Add L_PTE_DIRTY to PTEs for memory range with (VM_PFNMAP|VM_PFNWRITE),
then we could avoid unneeded page protection fault in write access
first time due to L_PTE_RDONLY.
There are no valid struct pages behind VM_PFNMAP range, so it make no
sense to set L_PTE_DIRTY in page fault handler.
Signed-off-by: Wang YanQing <udknight@xxxxxxxxx>
---
arch/arm/include/asm/mman.h | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
create mode 100644 arch/arm/include/asm/mman.h
diff --git a/arch/arm/include/asm/mman.h b/arch/arm/include/asm/mman.h
new file mode 100644
index 0000000..f59bbf3
--- /dev/null
+++ b/arch/arm/include/asm/mman.h
@@ -0,0 +1,21 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef __ASM_ARM_MMAN_H
+#define __ASM_ARM_MMAN_H
+
+#include <uapi/asm/mman.h>
+
+static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
+{
+ if ((vm_flags & (VM_PFNMAP|VM_WRITE)) == (VM_PFNMAP|VM_WRITE))
+ return __pgprot(L_PTE_DIRTY);
+ else
+ return __pgprot(0);
+}
+#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
+
+#endif /* __ASM_ARM_MMAN_H */
--
1.8.5.6.2.g3d8a54e.dirty
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>