x86/pkeys: Make mprotect_key() mask off additional vm_flags

Today, mprotect() takes 4 bits of data: PROT_READ/WRITE/EXEC/NONE.
Three of those bits: READ/WRITE/EXEC get translated directly in to
vma->vm_flags by calc_vm_prot_bits().  If a bit is unset in
mprotect()'s 'prot' argument then it must be cleared in vma->vm_flags
during the mprotect() call.

We do this clearing today by first calculating the VMA flags we
want set, then clearing the ones we do not want to inherit from
the original VMA:

	vm_flags = calc_vm_prot_bits(prot, key);
	...
	newflags = vm_flags;
	newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));

However, we *also* want to mask off the original VMA's vm_flags in
which we store the protection key.

To do that, this patch adds a new macro:

	ARCH_VM_PKEY_FLAGS

which allows the architecture to specify additional bits that it would
like cleared.  We use that to ensure that the VM_PKEY_BIT* bits get
cleared.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Dave Hansen <dave@sr71.net>
Cc: arnd@arndb.de
Cc: linux-api@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: luto@kernel.org
Cc: akpm@linux-foundation.org
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/20160729163013.E48D6981@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/pkeys.h

@@ -38,4 +38,6 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
 extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 		unsigned long init_val);
 
+#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3)
+
 #endif /*_ASM_X86_PKEYS_H */

include/linux/pkeys.h

@@ -16,6 +16,7 @@
 #define execute_only_pkey(mm) (0)
 #define arch_override_mprotect_pkey(vma, prot, pkey) (0)
 #define PKEY_DEDICATED_EXECUTE_ONLY 0
+#define ARCH_VM_PKEY_FLAGS 0
 #endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
 #endif /* _LINUX_PKEYS_H */

mm/mprotect.c

@@ -417,6 +417,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		prev = vma;
 
 	for (nstart = start ; ; ) {
+		unsigned long mask_off_old_flags;
 		unsigned long newflags;
 		int new_vma_pkey;
 
@@ -426,9 +427,17 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		if (rier && (vma->vm_flags & VM_MAYEXEC))
 			prot |= PROT_EXEC;
 
+		/*
+		 * Each mprotect() call explicitly passes r/w/x permissions.
+		 * If a permission is not passed to mprotect(), it must be
+		 * cleared from the VMA.
+		 */
+		mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC |
+					ARCH_VM_PKEY_FLAGS;
+
 		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
 		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
-		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+		newflags |= (vma->vm_flags & ~mask_off_old_flags);
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {