Skip to contentSkip to conversation

NestMMU pte upgrade workaround for mprotect

PATCH Superseded Aneesh Kumar K.V 4 participants 16 messages Dec 5, 2018 – Dec 18, 2018

Subsystems (12)
Memory management x86 PowerPC MM core +8 more subsystems

v3 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

Aneesh Kumar K.V

author
#0 lore raw

v3 cover NestMMU pte upgrade workaround for mprotect

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 bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang") for such updates. This patch series do that.

Changes from V2:
* Update commit message for patch 4
* use radix tlb flush routines directly.

Changes from V1:
* Restrict ths only for R->RW upgrade. We don't need to do this for Autonuma
* Restrict this only for radix translation mode.

Aneesh Kumar K.V (5):
mm: Update ptep_modify_prot_start/commit to take vm_area_struct as arg
mm: update ptep_modify_prot_commit to take old pte value as arg arch/powerpc/mm: Nest MMU workaround for mprotect RW upgrade. mm/hugetlb: Add prot_modify_start/commit sequence for hugetlb update arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW
upgrade

 arch/powerpc/include/asm/book3s/64/hugetlb.h | 12 ++++++++
 arch/powerpc/include/asm/book3s/64/pgtable.h | 18 ++++++++++++
 arch/powerpc/include/asm/book3s/64/radix.h   |  4 +++
 arch/powerpc/mm/hugetlbpage-radix.c          | 17 ++++++++++++
 arch/powerpc/mm/hugetlbpage.c                | 29 ++++++++++++++++++++
 arch/powerpc/mm/pgtable-book3s64.c           | 27 ++++++++++++++++++
 arch/powerpc/mm/pgtable-radix.c              | 18 ++++++++++++
 arch/s390/include/asm/pgtable.h              |  5 ++--
 arch/s390/mm/pgtable.c                       |  8 ++++--
 arch/x86/include/asm/paravirt.h              |  9 ++++--
 fs/proc/task_mmu.c                           |  8 ++++--
 include/asm-generic/pgtable.h                | 10 +++----
 include/linux/hugetlb.h                      | 20 ++++++++++++++
 mm/hugetlb.c                                 |  8 ++++--
 mm/memory.c                                  |  8 +++---
 mm/mprotect.c                                |  6 ++--
 16 files changed, 181 insertions(+), 26 deletions(-)
Signature · 1 line
2.19.2
author
#1 lore raw

PATCH v3 1/5 mm: Update ptep_modify_prot_start/commit to take vm_area_struct as arg

Some architecture may want to call flush_tlb_range from these helpers.

Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 arch/s390/include/asm/pgtable.h | 4 ++--
 arch/s390/mm/pgtable.c          | 6 ++++--
 arch/x86/include/asm/paravirt.h | 7 +++++--
 fs/proc/task_mmu.c              | 4 ++--
 include/asm-generic/pgtable.h   | 8 ++++----
 mm/memory.c                     | 4 ++--
 mm/mprotect.c                   | 4 ++--
 7 files changed, 21 insertions(+), 16 deletions(-)
arch/s390/include/asm/pgtable.h +2 -2
index 063732414dfb..5d730199e37b 100644
@@ -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 +4 -2
index f2cc7da473e4..29c0a21cd34a 100644
@@ -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);

@@ -320,10 +321,11 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(ptep_modify_prot_start);
 
-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 +5 -2
index 4bf42f9e4eea..1154f154025d 100644
@@ -417,19 +417,22 @@ 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;
+	struct mm_struct *mm = vma->vm_mm;
 
 	ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, 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)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	if (sizeof(pteval_t) > sizeof(long))
 		/* 5 arg words */
 		pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
fs/proc/task_mmu.c +2 -2
index 47c3764c469b..9952d7185170 100644
@@ -940,10 +940,10 @@ 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 +4 -4
index 359fb935ded6..c9897dcc46c4 100644
@@ -606,22 +606,22 @@ 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->vm_mm, 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->vm_mm, addr, ptep, pte);
 }
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */
mm/memory.c +2 -2
index 4ad2d293ddc2..d36b0eaa7862 100644
@@ -3588,12 +3588,12 @@ 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 +2 -2
index 6d331620b9e5..a301d4c83d3c 100644
@@ -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);
Signature · 1 line
2.19.2
build bot
#2 lore raw

Re: [PATCH V3 1/5] mm: Update ptep_modify_prot_start/commit to take vm_area_struct as arg

I love your patch! Yet something to improve:

Hi Aneesh,

I love your patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v4.20-rc5 next-20181206]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url: https://github.com/0day-ci/linux/commits/Aneesh-Kumar-K-V/NestMMU-pte-upgrade-workaround-for-mprotect/20181207-040417
config: x86_64-allmodconfig (attached as .config)
compiler: gcc-7 (Debian 7.3.0-1) 7.3.0 reproduce:

