re: [PATCH 1/4] hugetlb: Pass vma into huge_pte_alloc() and huge_pmd_share()

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 5882 bytes --]

Hi Peter,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on linux/master linus/master hnaz-linux-mm/master v5.11 next-20210217]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210218-003520
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
config: sparc-allyesconfig (attached as .config)
compiler: sparc64-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/0day-ci/linux/commit/58ca9ac367f24752915f352fa9ae1ae027a29de3
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Peter-Xu/hugetlb-Disable-huge-pmd-unshare-for-uffd-wp/20210218-003520
        git checkout 58ca9ac367f24752915f352fa9ae1ae027a29de3
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=sparc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> arch/sparc/mm/hugetlbpage.c:285:1: error: expected ';', ',' or ')' before '{' token
     285 | {
         | ^
>> arch/sparc/mm/hugetlbpage.c:269:22: error: 'huge_tte_to_size' defined but not used [-Werror=unused-function]
     269 | static unsigned long huge_tte_to_size(pte_t pte)
         |                      ^~~~~~~~~~~~~~~~
   cc1: all warnings being treated as errors


vim +285 arch/sparc/mm/hugetlbpage.c

c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  268  
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01 @269  static unsigned long huge_tte_to_size(pte_t pte)
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  270  {
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  271  	unsigned long size = 1UL << huge_tte_to_shift(pte);
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  272  
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  273  	if (size == REAL_HPAGE_SIZE)
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  274  		size = HPAGE_SIZE;
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  275  	return size;
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  276  }
c7d9f77d33a779 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-01  277  
e6e4f42eb773c1 arch/sparc/mm/hugetlbpage.c   Peter Zijlstra 2020-11-13  278  unsigned long pud_leaf_size(pud_t pud) { return 1UL << tte_to_shift(*(pte_t *)&pud); }
e6e4f42eb773c1 arch/sparc/mm/hugetlbpage.c   Peter Zijlstra 2020-11-13  279  unsigned long pmd_leaf_size(pmd_t pmd) { return 1UL << tte_to_shift(*(pte_t *)&pmd); }
e6e4f42eb773c1 arch/sparc/mm/hugetlbpage.c   Peter Zijlstra 2020-11-13  280  unsigned long pte_leaf_size(pte_t pte) { return 1UL << tte_to_shift(pte); }
e6e4f42eb773c1 arch/sparc/mm/hugetlbpage.c   Peter Zijlstra 2020-11-13  281  
a5516438959d90 arch/sparc64/mm/hugetlbpage.c Andi Kleen     2008-07-23  282  pte_t *huge_pte_alloc(struct mm_struct *mm,
58ca9ac367f247 arch/sparc/mm/hugetlbpage.c   Peter Xu       2021-02-17  283  pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
a5516438959d90 arch/sparc64/mm/hugetlbpage.c Andi Kleen     2008-07-23  284  			unsigned long addr, unsigned long sz)
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16 @285  {
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  286  	pgd_t *pgd;
5637bc50483404 arch/sparc/mm/hugetlbpage.c   Mike Rapoport  2019-11-24  287  	p4d_t *p4d;
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  288  	pud_t *pud;
dcd1912d21a025 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-06  289  	pmd_t *pmd;
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  290  
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  291  	pgd = pgd_offset(mm, addr);
5637bc50483404 arch/sparc/mm/hugetlbpage.c   Mike Rapoport  2019-11-24  292  	p4d = p4d_offset(pgd, addr);
5637bc50483404 arch/sparc/mm/hugetlbpage.c   Mike Rapoport  2019-11-24  293  	pud = pud_alloc(mm, p4d, addr);
df7b2155bbe755 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  294  	if (!pud)
df7b2155bbe755 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  295  		return NULL;
df7b2155bbe755 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  296  	if (sz >= PUD_SIZE)
4dbe87d5a70215 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  297  		return (pte_t *)pud;
dcd1912d21a025 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-06  298  	pmd = pmd_alloc(mm, pud, addr);
dcd1912d21a025 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-06  299  	if (!pmd)
dcd1912d21a025 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-02-06  300  		return NULL;
59f1183dd368f1 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-03-03  301  	if (sz >= PMD_SIZE)
4dbe87d5a70215 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  302  		return (pte_t *)pmd;
4dbe87d5a70215 arch/sparc/mm/hugetlbpage.c   Nitin Gupta    2017-08-11  303  	return pte_alloc_map(mm, pmd, addr);
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  304  }
^1da177e4c3f41 arch/sparc64/mm/hugetlbpage.c Linus Torvalds 2005-04-16  305  

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 68769 bytes --]