mm: update ptep_modify_prot_start/commit to take vm_area_struct as arg

Patch series "NestMMU pte upgrade workaround for mprotect", v5.

We can upgrade pte access (R -> RW transition) via mprotect.  We need to
make sure we follow the recommended pte update sequence as outlined in
commit bd5050e3 ("powerpc/mm/radix: Change pte relax sequence to
handle nest MMU hang") for such updates.  This patch series does that.

This patch (of 5):

Some architectures may want to call flush_tlb_range from these helpers.

Link: http://lkml.kernel.org/r/20190116085035.29729-2-aneesh.kumar@linux.ibm.comSigned-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

arch/s390/include/asm/pgtable.h

@@ -1069,8 +1069,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t);
+pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t);
 
 #define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,

arch/s390/mm/pgtable.c

@@ -301,12 +301,13 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(ptep_xchg_lazy);
 
-pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t *ptep)
 {
 	pgste_t pgste;
 	pte_t old;
 	int nodat;
+	struct mm_struct *mm = vma->vm_mm;
 
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
@@ -319,10 +320,11 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 	return old;
 }
 
-void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t *ptep, pte_t pte)
 {
 	pgste_t pgste;
+	struct mm_struct *mm = vma->vm_mm;
 
 	if (!MACHINE_HAS_NX)
 		pte_val(pte) &= ~_PAGE_NOEXEC;

arch/x86/include/asm/paravirt.h

@@ -422,25 +422,26 @@ static inline pgdval_t pgd_val(pgd_t pgd)
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 					   pte_t *ptep)
 {
 	pteval_t ret;
 
-	ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
+	ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep);
 
 	return (pte_t) { .pte = ret };
 }
 
-static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 					   pte_t *ptep, pte_t pte)
 {
+
 	if (sizeof(pteval_t) > sizeof(long))
 		/* 5 arg words */
-		pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
+		pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte);
 	else
 		PVOP_VCALL4(mmu.ptep_modify_prot_commit,
-			    mm, addr, ptep, pte.pte);
+			    vma, addr, ptep, pte.pte);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pte)

arch/x86/include/asm/paravirt_types.h

@@ -55,6 +55,7 @@ struct task_struct;
 struct cpumask;
 struct flush_tlb_info;
 struct mmu_gather;
+struct vm_area_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -254,9 +255,9 @@ struct pv_mmu_ops {
 			   pte_t *ptep, pte_t pteval);
 	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
 
-	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+	pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr,
 					pte_t *ptep);
-	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+	void (*ptep_modify_prot_commit)(struct vm_area_struct *vma, unsigned long addr,
 					pte_t *ptep, pte_t pte);
 
 	struct paravirt_callee_save pte_val;

arch/x86/xen/mmu.h

@@ -17,8 +17,8 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+void  xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t pte);
 
 unsigned long xen_read_cr2_direct(void);

arch/x86/xen/mmu_pv.c

@@ -306,20 +306,20 @@ static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	__xen_set_pte(ptep, pteval);
 }
 
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
 				 unsigned long addr, pte_t *ptep)
 {
 	/* Just return the pte as-is.  We preserve the bits on commit */
-	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
+	trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep);
 	return *ptep;
 }
 
-void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				 pte_t *ptep, pte_t pte)
 {
 	struct mmu_update u;
 
-	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
+	trace_xen_mmu_ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
 	xen_mc_batch();
 
 	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;

fs/proc/task_mmu.c

@@ -948,10 +948,10 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	pte_t ptent = *pte;
 
 	if (pte_present(ptent)) {
-		ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte);
+		ptent = ptep_modify_prot_start(vma, addr, pte);
 		ptent = pte_wrprotect(ptent);
 		ptent = pte_clear_soft_dirty(ptent);
-		ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent);
+		ptep_modify_prot_commit(vma, addr, pte, ptent);
 	} else if (is_swap_pte(ptent)) {
 		ptent = pte_swp_clear_soft_dirty(ptent);
 		set_pte_at(vma->vm_mm, addr, pte, ptent);

include/asm-generic/pgtable.h

@@ -606,7 +606,7 @@ static inline int pmd_none_or_clear_bad(pmd_t *pmd)
 	return 0;
 }
 
-static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
+static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
 					     unsigned long addr,
 					     pte_t *ptep)
 {
@@ -615,10 +615,10 @@ static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
 	 * non-present, preventing the hardware from asynchronously
 	 * updating it.
 	 */
-	return ptep_get_and_clear(mm, addr, ptep);
+	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
 }
 
-static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
+static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
 					     unsigned long addr,
 					     pte_t *ptep, pte_t pte)
 {
@@ -626,7 +626,7 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
 	 * The pte is non-present, so there's no hardware state to
 	 * preserve.
 	 */
-	set_pte_at(mm, addr, ptep, pte);
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
 
 #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -644,22 +644,22 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
  * queue the update to be done at some later time.  The update must be
  * actually committed before the pte lock is released, however.
  */
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
+static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   pte_t *ptep)
 {
-	return __ptep_modify_prot_start(mm, addr, ptep);
+	return __ptep_modify_prot_start(vma, addr, ptep);
 }
 
 /*
  * Commit an update to a pte, leaving any hardware-controlled bits in
  * the PTE unmodified.
  */
-static inline void ptep_modify_prot_commit(struct mm_struct *mm,
+static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   pte_t *ptep, pte_t pte)
 {
-	__ptep_modify_prot_commit(mm, addr, ptep, pte);
+	__ptep_modify_prot_commit(vma, addr, ptep, pte);
 }
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */

mm/memory.c

@@ -3619,12 +3619,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	 * Make it present again, Depending on how arch implementes non
 	 * accessible ptes, some can allow access by kernel mode.
 	 */
-	pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
+	pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
 	pte = pte_modify(pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
-	ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
+	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, pte);
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 
 	page = vm_normal_page(vma, vmf->address, pte);

mm/mprotect.c

@@ -110,7 +110,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 					continue;
 			}
 
-			ptent = ptep_modify_prot_start(mm, addr, pte);
+			ptent = ptep_modify_prot_start(vma, addr, pte);
 			ptent = pte_modify(ptent, newprot);
 			if (preserve_write)
 				ptent = pte_mk_savedwrite(ptent);
@@ -121,7 +121,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 					 !(vma->vm_flags & VM_SOFTDIRTY))) {
 				ptent = pte_mkwrite(ptent);
 			}
-			ptep_modify_prot_commit(mm, addr, pte, ptent);
+			ptep_modify_prot_commit(vma, addr, pte, ptent);
 			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);