        # save the attached .config to linux build tree
        make ARCH=x86_64

All errors (new ones prefixed by >>):

In file included from arch/x86/include/asm/msr.h:246:0,

                    from arch/x86/include/asm/processor.h:21,
                    from arch/x86/include/asm/cpufeature.h:8,
                    from arch/x86/include/asm/thread_info.h:53,
                    from include/linux/thread_info.h:38,
                    from arch/x86/include/asm/preempt.h:7,
                    from include/linux/preempt.h:81,
                    from include/linux/spinlock.h:51,
                    from include/linux/mmzone.h:8,
                    from include/linux/gfp.h:6,
                    from include/linux/slab.h:15,
                    from include/linux/crypto.h:24,
                    from arch/x86/kernel/asm-offsets.c:9:
   arch/x86/include/asm/paravirt.h: In function 'ptep_modify_prot_start':
>> arch/x86/include/asm/paravirt.h:424:28: error: dereferencing pointer to incomplete type 'struct vm_area_struct'
     struct mm_struct *mm = vma->vm_mm;
                               ^~

make[2]: *** [arch/x86/kernel/asm-offsets.s] Error 1 make[2]: Target '__build' not remade because of errors. make[1]: *** [prepare0] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [sub-make] Error 2

vim +424 arch/x86/include/asm/paravirt.h

418
419 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
420 static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
421 pte_t *ptep)
422 {
423 pteval_t ret;

 > 424		struct mm_struct *mm = vma->vm_mm;

425
426 ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
427
428 return (pte_t) { .pte = ret };
429 }
430

---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation

author
#3 lore raw

Re: [PATCH V3 1/5] mm: Update ptep_modify_prot_start/commit to take vm_area_struct as arg

Quoted 31 lines · kbuild test robot

Hi Aneesh,

I love your patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v4.20-rc5 next-20181206]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url: https://github.com/0day-ci/linux/commits/Aneesh-Kumar-K-V/NestMMU-pte-upgrade-workaround-for-mprotect/20181207-040417
config: x86_64-allmodconfig (attached as .config)
compiler: gcc-7 (Debian 7.3.0-1) 7.3.0 reproduce:

        # save the attached .config to linux build tree
        make ARCH=x86_64

All errors (new ones prefixed by >>):

   In file included from arch/x86/include/asm/msr.h:246:0,
                    from arch/x86/include/asm/processor.h:21,
                    from arch/x86/include/asm/cpufeature.h:8,
                    from arch/x86/include/asm/thread_info.h:53,
                    from include/linux/thread_info.h:38,
                    from arch/x86/include/asm/preempt.h:7,
                    from include/linux/preempt.h:81,
                    from include/linux/spinlock.h:51,
                    from include/linux/mmzone.h:8,
                    from include/linux/gfp.h:6,
                    from include/linux/slab.h:15,
                    from include/linux/crypto.h:24,
                    from arch/x86/kernel/asm-offsets.c:9:
   arch/x86/include/asm/paravirt.h: In function 'ptep_modify_prot_start':
Quoted 9 lines
Quoted 1 line
Quoted 1 line

arch/x86/include/asm/paravirt.h:424:28: error: dereferencing pointer to incomplete type 'struct vm_area_struct'

     struct mm_struct *mm = vma->vm_mm;
                               ^~

make[2]: *** [arch/x86/kernel/asm-offsets.s] Error 1 make[2]: Target '__build' not remade because of errors. make[1]: *** [prepare0] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [sub-make] Error 2

The fix turned out to be more code changes than what I expected. Instead of adding mm_types.h to paravirt.h, I changed most of the related functions to take vm_area_struct. That brings all ptep_modify_prot_start variants to take vm_area_struct as arg and IMHO that is better. What do you think?

arch/x86/include/asm/paravirt.h +3 -5
index 0d75a4f60500..28152236a65b 100644
@@ -421,9 +421,8 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned
 					   pte_t *ptep)
 {
 	pteval_t ret;
-	struct mm_struct *mm = vma->vm_mm;
 
-	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 };
 }

@@ -431,14 +430,13 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned
 static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
-	struct mm_struct *mm = vma->vm_mm;
 
 	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 +3 -2
index 26942ad63830..609a728ec809 100644
@@ -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 +2 -2
index a7e47cf7ec6c..6e4c6bd62203 100644
@@ -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 +4 -4
index a5d7ed125337..b7c89619cfc9 100644
@@ -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;
include/asm-generic/pgtable.h +6 -6
index 37039e918f17..3ff8b1c3f003 100644
@@ -568,7 +568,7 @@ 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)
 {

@@ -577,10 +577,10 @@ 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)
 {

@@ -588,7 +588,7 @@ 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

@@ -610,7 +610,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   pte_t *ptep)
 {
-	return __ptep_modify_prot_start(vma->vm_mm, addr, ptep);
+	return __ptep_modify_prot_start(vma, addr, ptep);
 }
 
 /*

@@ -621,7 +621,7 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
-	__ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
+	__ptep_modify_prot_commit(vma, addr, ptep, pte);
 }
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */
author
#4 lore raw

PATCH v3 2/5 mm: update ptep_modify_prot_commit to take old pte value as arg

In reply to Aneesh Kumar K.V

Architectures like ppc64 requires to do a conditional tlb flush based on the old and new value of pte. Enable that by passing old pte value as the arg.

Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 arch/s390/include/asm/pgtable.h | 3 ++-
 arch/s390/mm/pgtable.c          | 2 +-
 arch/x86/include/asm/paravirt.h | 2 +-
 fs/proc/task_mmu.c              | 8 +++++---
 include/asm-generic/pgtable.h   | 2 +-
 mm/memory.c                     | 8 ++++----
 mm/mprotect.c                   | 6 +++---
 7 files changed, 17 insertions(+), 14 deletions(-)
arch/s390/include/asm/pgtable.h +2 -1
index 5d730199e37b..76dc344edb8c 100644
@@ -1070,7 +1070,8 @@ 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 vm_area_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+			     pte_t *, 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 +1 -1
index 29c0a21cd34a..b283b92722cc 100644
@@ -322,7 +322,7 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 EXPORT_SYMBOL(ptep_modify_prot_start);
 
 void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-			     pte_t *ptep, pte_t pte)
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
 {
 	pgste_t pgste;
 	struct mm_struct *mm = vma->vm_mm;
arch/x86/include/asm/paravirt.h +1 -1
index 1154f154025d..0d75a4f60500 100644
@@ -429,7 +429,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned
 }
 
 static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-					   pte_t *ptep, pte_t pte)
+					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
fs/proc/task_mmu.c +5 -3
index 9952d7185170..8d62891d38a8 100644
@@ -940,10 +940,12 @@ 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, addr, pte);
-		ptent = pte_wrprotect(ptent);
+		pte_t old_pte;
+
+		old_pte = ptep_modify_prot_start(vma, addr, pte);
+		ptent = pte_wrprotect(old_pte);
 		ptent = pte_clear_soft_dirty(ptent);
-		ptep_modify_prot_commit(vma, addr, pte, ptent);
+		ptep_modify_prot_commit(vma, addr, pte, old_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 +1 -1
index c9897dcc46c4..37039e918f17 100644
@@ -619,7 +619,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
  */
 static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 					   unsigned long addr,
-					   pte_t *ptep, pte_t pte)
+					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
 	__ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
 }
mm/memory.c +4 -4
index d36b0eaa7862..4f3ddaedc764 100644
@@ -3568,7 +3568,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
-	pte_t pte;
+	pte_t pte, old_pte;
 	bool was_writable = pte_savedwrite(vmf->orig_pte);
 	int flags = 0;
 

@@ -3588,12 +3588,12 @@ 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, vmf->address, vmf->pte);
-	pte = pte_modify(pte, vma->vm_page_prot);
+	old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+	pte = pte_modify(old_pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
-	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, pte);
+	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 
 	page = vm_normal_page(vma, vmf->address, pte);
mm/mprotect.c +3 -3
index a301d4c83d3c..1b46b1b1248d 100644
@@ -110,8 +110,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 					continue;
 			}
 
-			ptent = ptep_modify_prot_start(vma, addr, pte);
-			ptent = pte_modify(ptent, newprot);
+			oldpte = ptep_modify_prot_start(vma, addr, pte);
+			ptent = pte_modify(oldpte, 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(vma, addr, pte, ptent);
+			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
 			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
Signature · 1 line
2.19.2
#5 lore raw

Re: [PATCH V3 2/5] mm: update ptep_modify_prot_commit to take old pte value as arg

Le 05/12/2018 à 04:09, Aneesh Kumar K.V a écrit :

Quoted 59 lines

Architectures like ppc64 requires to do a conditional tlb flush based on the old and new value of pte. Enable that by passing old pte value as the arg.

