arch/powerpc/mm: Nest MMU workaround for mprotect RW upgrade

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
bd5050e38a ("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.

Link: http://lkml.kernel.org/r/20190116085035.29729-4-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1306,6 +1306,24 @@ 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

@@ -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

@@ -401,6 +401,31 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #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);
+
+}
+
+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);
+}
+
 /*
  * For hash translation mode, we use the deposited table to store hash slot
  * information and they are stored at PTRS_PER_PMD offset from related pmd

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);
+}