x86/mm/pkeys: Add arch-specific VMA protection bits

Lots of things seem to do:

        vma->vm_page_prot = vm_get_page_prot(flags);

and the ptes get created right from things we pull out
of ->vm_page_prot.  So it is very convenient if we can
store the protection key in flags and vm_page_prot, just
like the existing permission bits (_PAGE_RW/PRESENT).  It
greatly reduces the amount of plumbing and arch-specific
hacking we have to do in generic code.

This also takes the new PROT_PKEY{0,1,2,3} flags and
turns *those* in to VM_ flags for vma->vm_flags.

The protection key values are stored in 4 places:
	1. "prot" argument to system calls
	2. vma->vm_flags, filled from the mmap "prot"
	3. vma->vm_page prot, filled from vma->vm_flags
	4. the PTE itself.

The pseudocode for these for steps are as follows:

	mmap(PROT_PKEY*)
	vma->vm_flags 	  = ... | arch_calc_vm_prot_bits(mmap_prot);
	vma->vm_page_prot = ... | arch_vm_get_page_prot(vma->vm_flags);
	pte = pfn | vma->vm_page_prot

Note that this provides a new definitions for x86:

	arch_vm_get_page_prot()

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20160212210210.FE483A42@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bfd9b2a..94c4c8b 100644 (file)
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -275,4 +275,15 @@ static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
                mpx_notify_unmap(mm, vma, start, end);
 }
 
+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;
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index cae10ba..8c35cf0 100644 (file)
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -115,7 +115,12 @@
 #define _KERNPG_TABLE  (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |    \
                         _PAGE_DIRTY)
 
-/* Set of bits not changed in pte_modify */
+/*
+ * Set of bits not changed in pte_modify.  The pte's
+ * protection key is treated like _PAGE_RW, for
+ * instance, and is *not* included in this mask since
+ * pte_modify() does modify it.
+ */
 #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |         \
                         _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
                         _PAGE_SOFT_DIRTY)
@@ -231,7 +236,10 @@ enum page_cache_mode {
 /* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */
 #define PTE_PFN_MASK           ((pteval_t)PHYSICAL_PAGE_MASK)
 
-/* Extracts the flags from a (pte|pmd|pud|pgd)val_t of a 4KB page */
+/*
+ *  Extracts the flags from a (pte|pmd|pud|pgd)val_t
+ *  This includes the protection key value.
+ */
 #define PTE_FLAGS_MASK         (~PTE_PFN_MASK)
 
 typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;

diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index 513b05f..e8562e0 100644 (file)
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -6,6 +6,22 @@
 #define MAP_HUGE_2MB    (21 << MAP_HUGE_SHIFT)
 #define MAP_HUGE_1GB    (30 << MAP_HUGE_SHIFT)
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+/*
+ * Take the 4 protection key bits out of the vma->vm_flags
+ * value and turn them in to the bits that we can put in
+ * to a pte.
+ *
+ * Only override these if Protection Keys are available
+ * (which is only on 64-bit).
+ */
+#define arch_vm_get_page_prot(vm_flags)        __pgprot(       \
+               ((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |     \
+               ((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |     \
+               ((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |     \
+               ((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
+#endif
+
 #include <asm-generic/mman.h>
 
 #endif /* _ASM_X86_MMAN_H */

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 54d173b..3056369 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -183,6 +183,13 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT                VM_ARCH_1       /* PAT reserves whole VMA at once (x86) */
+#if defined (CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)
+# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0
+# define VM_PKEY_BIT0  VM_HIGH_ARCH_0  /* A protection key is a 4-bit value */
+# define VM_PKEY_BIT1  VM_HIGH_ARCH_1
+# define VM_PKEY_BIT2  VM_HIGH_ARCH_2
+# define VM_PKEY_BIT3  VM_HIGH_ARCH_3
+#endif
 #elif defined(CONFIG_PPC)
 # define VM_SAO                VM_ARCH_1       /* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)