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
  ...

1 files changed, 89 insertions, 10 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7d42501c8bb4..450fc977ed02 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -193,8 +193,26 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
 #define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
 
+#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
+#define VM_HIGH_ARCH_BIT_0	32	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_1	33	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_2	34	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
+#define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
+#define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
+#define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
+#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
+
 #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)
@@ -256,6 +274,8 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_KILLABLE	0x10	/* The fault task is in SIGKILL killable region */
 #define FAULT_FLAG_TRIED	0x20	/* Second try */
 #define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
+#define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
+#define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -1224,24 +1244,82 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		      unsigned long start, unsigned long nr_pages,
 		      unsigned int foll_flags, struct page **pages,
 		      struct vm_area_struct **vmas, int *nonblocking);
-long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages,
-		    struct vm_area_struct **vmas);
-long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
-		    unsigned long start, unsigned long nr_pages,
-		    int write, int force, struct page **pages,
-		    int *locked);
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+			    unsigned long start, unsigned long nr_pages,
+			    int write, int force, struct page **pages,
+			    struct vm_area_struct **vmas);
+long get_user_pages6(unsigned long start, unsigned long nr_pages,
+			    int write, int force, struct page **pages,
+			    struct vm_area_struct **vmas);
+long get_user_pages_locked6(unsigned long start, unsigned long nr_pages,
+		    int write, int force, struct page **pages, int *locked);
 long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			       unsigned long start, unsigned long nr_pages,
 			       int write, int force, struct page **pages,
 			       unsigned int gup_flags);
-long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-		    unsigned long start, unsigned long nr_pages,
+long get_user_pages_unlocked5(unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 
+/* suppress warnings from use in EXPORT_SYMBOL() */
+#ifndef __DISABLE_GUP_DEPRECATED
+#define __gup_deprecated __deprecated
+#else
+#define __gup_deprecated
+#endif
+/*
+ * These macros provide backward-compatibility with the old
+ * get_user_pages() variants which took tsk/mm.  These
+ * functions/macros provide both compile-time __deprecated so we
+ * can catch old-style use and not break the build.  The actual
+ * functions also have WARN_ON()s to let us know at runtime if
+ * the get_user_pages() should have been the "remote" variant.
+ *
+ * These are hideous, but temporary.
+ *
+ * If you run into one of these __deprecated warnings, look
+ * at how you are calling get_user_pages().  If you are calling
+ * it with current/current->mm as the first two arguments,
+ * simply remove those arguments.  The behavior will be the same
+ * as it is now.  If you are calling it on another task, use
+ * get_user_pages_remote() instead.
+ *
+ * Any questions?  Ask Dave Hansen <dave@sr71.net>
+ */
+long
+__gup_deprecated
+get_user_pages8(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		int write, int force, struct page **pages,
+		struct vm_area_struct **vmas);
+#define GUP_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages, ...)	\
+	get_user_pages
+#define get_user_pages(...) GUP_MACRO(__VA_ARGS__,	\
+		get_user_pages8, x,			\
+		get_user_pages6, x, x, x, x, x)(__VA_ARGS__)
+
+__gup_deprecated
+long get_user_pages_locked8(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		int write, int force, struct page **pages,
+		int *locked);
+#define GUPL_MACRO(_1, _2, _3, _4, _5, _6, _7, _8, get_user_pages_locked, ...)	\
+	get_user_pages_locked
+#define get_user_pages_locked(...) GUPL_MACRO(__VA_ARGS__,	\
+		get_user_pages_locked8,	x,			\
+		get_user_pages_locked6, x, x, x, x)(__VA_ARGS__)
+
+__gup_deprecated
+long get_user_pages_unlocked7(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		int write, int force, struct page **pages);
+#define GUPU_MACRO(_1, _2, _3, _4, _5, _6, _7, get_user_pages_unlocked, ...)	\
+	get_user_pages_unlocked
+#define get_user_pages_unlocked(...) GUPU_MACRO(__VA_ARGS__,	\
+		get_user_pages_unlocked7, x,			\
+		get_user_pages_unlocked5, x, x, x, x)(__VA_ARGS__)
+
 /* Container for pinned pfns / pages */
 struct frame_vector {
 	unsigned int nr_allocated;	/* Number of frames we have space for */
@@ -2169,6 +2247,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_MLOCK	0x1000	/* lock present pages */
+#define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);