Signed-off-by Aneesh Kumar K.V <[email protected]>
---
  arch/s390/include/asm/pgtable.h | 3 ++-
  arch/s390/mm/pgtable.c          | 2 +-
  arch/x86/include/asm/paravirt.h | 2 +-
  fs/proc/task_mmu.c              | 8 +++++---
  include/asm-generic/pgtable.h   | 2 +-
  mm/memory.c                     | 8 ++++----
  mm/mprotect.c                   | 6 +++---
  7 files changed, 17 insertions(+), 14 deletions(-)
arch/s390/include/asm/pgtable.h +2 -1
index 5d730199e37b..76dc344edb8c 100644
@@ -1070,7 +1070,8 @@ 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 vm_area_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+			     pte_t *, 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 +1 -1
index 29c0a21cd34a..b283b92722cc 100644
@@ -322,7 +322,7 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
  EXPORT_SYMBOL(ptep_modify_prot_start);
 
  void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-			     pte_t *ptep, pte_t pte)
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
  {
  	pgste_t pgste;
  	struct mm_struct *mm = vma->vm_mm;
arch/x86/include/asm/paravirt.h +1 -1
index 1154f154025d..0d75a4f60500 100644
@@ -429,7 +429,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned
  }
 
  static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-					   pte_t *ptep, pte_t pte)
+					   pte_t *ptep, pte_t old_pte, pte_t pte)
  {
  	struct mm_struct *mm = vma->vm_mm;
fs/proc/task_mmu.c +0 -0
index 9952d7185170..8d62891d38a8 100644

fs/proc/task_mmu.c static inline void clear_soft_dirty(struct vm_area_struct *vma, · line 946

Quoted 9 lines
fs/proc/task_mmu.c +4 -2
@@ -940,10 +940,12 @@ 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, addr, pte);
-		ptent = pte_wrprotect(ptent);
+		pte_t old_pte;
+
+		old_pte = ptep_modify_prot_start(vma, addr, pte);
+		ptent = pte_wrprotect(old_pte);

This change doesn't seem to fit with the commit description. Why write protecting in addition to clearing dirty ?

Christophe

Quoted 73 lines
fs/proc/task_mmu.c +1 -1
  		ptent = pte_clear_soft_dirty(ptent);
-		ptep_modify_prot_commit(vma, addr, pte, ptent);
+		ptep_modify_prot_commit(vma, addr, pte, old_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 +1 -1
index c9897dcc46c4..37039e918f17 100644
@@ -619,7 +619,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
   */
  static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
  					   unsigned long addr,
-					   pte_t *ptep, pte_t pte)
+					   pte_t *ptep, pte_t old_pte, pte_t pte)
  {
  	__ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
  }
mm/memory.c +4 -4
index d36b0eaa7862..4f3ddaedc764 100644
@@ -3568,7 +3568,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
  	int last_cpupid;
  	int target_nid;
  	bool migrated = false;
-	pte_t pte;
+	pte_t pte, old_pte;
  	bool was_writable = pte_savedwrite(vmf->orig_pte);
  	int flags = 0;
 

@@ -3588,12 +3588,12 @@ 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, vmf->address, vmf->pte);
-	pte = pte_modify(pte, vma->vm_page_prot);
+	old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+	pte = pte_modify(old_pte, vma->vm_page_prot);
  	pte = pte_mkyoung(pte);
  	if (was_writable)
  		pte = pte_mkwrite(pte);
-	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, pte);
+	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
  	update_mmu_cache(vma, vmf->address, vmf->pte);
 
  	page = vm_normal_page(vma, vmf->address, pte);
mm/mprotect.c +3 -3
index a301d4c83d3c..1b46b1b1248d 100644
@@ -110,8 +110,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
  					continue;
  			}
 
-			ptent = ptep_modify_prot_start(vma, addr, pte);
-			ptent = pte_modify(ptent, newprot);
+			oldpte = ptep_modify_prot_start(vma, addr, pte);
+			ptent = pte_modify(oldpte, 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(vma, addr, pte, ptent);
+			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
  			pages++;
  		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
  			swp_entry_t entry = pte_to_swp_entry(oldpte);
author
#6 lore raw

Re: [PATCH V3 2/5] mm: update ptep_modify_prot_commit to take old pte value as arg

Quoted 64 lines · Christophe LEROY

Le 05/12/2018 à 04:09, Aneesh Kumar K.V a écrit :

Quoted 61 lines

Architectures like ppc64 requires to do a conditional tlb flush based on the old and new value of pte. Enable that by passing old pte value as the arg.

