mm/hugetlb: add size parameter to huge_pte_offset()

A poisoned or migrated hugepage is stored as a swap entry in the page
tables.  On architectures that support hugepages consisting of
contiguous page table entries (such as on arm64) this leads to ambiguity
in determining the page table entry to return in huge_pte_offset() when
a poisoned entry is encountered.

Let's remove the ambiguity by adding a size parameter to convey
additional information about the requested address.  Also fixup the
definition/usage of huge_pte_offset() throughout the tree.

Link: http://lkml.kernel.org/r/20170522133604.11392-4-punit.agrawal@arm.com
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Acked-by: Steve Capper <steve.capper@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: James Hogan <james.hogan@imgtec.com> (odd fixer:METAG ARCHITECTURE)
Cc: Ralf Baechle <ralf@linux-mips.org> (supporter:MIPS)
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

11 files changed, 20 insertions, 12 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index f89aa8fa5855..656e0ece2289 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -131,7 +131,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 85de86d36fdf..ae35140332f7 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -44,7 +44,7 @@ huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 }
 
 pte_t *
-huge_pte_offset (struct mm_struct *mm, unsigned long addr)
+huge_pte_offset (struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;
@@ -92,7 +92,7 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int writ
 	if (REGION_NUMBER(addr) != RGN_HPAGE)
 		return ERR_PTR(-EINVAL);
 
-	ptep = huge_pte_offset(mm, addr);
+	ptep = huge_pte_offset(mm, addr, HPAGE_SIZE);
 	if (!ptep || pte_none(*ptep))
 		return NULL;
 	page = pte_page(*ptep);
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index db1b7da91e4f..67fd53e2935a 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -74,7 +74,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 74aa6f62468f..cef152234312 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -36,7 +36,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
+		       unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index aa50ac090e9b..5eb8f633b282 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -69,7 +69,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1816b965a142..c41dc44472c5 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -57,7 +57,7 @@ static unsigned nr_gpages;
 
 #define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d3a5e39756f6..44a8e6f0391e 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -180,7 +180,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return (pte_t *) pmdp;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
 	p4d_t *p4dp;
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index cc948db74878..d2412d2d6462 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -42,7 +42,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 88855e383b34..28ee8d8ffa07 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -277,7 +277,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	return pte;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 03e5cc4e76e4..0986d426a413 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -102,7 +102,8 @@ static pte_t *get_pte(pte_t *base, int index, int level)
 	return ptep;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index adad702b39cd..2824607df108 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -33,7 +33,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 	if (!vma || !is_vm_hugetlb_page(vma))
 		return ERR_PTR(-EINVAL);
 
-	pte = huge_pte_offset(mm, address);
+	pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
 
 	/* hugetlb should be locked, and hence, prefaulted */
 	WARN_ON(!pte || pte_none(*pte));