8 files changed, 85 insertions, 0 deletions

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index d5562f9ce600..fd9717e9fee3 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -280,6 +280,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr
 	tlb_add_flush(tlb, addr);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb_add_flush(tlb, address);
+	tlb_add_flush(tlb, address + size - PMD_SIZE);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..26d49489498b 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -269,6 +269,16 @@ __tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long addre
 	tlb->end_addr = address + PAGE_SIZE;
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start_addr > address)
+		tlb->start_addr = address;
+	if (tlb->end_addr < address + size)
+		tlb->end_addr = address + size;
+}
+
 #define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
 
 #define tlb_start_vma(tlb, vma)			do { } while (0)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 457b7ba0fbb6..c216a24ddff8 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -116,6 +116,20 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				unsigned long address, unsigned long size)
+{
+	/*
+	 * the range might exceed the original range that was provided to
+	 * tlb_gather_mmu(), so we need to update it despite the fact it is
+	 * usually not updated.
+	 */
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 77abe192fb43..adcb0bfe238e 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -127,6 +127,16 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 #define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 						     unsigned int page_size)
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index dce6db147f24..02e61f6abfca 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -130,6 +130,18 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 	return tlb_remove_page(tlb, page);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb->need_flush = 1;
+
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index faddde44de8c..5e7e4aaf36c5 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -117,6 +117,8 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+			 unsigned long size);
 extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c765fd01f0aa..515ba949c06a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3386,6 +3386,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	unsigned long sz = huge_page_size(h);
 	const unsigned long mmun_start = start;	/* For mmu_notifiers */
 	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
+	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
@@ -3407,6 +3408,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			spin_unlock(ptl);
+			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+			force_flush = true;
 			continue;
 		}
 
@@ -3463,6 +3466,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	}
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	tlb_end_vma(tlb, vma);
+
+	/*
+	 * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+	 * could defer the flush until now, since by holding i_mmap_rwsem we
+	 * guaranteed that the last refernece would not be dropped. But we must
+	 * do the flushing before we return, as otherwise i_mmap_rwsem will be
+	 * dropped and the last reference to the shared PMDs page might be
+	 * dropped as well.
+	 *
+	 * In theory we could defer the freeing of the PMD pages as well, but
+	 * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+	 * detect sharing, so we cannot defer the release of the page either.
+	 * Instead, do flush now.
+	 */
+	if (force_flush)
+		tlb_flush_mmu(tlb);
 }
 
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
diff --git a/mm/memory.c b/mm/memory.c
index c4f142d1ff98..b001670c9615 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -335,6 +335,16 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+			 unsigned long size)
+{
+	if (tlb->page_size != 0 && tlb->page_size != PMD_SIZE)
+		tlb_flush_mmu(tlb);
+
+	tlb->page_size = PMD_SIZE;
+	tlb->start = min(tlb->start, address);
+	tlb->end = max(tlb->end, address + size);
+}
 #endif /* HAVE_GENERIC_MMU_GATHER */
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE