mm: hugetlb: Add huge page size param to huge_ptep_get_and_clear()

Ryan Roberts · willdeacon · commit 02410ac72ac3 · 2025-02-27T17:40:57.000Z
In order to fix a bug, arm64 needs to be told the size of the huge page for which the huge_pte is being cleared in huge_ptep_get_and_clear(). Provide for this by adding an `unsigned long sz` parameter to the function. This follows the same pattern as huge_pte_clear() and set_huge_pte_at(). This commit makes the required interface modifications to the core mm as well as all arches that implement this function (arm64, loongarch, mips, parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed in a separate commit. Cc: stable@vger.kernel.org Fixes: 66b3923 ("arm64: hugetlb: add support for PTE contiguous bit") Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> # riscv Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> # s390 Link: https://lore.kernel.org/r/20250226120656.2400136-2-ryan.roberts@arm.com Signed-off-by: Will Deacon <will@kernel.org>
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
@@ -396,8 +396,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
@@ -549,6 +549,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
@@ -90,7 +90,7 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-		unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep, unsigned long sz)
 {
 	return ptep_get_and_clear(mm, addr, ptep);
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
@@ -1004,7 +1004,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 #endif
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
@@ -5447,7 +5447,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
-	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
+	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz);
 
 	if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
 		huge_pte_clear(mm, new_addr, dst_pte, sz);
@@ -5622,7 +5622,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
 		}
 
-		pte = huge_ptep_get_and_clear(mm, address, ptep);
+		pte = huge_ptep_get_and_clear(mm, address, ptep, sz);
 		tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);

Original file line number	Diff line number	Diff line change
`@@ -396,8 +396,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,`
`396`	`396`	`__pte_clear(mm, addr, ptep);`
`397`	`397`	`}`
`398`	`398`
`399`		`-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,`
`400`		`- unsigned long addr, pte_t *ptep)`
	`399`	`+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,`
	`400`	`+ pte_t *ptep, unsigned long sz)`
`401`	`401`	`{`
`402`	`402`	`int ncontig;`
`403`	`403`	`size_t pgsize;`
`@@ -549,6 +549,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)`
`549`	`549`
`550`	`550`	`pte_t huge_ptep_modify_prot_start(struct vm_area_struct vma, unsigned long addr, pte_t ptep)`
`551`	`551`	`{`
	`552`	`+ unsigned long psize = huge_page_size(hstate_vma(vma));`
	`553`	`+`
`552`	`554`	`if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {`
`553`	`555`	`/*`
`554`	`556`	`* Break-before-make (BBM) is required for all user space mappings`
`@@ -558,7 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr`
`558`	`560`	`if (pte_user_exec(__ptep_get(ptep)))`
`559`	`561`	`return huge_ptep_clear_flush(vma, addr, ptep);`
`560`	`562`	`}`
`561`		`- return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);`
	`563`	`+ return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);`
`562`	`564`	`}`
`563`	`565`
`564`	`566`	`void huge_ptep_modify_prot_commit(struct vm_area_struct vma, unsigned long addr, pte_t ptep,`
Original file line number	Diff line number	Diff line change
`@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,`
`36`	`36`
`37`	`37`	`#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR`
`38`	`38`	`static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,`
`39`		`- unsigned long addr, pte_t *ptep)`
	`39`	`+ unsigned long addr, pte_t *ptep,`
	`40`	`+ unsigned long sz)`
`40`	`41`	`{`
`41`	`42`	`pte_t clear;`
`42`	`43`	`pte_t pte = ptep_get(ptep);`
`@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,`
`51`	`52`	`unsigned long addr, pte_t *ptep)`
`52`	`53`	`{`
`53`	`54`	`pte_t pte;`
	`55`	`+ unsigned long sz = huge_page_size(hstate_vma(vma));`
`54`	`56`
`55`		`- pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);`
	`57`	`+ pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);`
`56`	`58`	`flush_tlb_page(vma, addr);`
`57`	`59`	`return pte;`
`58`	`60`	`}`
Original file line number	Diff line number	Diff line change
`@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,`
`126`	`126`
`127`	`127`
`128`	`128`	`pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,`
`129`		`- pte_t *ptep)`
	`129`	`+ pte_t *ptep, unsigned long sz)`
`130`	`130`	`{`
`131`	`131`	`pte_t entry;`
`132`	`132`
Original file line number	Diff line number	Diff line change
`@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct mm, unsigned long addr, pte_t ptep,`
`45`	`45`
`46`	`46`	`#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR`
`47`	`47`	`static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,`
`48`		`- unsigned long addr, pte_t *ptep)`
	`48`	`+ unsigned long addr, pte_t *ptep,`
	`49`	`+ unsigned long sz)`
`49`	`50`	`{`
`50`	`51`	`return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));`
`51`	`52`	`}`
`@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,`
`55`	`56`	`unsigned long addr, pte_t *ptep)`
`56`	`57`	`{`
`57`	`58`	`pte_t pte;`
	`59`	`+ unsigned long sz = huge_page_size(hstate_vma(vma));`
`58`	`60`
`59`		`- pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);`
	`61`	`+ pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);`
`60`	`62`	`flush_hugetlb_page(vma, addr);`
`61`	`63`	`return pte;`
`62`	`64`	`}`
Original file line number	Diff line number	Diff line change
`@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,`
`293`	`293`
`294`	`294`	`pte_t huge_ptep_get_and_clear(struct mm_struct *mm,`
`295`	`295`	`unsigned long addr,`
`296`		`- pte_t *ptep)`
	`296`	`+ pte_t *ptep, unsigned long sz)`
`297`	`297`	`{`
`298`	`298`	`pte_t orig_pte = ptep_get(ptep);`
`299`	`299`	`int pte_num;`