Signed-off-by Aneesh Kumar K.V <[email protected]>

---
  arch/s390/include/asm/pgtable.h | 3 ++-
  arch/s390/mm/pgtable.c          | 2 +-
  arch/x86/include/asm/paravirt.h | 2 +-
  fs/proc/task_mmu.c              | 8 +++++---
  include/asm-generic/pgtable.h   | 2 +-
  mm/memory.c                     | 8 ++++----
  mm/mprotect.c                   | 6 +++---

  7 files changed, 17 insertions(+), 14 deletions(-)
arch/s390/include/asm/pgtable.h +2 -1
index 5d730199e37b..76dc344edb8c 100644
@@ -1070,7 +1070,8 @@ 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 vm_area_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, 
 pte_t *, pte_t);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+                 pte_t *, 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 +1 -1
index 29c0a21cd34a..b283b92722cc 100644
@@ -322,7 +322,7 @@ pte_t ptep_modify_prot_start(struct vm_area_struct 
 *vma, unsigned long addr,
   EXPORT_SYMBOL(ptep_modify_prot_start);
   void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-                 pte_t *ptep, pte_t pte)
+                 pte_t *ptep, pte_t old_pte, pte_t pte)
   {
       pgste_t pgste;
       struct mm_struct *mm = vma->vm_mm;
arch/x86/include/asm/paravirt.h +0 -0
index 1154f154025d..0d75a4f60500 100644
@@ -429,7 +429,7 @@ static inline pte_t ptep_modify_prot_start(struct

vm_area_struct *vma, unsigned
  }
  static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, -                       pte_t *ptep, pte_t pte)
+                       pte_t *ptep, pte_t old_pte, pte_t pte)
  {
      struct mm_struct *mm = vma->vm_mm;

fs/proc/task_mmu.c +0 -0
index 9952d7185170..8d62891d38a8 100644
@@ -940,10 +940,12 @@ static inline void clear_soft_dirty(struct 
 vm_area_struct *vma,
       pte_t ptent = *pte;
       if (pte_present(ptent)) {
Quoted 10 lines

fs/proc/task_mmu.c static inline void clear_soft_dirty(struct vm_area_struct *vma, · line 946

Quoted 6 lines
fs/proc/task_mmu.c +4 -2
-        ptent = ptep_modify_prot_start(vma, addr, pte);
-        ptent = pte_wrprotect(ptent);
+        pte_t old_pte;
+
+        old_pte = ptep_modify_prot_start(vma, addr, pte);
+        ptent = pte_wrprotect(old_pte);

This change doesn't seem to fit with the commit description. Why write protecting in addition to clearing dirty ?

The hunk above use a new variable old_pte. There is no functional change in that hunk.

-aneesh

#7 lore raw

Re: [PATCH V3 2/5] mm: update ptep_modify_prot_commit to take old pte value as arg

Le 05/12/2018 à 05:06, Aneesh Kumar K.V a écrit :

Quoted 76 lines · Christophe LEROY
Quoted 64 lines

Le 05/12/2018 à 04:09, Aneesh Kumar K.V a écrit :

Quoted 61 lines

Architectures like ppc64 requires to do a conditional tlb flush based on the old and new value of pte. Enable that by passing old pte value as the arg.

Signed-off-by Aneesh Kumar K.V <[email protected]>

---
  arch/s390/include/asm/pgtable.h | 3 ++-
  arch/s390/mm/pgtable.c          | 2 +-
  arch/x86/include/asm/paravirt.h | 2 +-
  fs/proc/task_mmu.c              | 8 +++++---
  include/asm-generic/pgtable.h   | 2 +-
  mm/memory.c                     | 8 ++++----
  mm/mprotect.c                   | 6 +++---

  7 files changed, 17 insertions(+), 14 deletions(-)
arch/s390/include/asm/pgtable.h +2 -1
index 5d730199e37b..76dc344edb8c 100644
@@ -1070,7 +1070,8 @@ 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 vm_area_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, 
 pte_t *, pte_t);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+                 pte_t *, 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 +1 -1
index 29c0a21cd34a..b283b92722cc 100644
@@ -322,7 +322,7 @@ pte_t ptep_modify_prot_start(struct 
 vm_area_struct *vma, unsigned long addr,
   EXPORT_SYMBOL(ptep_modify_prot_start);
   void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
-                 pte_t *ptep, pte_t pte)
+                 pte_t *ptep, pte_t old_pte, pte_t pte)
   {
       pgste_t pgste;
       struct mm_struct *mm = vma->vm_mm;
arch/x86/include/asm/paravirt.h +0 -0
index 1154f154025d..0d75a4f60500 100644
@@ -429,7 +429,7 @@ static inline pte_t ptep_modify_prot_start(struct

vm_area_struct *vma, unsigned
  }
  static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, -                       pte_t *ptep, pte_t pte)
+                       pte_t *ptep, pte_t old_pte, pte_t pte)
  {
      struct mm_struct *mm = vma->vm_mm;

fs/proc/task_mmu.c +0 -0
index 9952d7185170..8d62891d38a8 100644
@@ -940,10 +940,12 @@ static inline void clear_soft_dirty(struct 
 vm_area_struct *vma,
       pte_t ptent = *pte;
       if (pte_present(ptent)) {
Quoted 10 lines

fs/proc/task_mmu.c static inline void clear_soft_dirty(struct vm_area_struct *vma, · line 946

Quoted 6 lines
fs/proc/task_mmu.c +4 -2
-        ptent = ptep_modify_prot_start(vma, addr, pte);
-        ptent = pte_wrprotect(ptent);
+        pte_t old_pte;
+
+        old_pte = ptep_modify_prot_start(vma, addr, pte);
+        ptent = pte_wrprotect(old_pte);

This change doesn't seem to fit with the commit description. Why write protecting in addition to clearing dirty ?

Quoted 2 lines

The hunk above use a new variable old_pte. There is no functional change in that hunk.

Oops, sorry, I misread the patch, don't know why.

Christophe

author
#8 lore raw

PATCH v3 3/5 arch/powerpc/mm: Nest MMU workaround for mprotect RW upgrade.

In reply to Aneesh Kumar K.V

NestMMU requires us to mark the pte invalid and flush the tlb when we do a RW upgrade of pte. We fixed a variant of this in the fault path in commit

Fixes bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang")

Do the same for mprotect upgrades.

Hugetlb is handled in the next patch.

Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 18 +++++++++++++
 arch/powerpc/include/asm/book3s/64/radix.h   |  4 +++
 arch/powerpc/mm/pgtable-book3s64.c           | 27 ++++++++++++++++++++
 arch/powerpc/mm/pgtable-radix.c              | 18 +++++++++++++
 4 files changed, 67 insertions(+)
arch/powerpc/include/asm/book3s/64/pgtable.h +18 -0
index 2e6ada28da64..92eaea164700 100644
@@ -1314,6 +1314,24 @@ static inline int pud_pfn(pud_t pud)
 	BUILD_BUG();
 	return 0;
 }
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+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, pte_t);
+
+/*
+ * Returns true for a R -> RW upgrade of pte
+ */
+static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val)
+{
+	if (!(old_val & _PAGE_READ))
+		return false;
+
+	if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
+		return true;
+
+	return false;
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
arch/powerpc/include/asm/book3s/64/radix.h +4 -0
index 7d1a3d1543fc..5ab134eeed20 100644
@@ -127,6 +127,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep
 					 pte_t entry, unsigned long address,
 					 int psize);
 
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t old_pte, pte_t pte);
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
arch/powerpc/mm/pgtable-book3s64.c +27 -0
index 9f93c9f985c5..3d126353b11e 100644
@@ -482,3 +482,30 @@ void arch_report_meminfo(struct seq_file *m)
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
 }
 #endif /* CONFIG_PROC_FS */
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep)
+{
+	unsigned long pte_val;
+
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
+
+	return __pte(pte_val);
+
+}
+EXPORT_SYMBOL(ptep_modify_prot_start);
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+	if (radix_enabled())
+		return radix__ptep_modify_prot_commit(vma, addr,
+						      ptep, old_pte, pte);
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(ptep_modify_prot_commit);
arch/powerpc/mm/pgtable-radix.c +18 -0
index 931156069a81..dced3cd241c2 100644
@@ -1063,3 +1063,21 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 	}
 	/* See ptesync comment in radix__set_pte_at */
 }
+
+void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value. We need to do this only for radix, because hash
+	 * translation does flush when updating the linux pte.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_tlb_page(vma, addr);
+
+	set_pte_at(mm, addr, ptep, pte);
+}
Signature · 1 line
2.19.2
#9 lore raw

Re: [PATCH V3 3/5] arch/powerpc/mm: Nest MMU workaround for mprotect RW upgrade.

Quoted 6 lines · Aneesh Kumar K.V
arch/powerpc/mm/pgtable-book3s64.c +6 -0
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep)
+{
+	unsigned long pte_val;
+
+	/*

arch/powerpc/mm/pgtable-book3s64.c void arch_report_meminfo(struct seq_file *m) · line 501

Quoted 10 lines
arch/powerpc/mm/pgtable-book3s64.c +10 -0
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
+
+	return __pte(pte_val);
+
+}
+EXPORT_SYMBOL(ptep_modify_prot_start);

As far as I can tell this is only called from mm/memory.c, mm/mprotect.c and fs/proc/task_mmu.c, so there should be no need to export the function.

author
#10 lore raw

PATCH v3 4/5 mm/hugetlb: Add prot_modify_start/commit sequence for hugetlb update

In reply to Aneesh Kumar K.V

Architectures like ppc64 requires to do a conditional tlb flush based on the old and new value of pte. Follow the regular pte change protection sequence for hugetlb too. This allow the architectures to override the update sequence.

Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 include/linux/hugetlb.h | 20 ++++++++++++++++++++
 mm/hugetlb.c            |  8 +++++---
 2 files changed, 25 insertions(+), 3 deletions(-)
include/linux/hugetlb.h +20 -0
index 087fd5f48c91..39e78b80375c 100644
@@ -543,6 +543,26 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 	set_huge_pte_at(mm, addr, ptep, pte);
 }
 #endif
+
+#ifndef huge_ptep_modify_prot_start
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+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);
+}
+#endif
+
+#ifndef huge_ptep_modify_prot_commit
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte)
+{
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+#endif
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
mm/hugetlb.c +5 -3
index 705a3e9cc910..353bff385595 100644
@@ -4388,10 +4388,12 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			continue;
 		}
 		if (!huge_pte_none(pte)) {
-			pte = huge_ptep_get_and_clear(mm, address, ptep);
-			pte = pte_mkhuge(huge_pte_modify(pte, newprot));
+			pte_t old_pte;
+
+			old_pte = huge_ptep_modify_prot_start(vma, address, ptep);
+			pte = pte_mkhuge(huge_pte_modify(old_pte, newprot));
 			pte = arch_make_huge_pte(pte, vma, NULL, 0);
-			set_huge_pte_at(mm, address, ptep, pte);
+			huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte);
 			pages++;
 		}
 		spin_unlock(ptl);
Signature · 1 line
2.19.2
author
#11 lore raw

PATCH v3 5/5 arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW upgrade

In reply to Aneesh Kumar K.V

NestMMU requires us to mark the pte invalid and flush the tlb when we do a RW upgrade of pte. We fixed a variant of this in the fault path in commit

Fixes bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang")
Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 arch/powerpc/include/asm/book3s/64/hugetlb.h | 12 ++++++++
 arch/powerpc/mm/hugetlbpage-radix.c          | 17 ++++++++++++
 arch/powerpc/mm/hugetlbpage.c                | 29 ++++++++++++++++++++
 3 files changed, 58 insertions(+)
arch/powerpc/include/asm/book3s/64/hugetlb.h +12 -0
index 5b0177733994..66c1e4f88d65 100644
@@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
 static inline int hstate_get_psize(struct hstate *hstate)
 {
 	unsigned long shift;

@@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
 #endif
arch/powerpc/mm/hugetlbpage-radix.c +17 -0
index 2486bee0f93e..11d9ea28a816 100644
@@ -90,3 +90,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	return vm_unmapped_area(&info);
 }
+
+void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
arch/powerpc/mm/hugetlbpage.c +29 -0
index 8cf035e68378..39d33a3d0dc6 100644
@@ -912,3 +912,32 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 
 	return 1;
 }
+
+#ifdef CONFIG_PPC_BOOK3S_64
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_val;
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep,
+			     _PAGE_PRESENT, _PAGE_INVALID, 1);
+
+	return __pte(pte_val);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_start);
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+				  pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+
+	if (radix_enabled())
+		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
+							   old_pte, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_commit);
+#endif
Signature · 1 line
2.19.2
#12 lore raw

Re: [PATCH V3 5/5] arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW upgrade

Le 05/12/2018 à 04:09, Aneesh Kumar K.V a écrit :

Quoted 69 lines

NestMMU requires us to mark the pte invalid and flush the tlb when we do a RW upgrade of pte. We fixed a variant of this in the fault path in commit

Fixes bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang")
Signed-off-by Aneesh Kumar K.V <[email protected]>
---
  arch/powerpc/include/asm/book3s/64/hugetlb.h | 12 ++++++++
  arch/powerpc/mm/hugetlbpage-radix.c          | 17 ++++++++++++
  arch/powerpc/mm/hugetlbpage.c                | 29 ++++++++++++++++++++
  3 files changed, 58 insertions(+)
arch/powerpc/include/asm/book3s/64/hugetlb.h +12 -0
index 5b0177733994..66c1e4f88d65 100644
@@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
  				unsigned long len, unsigned long pgoff,
  				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
  static inline int hstate_get_psize(struct hstate *hstate)
  {
  	unsigned long shift;

@@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
  /* hugepd entry valid bit */
  #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
  #endif
arch/powerpc/mm/hugetlbpage-radix.c +17 -0
index 2486bee0f93e..11d9ea28a816 100644
@@ -90,3 +90,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
  	return vm_unmapped_area(&info);
  }
+
+void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
arch/powerpc/mm/hugetlbpage.c +0 -0
index 8cf035e68378..39d33a3d0dc6 100644

arch/powerpc/mm/hugetlbpage.c int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, · line 916

Quoted 5 lines
arch/powerpc/mm/hugetlbpage.c +2 -0
@@ -912,3 +912,32 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 
  	return 1;
  }
+
+#ifdef CONFIG_PPC_BOOK3S_64

Could this go in hugetlbpage-hash64.c instead to avoid the #ifdef sequence ?

