[RFC PATCH 0/5] NestMMU pte upgrade workaround for mprotect and autonuma

[RFC PATCH 0/5] NestMMU pte upgrade workaround for mprotect and autonuma

[Aneesh Kumar K.V]

We can upgrade pte access (R -> RW transition) via mprotect or autonuma. 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.

-aneesh


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/autonuma 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 |  8 +++++
 arch/powerpc/include/asm/book3s/64/pgtable.h | 18 ++++++++++
 arch/powerpc/include/asm/hugetlb.h           |  2 +-
 arch/powerpc/mm/hugetlbpage.c                | 35 ++++++++++++++++++++
 arch/powerpc/mm/pgtable-book3s64.c           | 34 +++++++++++++++++++
 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                      | 18 ++++++++++
 mm/hugetlb.c                                 |  8 +++--
 mm/memory.c                                  |  8 ++---
 mm/mprotect.c                                |  6 ++--
 14 files changed, 150 insertions(+), 27 deletions(-)

-- 
2.17.1

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

[Aneesh Kumar K.V]

Some architecture may want to call flush_tlb_range from these helpers.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 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(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 0e7cb0dc9c33..8e7f26dfedc6 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1035,8 +1035,8 @@ 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,
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index f2cc7da473e4..29c0a21cd34a 100644
--- a/arch/s390/mm/pgtable.c
+++ b/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);
@@ -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;
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e375d4266b53..c5d203a51e50 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -421,10 +421,11 @@ 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, pv_mmu_ops.ptep_modify_prot_start,
 			 mm, addr, ptep);
@@ -432,9 +433,11 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long a
 	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_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5ea1d64cb0b4..229df16e7ad0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -938,10 +938,10 @@ 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);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 88ebc6102c7c..021b94cd3260 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -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 */
diff --git a/mm/memory.c b/mm/memory.c
index c467102a5cbc..261d30f51499 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3806,12 +3806,12 @@ 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);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6d331620b9e5..a301d4c83d3c 100644
--- a/mm/mprotect.c
+++ b/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);
-- 
2.17.1

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

[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 <aneesh.kumar@linux.ibm.com>
---
 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(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 8e7f26dfedc6..626250436897 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1036,7 +1036,8 @@ 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,
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 29c0a21cd34a..b283b92722cc 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -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;
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c5d203a51e50..17214e074286 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -434,7 +434,7 @@ 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;
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 229df16e7ad0..505aa21d04df 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -938,10 +938,12 @@ 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);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 021b94cd3260..4e4723f6be5e 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -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);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 261d30f51499..211df764f232 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3786,7 +3786,7 @@ 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;
 
@@ -3806,12 +3806,12 @@ 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);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a301d4c83d3c..1b46b1b1248d 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -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);
-- 
2.17.1

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

[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 and autonuma upgrades.

Hugetlb is handled in the next patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 18 +++++++++++
 arch/powerpc/mm/pgtable-book3s64.c           | 34 ++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 13a688fc8cd0..5b4ac83a5649 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1291,6 +1291,24 @@ static inline const 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 Read or Write upgrade of pte.
+ */
+static inline bool is_pte_upgrade(unsigned long old_val, unsigned long new_val)
+{
+	if ((!(old_val & _PAGE_READ)) && (new_val & _PAGE_READ))
+		return true;
+
+	if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
+		return true;
+
+	return false;
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 01d7c0f7c4f0..243a7cb1bdba 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -477,3 +477,37 @@ 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)
+{
+	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_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		flush_tlb_page(vma, addr);
+
+	set_pte_at(mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(ptep_modify_prot_commit);
-- 
2.17.1

[RFC PATCH 4/5] mm/hugetlb: Add prot_modify_start/commit sequence for hugetlb update

[Aneesh Kumar K.V]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 include/linux/hugetlb.h | 18 ++++++++++++++++++
 mm/hugetlb.c            |  8 +++++---
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6b68e345f0ca..d39ba48f43b0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -529,6 +529,24 @@ 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
+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(mm, address, ptep);
+}
+#endif
+
+#ifndef 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
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3c21775f196b..d147662442ca 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4336,10 +4336,12 @@ 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);
-- 
2.17.1

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

[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 <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/hugetlb.h |  8 +++++
 arch/powerpc/include/asm/hugetlb.h           |  2 +-
 arch/powerpc/mm/hugetlbpage.c                | 35 ++++++++++++++++++++
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 50888388a359..45a94885c1fa 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -39,4 +39,12 @@ static inline bool gigantic_page_supported(void)
 }
 #endif
 
+#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
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 2d00cc530083..60c1d37e446a 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -4,7 +4,6 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 extern struct kmem_cache *hugepte_cache;
 
@@ -176,6 +175,7 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
 #else /* ! CONFIG_HUGETLB_PAGE */
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index e87f9ef9115b..8c7ee22c2ac7 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -906,3 +906,38 @@ 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)
+{
+	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_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+EXPORT_SYMBOL(huge_ptep_modify_prot_commit);
+#endif
-- 
2.17.1