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

Pull x86 protection key support from Ingo Molnar:
 "This tree adds support for a new memory protection hardware feature
  that is available in upcoming Intel CPUs: 'protection keys' (pkeys).

  There's a background article at LWN.net:

      https://lwn.net/Articles/643797/

  The gist is that protection keys allow the encoding of
  user-controllable permission masks in the pte.  So instead of having a
  fixed protection mask in the pte (which needs a system call to change
  and works on a per page basis), the user can map a (handful of)
  protection mask variants and can change the masks runtime relatively
  cheaply, without having to change every single page in the affected
  virtual memory range.

  This allows the dynamic switching of the protection bits of large
  amounts of virtual memory, via user-space instructions.  It also
  allows more precise control of MMU permission bits: for example the
  executable bit is separate from the read bit (see more about that
  below).

  This tree adds the MM infrastructure and low level x86 glue needed for
  that, plus it adds a high level API to make use of protection keys -
  if a user-space application calls:

        mmap(..., PROT_EXEC);

  or

        mprotect(ptr, sz, PROT_EXEC);

  (note PROT_EXEC-only, without PROT_READ/WRITE), the kernel will notice
  this special case, and will set a special protection key on this
  memory range.  It also sets the appropriate bits in the Protection
  Keys User Rights (PKRU) register so that the memory becomes unreadable
  and unwritable.

  So using protection keys the kernel is able to implement 'true'
  PROT_EXEC on x86 CPUs: without protection keys PROT_EXEC implies
  PROT_READ as well.  Unreadable executable mappings have security
  advantages: they cannot be read via information leaks to figure out
  ASLR details, nor can they be scanned for ROP gadgets - and they
  cannot be used by exploits for data purposes either.

  We know about no user-space code that relies on pure PROT_EXEC
  mappings today, but binary loaders could start making use of this new
  feature to map binaries and libraries in a more secure fashion.

  There is other pending pkeys work that offers more high level system
  call APIs to manage protection keys - but those are not part of this
  pull request.

  Right now there's a Kconfig that controls this feature
  (CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) that is default enabled
  (like most x86 CPU feature enablement code that has no runtime
  overhead), but it's not user-configurable at the moment.  If there's
  any serious problem with this then we can make it configurable and/or
  flip the default"

* 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  x86/mm/pkeys: Fix mismerge of protection keys CPUID bits
  mm/pkeys: Fix siginfo ABI breakage caused by new u64 field
  x86/mm/pkeys: Fix access_error() denial of writes to write-only VMA
  mm/core, x86/mm/pkeys: Add execute-only protection keys support
  x86/mm/pkeys: Create an x86 arch_calc_vm_prot_bits() for VMA flags
  x86/mm/pkeys: Allow kernel to modify user pkey rights register
  x86/fpu: Allow setting of XSAVE state
  x86/mm: Factor out LDT init from context init
  mm/core, x86/mm/pkeys: Add arch_validate_pkey()
  mm/core, arch, powerpc: Pass a protection key in to calc_vm_flag_bits()
  x86/mm/pkeys: Actually enable Memory Protection Keys in the CPU
  x86/mm/pkeys: Add Kconfig prompt to existing config option
  x86/mm/pkeys: Dump pkey from VMA in /proc/pid/smaps
  x86/mm/pkeys: Dump PKRU with other kernel registers
  mm/core, x86/mm/pkeys: Differentiate instruction fetches
  x86/mm/pkeys: Optimize fault handling in access_error()
  mm/core: Do not enforce PKEY permissions on remote mm access
  um, pkeys: Add UML arch_*_access_permitted() methods
  mm/gup, x86/mm/pkeys: Check VMAs and PTEs for protection keys
  x86/mm/gup: Simplify get_user_pages() PTE bit handling
  ...

14 files changed, 310 insertions, 32 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 68e4e8258b84..3636ec06c887 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -26,6 +26,7 @@ enum cpuid_leafs
 	CPUID_8000_0008_EBX,
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
+	CPUID_7_ECX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -48,28 +49,42 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
 #define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
-	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
-	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
-	   (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||	\
-	   (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||	\
-	   (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||	\
-	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
-	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
+	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
+	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
+	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
+	   (((bit)>>5)==4  && (1UL<<((bit)&31) & REQUIRED_MASK4 )) ||	\
+	   (((bit)>>5)==5  && (1UL<<((bit)&31) & REQUIRED_MASK5 )) ||	\
+	   (((bit)>>5)==6  && (1UL<<((bit)&31) & REQUIRED_MASK6 )) ||	\
+	   (((bit)>>5)==7  && (1UL<<((bit)&31) & REQUIRED_MASK7 )) ||	\
+	   (((bit)>>5)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
+	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
+	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
+	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
+	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
 
 #define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) ||	\
-	   (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) ||	\
-	   (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) ||	\
-	   (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) ||	\
-	   (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) ||	\
-	   (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) ||	\
-	   (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) ||	\
-	   (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) )
+	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
+	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
+	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
+	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
+	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
+	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
+	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
+	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
+	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
+	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
+	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
+	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
+	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
+	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 074b7604bd51..3d1a84383162 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	16	/* N 32-bit words worth of info */
+#define NCAPINTS	17	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -274,6 +274,10 @@
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index f226df064660..39343be7d4f4 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -28,6 +28,14 @@
 # define DISABLE_CENTAUR_MCR	0
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE))
+#else
+# define DISABLE_PKU		0
+# define DISABLE_OSPKE		0
+#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -41,5 +49,12 @@
 #define DISABLED_MASK7	0
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK10	0
+#define DISABLED_MASK11	0
+#define DISABLED_MASK12	0
+#define DISABLED_MASK13	0
+#define DISABLED_MASK14	0
+#define DISABLED_MASK15	0
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a2124343edf5..31ac8e6d9f36 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -25,6 +25,8 @@
 extern void fpu__activate_curr(struct fpu *fpu);
 extern void fpu__activate_fpstate_read(struct fpu *fpu);
 extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__current_fpstate_write_begin(void);
+extern void fpu__current_fpstate_write_end(void);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 1c6f6ac52ad0..36b90bbfc69f 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -108,6 +108,8 @@ enum xfeature {
 	XFEATURE_OPMASK,
 	XFEATURE_ZMM_Hi256,
 	XFEATURE_Hi16_ZMM,
+	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
+	XFEATURE_PKRU,
 
 	XFEATURE_MAX,
 };
@@ -120,6 +122,7 @@ enum xfeature {
 #define XFEATURE_MASK_OPMASK		(1 << XFEATURE_OPMASK)
 #define XFEATURE_MASK_ZMM_Hi256		(1 << XFEATURE_ZMM_Hi256)
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -212,6 +215,15 @@ struct avx_512_hi16_state {
 	struct reg_512_bit		hi16_zmm[16];
 } __packed;
 
+/*
+ * State component 9: 32-bit PKRU register.  The state is
+ * 8 bytes long but only 4 bytes is used currently.
+ */
+struct pkru_state {
+	u32				pkru;
+	u32				pad;
+} __packed;
+
 struct xstate_header {
 	u64				xfeatures;
 	u64				xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index f23cd8c80b1c..38951b0fcc5a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -24,7 +24,8 @@
 				 XFEATURE_MASK_YMM | \
 				 XFEATURE_MASK_OPMASK | \
 				 XFEATURE_MASK_ZMM_Hi256 | \
-				 XFEATURE_MASK_Hi16_ZMM)
+				 XFEATURE_MASK_Hi16_ZMM	 | \
+				 XFEATURE_MASK_PKRU)
 
 /* Supported features which require eager state saving */
 #define XFEATURE_MASK_EAGER	(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bfd9b2a35a0b..84280029cafd 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -52,15 +52,15 @@ struct ldt_struct {
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
+int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context_ldt(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context(struct task_struct *tsk,
-				   struct mm_struct *mm)
+static inline int init_new_context_ldt(struct task_struct *tsk,
+				       struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) {}
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -104,6 +104,17 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 #endif
 }
 
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	init_new_context_ldt(tsk, mm);
+	return 0;
+}
+static inline void destroy_context(struct mm_struct *mm)
+{
+	destroy_context_ldt(mm);
+}
+
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
@@ -275,4 +286,68 @@ 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;
+}
+
+static inline bool __pkru_allows_pkey(u16 pkey, bool write)
+{
+	u32 pkru = read_pkru();
+
+	if (!__pkru_allows_read(pkru, pkey))
+		return false;
+	if (write && !__pkru_allows_write(pkru, pkey))
+		return false;
+
+	return true;
+}
+
+/*
+ * We only want to enforce protection keys on the current process
+ * because we effectively have no access to PKRU for other
+ * processes or any way to tell *which * PKRU in a threaded
+ * process we could use.
+ *
+ * So do not enforce things if the VMA is not from the current
+ * mm, or if we are in a kernel thread.
+ */
+static inline bool vma_is_foreign(struct vm_area_struct *vma)
+{
+	if (!current->mm)
+		return true;
+	/*
+	 * Should PKRU be enforced on the access to this VMA?  If
+	 * the VMA is from another process, then PKRU has no
+	 * relevance and should not be enforced.
+	 */
+	if (current->mm != vma->vm_mm)
+		return true;
+
+	return false;
+}
+
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool execute, bool foreign)
+{
+	/* pkeys never affect instruction fetches */
+	if (execute)
+		return true;
+	/* allow access if the VMA is not one from this process */
+	if (foreign || vma_is_foreign(vma))
+		return true;
+	return __pkru_allows_pkey(vma_pkey(vma), write);
+}
+
+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/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0687c4748b8f..1ff49ec29ece 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -99,6 +99,14 @@ static inline int pte_dirty(pte_t pte)
 	return pte_flags(pte) & _PAGE_DIRTY;
 }
 
+
+static inline u32 read_pkru(void)
+{
+	if (boot_cpu_has(X86_FEATURE_OSPKE))
+		return __read_pkru();
+	return 0;
+}
+
 static inline int pte_young(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_ACCESSED;
@@ -911,6 +919,36 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 }
 #endif
 
+#define PKRU_AD_BIT 0x1
+#define PKRU_WD_BIT 0x2
+#define PKRU_BITS_PER_PKEY 2
+
+static inline bool __pkru_allows_read(u32 pkru, u16 pkey)
+{
+	int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
+	return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits));
+}
+
+static inline bool __pkru_allows_write(u32 pkru, u16 pkey)
+{
+	int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
+	/*
+	 * Access-disable disables writes too so we need to check
+	 * both bits here.
+	 */
+	return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits));
+}
+
+static inline u16 pte_flags_pkey(unsigned long pte_flags)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	/* ifdef to avoid doing 59-bit shift on 32-bit values */
+	return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0;
+#else
+	return 0;
+#endif
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4432ab7f407c..7b5efe264eff 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -20,13 +20,18 @@
 #define _PAGE_BIT_SOFTW2	10	/* " */
 #define _PAGE_BIT_SOFTW3	11	/* " */
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
+#define _PAGE_BIT_SOFTW4	58	/* available for programmer */
+#define _PAGE_BIT_PKEY_BIT0	59	/* Protection Keys, bit 1/4 */
+#define _PAGE_BIT_PKEY_BIT1	60	/* Protection Keys, bit 2/4 */
+#define _PAGE_BIT_PKEY_BIT2	61	/* Protection Keys, bit 3/4 */
+#define _PAGE_BIT_PKEY_BIT3	62	/* Protection Keys, bit 4/4 */
+#define _PAGE_BIT_NX		63	/* No execute: only valid after cpuid check */
+
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_HIDDEN	_PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
-#define _PAGE_BIT_SOFTW4	58	/* available for programmer */
-#define _PAGE_BIT_DEVMAP		_PAGE_BIT_SOFTW4
-#define _PAGE_BIT_NX		63	/* No execute: only valid after cpuid check */
+#define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
 /* - if the user mapped it with PROT_NONE; pte_present gives true */
@@ -47,8 +52,24 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#define _PAGE_PKEY_BIT0	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
+#define _PAGE_PKEY_BIT1	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
+#define _PAGE_PKEY_BIT2	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT2)
+#define _PAGE_PKEY_BIT3	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT3)
+#else
+#define _PAGE_PKEY_BIT0	(_AT(pteval_t, 0))
+#define _PAGE_PKEY_BIT1	(_AT(pteval_t, 0))
+#define _PAGE_PKEY_BIT2	(_AT(pteval_t, 0))
+#define _PAGE_PKEY_BIT3	(_AT(pteval_t, 0))
+#endif
 #define __HAVE_ARCH_PTE_SPECIAL
 
+#define _PAGE_PKEY_MASK (_PAGE_PKEY_BIT0 | \
+			 _PAGE_PKEY_BIT1 | \
+			 _PAGE_PKEY_BIT2 | \
+			 _PAGE_PKEY_BIT3)
+
 #ifdef CONFIG_KMEMCHECK
 #define _PAGE_HIDDEN	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
 #else
@@ -99,7 +120,12 @@
 #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)
@@ -215,7 +241,10 @@ 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/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
new file mode 100644
index 000000000000..7b84565c916c
--- /dev/null
+++ b/arch/x86/include/asm/pkeys.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_X86_PKEYS_H
+#define _ASM_X86_PKEYS_H
+
+#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
+
+extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+
+/*
+ * 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)
+{
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return 0;
+
+	return __execute_only_pkey(mm);
+}
+
+extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma,
+		int prot, int pkey);
+static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
+		int prot, int pkey)
+{
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return 0;
+
+	return __arch_override_mprotect_pkey(vma, prot, pkey);
+}
+
+#endif /*_ASM_X86_PKEYS_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 5c6e4fb370f5..4916144e3c42 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -92,5 +92,12 @@
 #define REQUIRED_MASK7	0
 #define REQUIRED_MASK8	0
 #define REQUIRED_MASK9	0
+#define REQUIRED_MASK10	0
+#define REQUIRED_MASK11	0
+#define REQUIRED_MASK12	0
+#define REQUIRED_MASK13	0
+#define REQUIRED_MASK14	0
+#define REQUIRED_MASK15	0
+#define REQUIRED_MASK16	0
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2270e41b32fd..aee6e76e561e 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -98,6 +98,28 @@ static inline void native_write_cr8(unsigned long val)
 }
 #endif
 
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+static inline u32 __read_pkru(void)
+{
+	u32 ecx = 0;
+	u32 edx, pkru;
+
+	/*
+	 * "rdpkru" instruction.  Places PKRU contents in to EAX,
+	 * clears EDX and requires that ecx=0.
+	 */
+	asm volatile(".byte 0x0f,0x01,0xee\n\t"
+		     : "=a" (pkru), "=d" (edx)
+		     : "c" (ecx));
+	return pkru;
+}
+#else
+static inline u32 __read_pkru(void)
+{
+	return 0;
+}
+#endif
+
 static inline void native_wbinvd(void)
 {
 	asm volatile("wbinvd": : :"memory");
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index 513b05f15bb4..39bca7fac087 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -6,6 +6,28 @@
 #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))
+
+#define arch_calc_vm_prot_bits(prot, key) (		\
+		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
+		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
+		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
+		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#endif
+
 #include <asm-generic/mman.h>
 
 #endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 79887abcb5e1..567de50a4c2a 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -118,6 +118,8 @@
 #define X86_CR4_SMEP		_BITUL(X86_CR4_SMEP_BIT)
 #define X86_CR4_SMAP_BIT	21 /* enable SMAP support */
 #define X86_CR4_SMAP		_BITUL(X86_CR4_SMAP_BIT)
+#define X86_CR4_PKE_BIT		22 /* enable Protection Keys support */
+#define X86_CR4_PKE		_BITUL(X86_CR4_PKE_BIT)
 
 /*
  * x86-64 Task Priority Register, CR8