mm: Implement new pkey_mprotect() system call

pkey_mprotect() is just like mprotect, except it also takes a
protection key as an argument.  On systems that do not support
protection keys, it still works, but requires that key=0.
Otherwise it does exactly what mprotect does.

I expect it to get used like this, if you want to guarantee that
any mapping you create can *never* be accessed without the right
protection keys set up.

	int real_prot = PROT_READ|PROT_WRITE;
	pkey = pkey_alloc(0, PKEY_DENY_ACCESS);
	ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
	ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey);

This way, there is *no* window where the mapping is accessible
since it was always either PROT_NONE or had a protection key set
that denied all access.

We settled on 'unsigned long' for the type of the key here.  We
only need 4 bits on x86 today, but I figured that other
architectures might need some more space.

Semantically, we have a bit of a problem if we combine this
syscall with our previously-introduced execute-only support:
What do we do when we mix execute-only pkey use with
pkey_mprotect() use?  For instance:

	pkey_mprotect(ptr, PAGE_SIZE, PROT_WRITE, 6); // set pkey=6
	mprotect(ptr, PAGE_SIZE, PROT_EXEC);  // set pkey=X_ONLY_PKEY?
	mprotect(ptr, PAGE_SIZE, PROT_WRITE); // is pkey=6 again?

To solve that, we make the plain-mprotect()-initiated execute-only
support only apply to VMAs that have the default protection key (0)
set on them.

Proposed semantics:
1. protection key 0 is special and represents the default,
   "unassigned" protection key.  It is always allocated.
2. mprotect() never affects a mapping's pkey_mprotect()-assigned
   protection key. A protection key of 0 (even if set explicitly)
   represents an unassigned protection key.
   2a. mprotect(PROT_EXEC) on a mapping with an assigned protection
       key may or may not result in a mapping with execute-only
       properties.  pkey_mprotect() plus pkey_set() on all threads
       should be used to _guarantee_ execute-only semantics if this
       is not a strong enough semantic.
3. mprotect(PROT_EXEC) may result in an "execute-only" mapping. The
   kernel will internally attempt to allocate and dedicate a
   protection key for the purpose of execute-only mappings.  This
   may not be possible in cases where there are no free protection
   keys available.  It can also happen, of course, in situations
   where there is no hardware support for protection keys.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
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/20160729163012.3DDD36C4@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

2 files changed, 19 insertions, 7 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d8abfcf..af0251f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -4,6 +4,7 @@
 #include <asm/desc.h>
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
+#include <linux/pkeys.h>
 
 #include <trace/events/tlb.h>
 
@@ -195,16 +196,20 @@ static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		mpx_notify_unmap(mm, vma, start, end);
 }
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 static inline int vma_pkey(struct vm_area_struct *vma)
 {
-	u16 pkey = 0;
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 |
 				      VM_PKEY_BIT2 | VM_PKEY_BIT3;
-	pkey = (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT;
-#endif
-	return pkey;
+
+	return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT;
+}
+#else
+static inline int vma_pkey(struct vm_area_struct *vma)
+{
+	return 0;
 }
+#endif
 
 static inline bool __pkru_allows_pkey(u16 pkey, bool write)
 {
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 7b84565..33777c2 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -1,7 +1,12 @@
 #ifndef _ASM_X86_PKEYS_H
 #define _ASM_X86_PKEYS_H
 
-#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
+#define PKEY_DEDICATED_EXECUTE_ONLY 15
+/*
+ * Consider the PKEY_DEDICATED_EXECUTE_ONLY key unavailable.
+ */
+#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? \
+		PKEY_DEDICATED_EXECUTE_ONLY : 1)
 
 extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 		unsigned long init_val);
@@ -10,7 +15,6 @@ extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
  * Try to dedicate one of the protection keys to be used as an
  * execute-only protection key.
  */
-#define PKEY_DEDICATED_EXECUTE_ONLY 15
 extern int __execute_only_pkey(struct mm_struct *mm);
 static inline int execute_only_pkey(struct mm_struct *mm)
 {
@@ -31,4 +35,7 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
 	return __arch_override_mprotect_pkey(vma, prot, pkey);
 }
 
+extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+
 #endif /*_ASM_X86_PKEYS_H */