Merge branch 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull protection keys syscall interface from Thomas Gleixner:
 "This is the final step of Protection Keys support which adds the
  syscalls so user space can actually allocate keys and protect memory
  areas with them. Details and usage examples can be found in the
  documentation.

  The mm side of this has been acked by Mel"

* 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/pkeys: Update documentation
  x86/mm/pkeys: Do not skip PKRU register if debug registers are not used
  x86/pkeys: Fix pkeys build breakage for some non-x86 arches
  x86/pkeys: Add self-tests
  x86/pkeys: Allow configuration of init_pkru
  x86/pkeys: Default to a restrictive init PKRU
  pkeys: Add details of system call use to Documentation/
  generic syscalls: Wire up memory protection keys syscalls
  x86: Wire up protection keys system calls
  x86/pkeys: Allocation/free syscalls
  x86/pkeys: Make mprotect_key() mask off additional vm_flags
  mm: Implement new pkey_mprotect() system call
  x86/pkeys: Add fault handling for PF_PK page fault bit

3 files changed, 99 insertions, 7 deletions

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 1ea0bae..72198c6 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -23,6 +23,14 @@ typedef struct {
 	const struct vdso_image *vdso_image;	/* vdso image in use */
 
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	/*
+	 * One bit per protection key says whether userspace can
+	 * use it or not.  protected by mmap_sem.
+	 */
+	u16 pkey_allocation_map;
+	s16 execute_only_pkey;
+#endif
 } mm_context_t;
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d8abfcf..8e0a9fe 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>
 
@@ -107,7 +108,16 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
+		/* pkey 0 is the default and always allocated */
+		mm->context.pkey_allocation_map = 0x1;
+		/* -1 means unallocated or invalid */
+		mm->context.execute_only_pkey = -1;
+	}
+	#endif
 	init_new_context_ldt(tsk, mm);
+
 	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
@@ -195,16 +205,20 @@ 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)
 {
@@ -258,5 +272,4 @@ static inline bool arch_pte_access_permitted(pte_t pte, bool write)
 {
 	return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write);
 }
-
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 7b84565..34684ad 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -10,7 +10,6 @@ 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 +30,76 @@ 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);
+
+#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3)
+
+#define mm_pkey_allocation_map(mm)	(mm->context.pkey_allocation_map)
+#define mm_set_pkey_allocated(mm, pkey) do {		\
+	mm_pkey_allocation_map(mm) |= (1U << pkey);	\
+} while (0)
+#define mm_set_pkey_free(mm, pkey) do {			\
+	mm_pkey_allocation_map(mm) &= ~(1U << pkey);	\
+} while (0)
+
+static inline
+bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
+{
+	return mm_pkey_allocation_map(mm) & (1U << pkey);
+}
+
+/*
+ * Returns a positive, 4-bit key on success, or -1 on failure.
+ */
+static inline
+int mm_pkey_alloc(struct mm_struct *mm)
+{
+	/*
+	 * Note: this is the one and only place we make sure
+	 * that the pkey is valid as far as the hardware is
+	 * concerned.  The rest of the kernel trusts that
+	 * only good, valid pkeys come out of here.
+	 */
+	u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1);
+	int ret;
+
+	/*
+	 * Are we out of pkeys?  We must handle this specially
+	 * because ffz() behavior is undefined if there are no
+	 * zeros.
+	 */
+	if (mm_pkey_allocation_map(mm) == all_pkeys_mask)
+		return -1;
+
+	ret = ffz(mm_pkey_allocation_map(mm));
+
+	mm_set_pkey_allocated(mm, ret);
+
+	return ret;
+}
+
+static inline
+int mm_pkey_free(struct mm_struct *mm, int pkey)
+{
+	/*
+	 * pkey 0 is special, always allocated and can never
+	 * be freed.
+	 */
+	if (!pkey)
+		return -EINVAL;
+	if (!mm_pkey_is_allocated(mm, pkey))
+		return -EINVAL;
+
+	mm_set_pkey_free(mm, pkey);
+
+	return 0;
+}
+
+extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+extern void copy_init_pkru_to_fpregs(void);
+
 #endif /*_ASM_X86_PKEYS_H */