diff mbox series

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

Message ID 20181205030931.12037-4-aneesh.kumar@linux.ibm.com (mailing list archive)
State New, archived
Headers show
Series NestMMU pte upgrade workaround for mprotect | expand

Commit Message

Aneesh Kumar K.V Dec. 5, 2018, 3:09 a.m. UTC
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 <aneesh.kumar@linux.ibm.com>
---
 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(+)

Comments

Christoph Hellwig Dec. 18, 2018, 5:21 p.m. UTC | #1
On Wed, Dec 05, 2018 at 08:39:29AM +0530, Aneesh Kumar K.V wrote:
> +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);

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.
diff mbox series

Patch

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 2e6ada28da64..92eaea164700 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -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_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 7d1a3d1543fc..5ab134eeed20 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -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)
 {
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 9f93c9f985c5..3d126353b11e 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -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);
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 931156069a81..dced3cd241c2 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -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);
+}