Christophe

Quoted 28 lines
arch/powerpc/mm/hugetlbpage.c +27 -0
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_val;
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep,
+			     _PAGE_PRESENT, _PAGE_INVALID, 1);
+
+	return __pte(pte_val);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_start);
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+				  pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+
+	if (radix_enabled())
+		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
+							   old_pte, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_commit);
+#endif
author
#13 lore raw

Re: [PATCH V3 5/5] arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW upgrade

Quoted 6 lines · Christophe LEROY
arch/powerpc/mm/hugetlbpage.c +0 -0
Quoted 5 lines

index 8cf035e68378..39d33a3d0dc6 100644

arch/powerpc/mm/hugetlbpage.c +0 -0
@@ -912,3 +912,32 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
Quoted 7 lines

arch/powerpc/mm/hugetlbpage.c int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, · line 916

Quoted 4 lines
arch/powerpc/mm/hugetlbpage.c +2 -0
  	return 1;
  }
+
+#ifdef CONFIG_PPC_BOOK3S_64

Could this go in hugetlbpage-hash64.c instead to avoid the #ifdef sequence ?

yes. I will send updated patch as reply

-aneesh

author
#14 lore raw

PATCH v3 1/1 arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW upgrade

In reply to Aneesh Kumar K.V

NestMMU requires us to mark the pte invalid and flush the tlb when we do a RW upgrade of pte. We fixed a variant of this in the fault path in commit

Fixes bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang")
Signed-off-by Aneesh Kumar K.V <[email protected]>
---
 arch/powerpc/include/asm/book3s/64/hugetlb.h | 12 +++++++++
 arch/powerpc/mm/hugetlbpage-hash64.c         | 27 ++++++++++++++++++++
 arch/powerpc/mm/hugetlbpage-radix.c          | 17 ++++++++++++
 3 files changed, 56 insertions(+)
arch/powerpc/include/asm/book3s/64/hugetlb.h +12 -0
index 5b0177733994..66c1e4f88d65 100644
@@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
 static inline int hstate_get_psize(struct hstate *hstate)
 {
 	unsigned long shift;

@@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
 #endif
arch/powerpc/mm/hugetlbpage-hash64.c +27 -0
index 2e6a8f9345d3..48fe74bfeab1 100644
@@ -121,3 +121,30 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
 }
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_val;
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep,
+			     _PAGE_PRESENT, _PAGE_INVALID, 1);
+
+	return __pte(pte_val);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_start);
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+				  pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+
+	if (radix_enabled())
+		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
+							   old_pte, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_commit);
arch/powerpc/mm/hugetlbpage-radix.c +17 -0
index 2486bee0f93e..11d9ea28a816 100644
@@ -90,3 +90,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	return vm_unmapped_area(&info);
 }
+
+void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
Signature · 1 line
2.19.2
build bot
#15 lore raw

Re: [PATCH V3 updated] arch/powerpc/mm/hugetlb: NestMMU workaround for hugetlb mprotect RW upgrade

I love your patch! Yet something to improve:

Hi Aneesh,

I love your patch! Yet something to improve:

[auto build test ERROR on powerpc/next]
[also build test ERROR on v4.20-rc5 next-20181207]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Aneesh-Kumar-K-V/arch-powerpc-mm-hugetlb-NestMMU-workaround-for-hugetlb-mprotect-RW-upgrade/20181207-025514
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-allmodconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0

reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=powerpc

All errors (new ones prefixed by >>):

arch/powerpc/mm/hugetlbpage-radix.c: In function 'radix__huge_ptep_modify_prot_commit':

>> arch/powerpc/mm/hugetlbpage-radix.c:104:6: error: implicit declaration of function 'is_pte_rw_upgrade' [-Werror=implicit-function-declaration]
     if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
         ^~~~~~~~~~~~~~~~~

cc1: some warnings being treated as errors

vim +/is_pte_rw_upgrade +104 arch/powerpc/mm/hugetlbpage-radix.c

    93	
    94	void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
    95						 unsigned long addr, pte_t *ptep,
    96						 pte_t old_pte, pte_t pte)
    97	{
    98		struct mm_struct *mm = vma->vm_mm;
    99	
   100		/*
   101		 * To avoid NMMU hang while relaxing access we need to flush the tlb before
   102		 * we set the new value.
   103		 */
 > 104		if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&

---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation