4 files changed, 45 insertions, 23 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d8abfcf524d1..af0251fc85ed 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 7b84565c916c..33777c291a85 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 */
diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h
index 1d405a2b7272..0030b4024559 100644
--- a/include/linux/pkeys.h
+++ b/include/linux/pkeys.h
@@ -18,16 +18,4 @@
 #define PKEY_DEDICATED_EXECUTE_ONLY 0
 #endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
-/*
- * This is called from mprotect_pkey().
- *
- * Returns true if the protection keys is valid.
- */
-static inline bool validate_pkey(int pkey)
-{
-        if (pkey < 0)
-                return false;
-        return (pkey < arch_max_pkey());
-}
-
 #endif /* _LINUX_PKEYS_H */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a4830f0325fe..dd3f40a2935f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -352,8 +352,11 @@ fail:
         return error;
 }
 
-SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
-                unsigned long, prot)
+/*
+ * pkey==-1 when doing a legacy mprotect()
+ */
+static int do_mprotect_pkey(unsigned long start, size_t len,
+                unsigned long prot, int pkey)
 {
         unsigned long nstart, end, tmp, reqprot;
         struct vm_area_struct *vma, *prev;
@@ -361,6 +364,12 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
         const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
         const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
                                 (prot & PROT_READ);
+        /*
+         * A temporary safety check since we are not validating
+         * the pkey before we introduce the allocation code.
+         */
+        if (pkey != -1)
+                return -EINVAL;
 
         prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
         if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
@@ -409,7 +418,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 
         for (nstart = start ; ; ) {
                 unsigned long newflags;
-                int pkey = arch_override_mprotect_pkey(vma, prot, -1);
+                int new_vma_pkey;
 
                 /* Here we know that vma->vm_start <= nstart < vma->vm_end. */
 
@@ -417,7 +426,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
                 if (rier && (vma->vm_flags & VM_MAYEXEC))
                         prot |= PROT_EXEC;
 
-                newflags = calc_vm_prot_bits(prot, pkey);
+                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 >> 4 shift VM_MAY% in place of VM_% */
@@ -454,3 +464,15 @@ out:
         up_write(&current->mm->mmap_sem);
         return error;
 }
+
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+                unsigned long, prot)
+{
+        return do_mprotect_pkey(start, len, prot, -1);
+}
+
+SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
+                unsigned long, prot, int, pkey)
+{
+        return do_mprotect_pkey(start, len, prot, pkey);
+}