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

Documentation/kernel-parameters.txt

@@ -1666,6 +1666,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	initrd=		[BOOT] Specify the location of the initial ramdisk
 
+	init_pkru=	[x86] Specify the default memory protection keys rights
+			register contents for all processes.  0x55555554 by
+			default (disallow access to all but pkey 0).  Can
+			override in debugfs after boot.
+
 	inport.irq=	[HW] Inport (ATI XL and Microsoft) busmouse driver
 			Format: <irq>
 

Documentation/x86/protection-keys.txt

@@ -18,10 +18,68 @@ even though there is theoretically space in the PAE PTEs.  These
 permissions are enforced on data access only and have no effect on
 instruction fetches.
 
-=========================== Config Option ===========================
+=========================== Syscalls ===========================
 
-This config option adds approximately 1.5kb of text. and 50 bytes of
-data to the executable.  A workload which does large O_DIRECT reads
-of holes in XFS files was run to exercise get_user_pages_fast().  No
-performance delta was observed with the config option
-enabled or disabled.
+There are 3 system calls which directly interact with pkeys:
+
+	int pkey_alloc(unsigned long flags, unsigned long init_access_rights)
+	int pkey_free(int pkey);
+	int pkey_mprotect(unsigned long start, size_t len,
+			  unsigned long prot, int pkey);
+
+Before a pkey can be used, it must first be allocated with
+pkey_alloc().  An application calls the WRPKRU instruction
+directly in order to change access permissions to memory covered
+with a key.  In this example WRPKRU is wrapped by a C function
+called pkey_set().
+
+	int real_prot = PROT_READ|PROT_WRITE;
+	pkey = pkey_alloc(0, PKEY_DENY_WRITE);
+	ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey);
+	... application runs here
+
+Now, if the application needs to update the data at 'ptr', it can
+gain access, do the update, then remove its write access:
+
+	pkey_set(pkey, 0); // clear PKEY_DENY_WRITE
+	*ptr = foo; // assign something
+	pkey_set(pkey, PKEY_DENY_WRITE); // set PKEY_DENY_WRITE again
+
+Now when it frees the memory, it will also free the pkey since it
+is no longer in use:
+
+	munmap(ptr, PAGE_SIZE);
+	pkey_free(pkey);
+
+(Note: pkey_set() is a wrapper for the RDPKRU and WRPKRU instructions.
+ An example implementation can be found in
+ tools/testing/selftests/x86/protection_keys.c)
+
+=========================== Behavior ===========================
+
+The kernel attempts to make protection keys consistent with the
+behavior of a plain mprotect().  For instance if you do this:
+
+	mprotect(ptr, size, PROT_NONE);
+	something(ptr);
+
+you can expect the same effects with protection keys when doing this:
+
+	pkey = pkey_alloc(0, PKEY_DISABLE_WRITE | PKEY_DISABLE_READ);
+	pkey_mprotect(ptr, size, PROT_READ|PROT_WRITE, pkey);
+	something(ptr);
+
+That should be true whether something() is a direct access to 'ptr'
+like:
+
+	*ptr = foo;
+
+or when the kernel does the access on the application's behalf like
+with a read():
+
+	read(fd, ptr, 1);
+
+The kernel will send a SIGSEGV in both cases, but si_code will be set
+to SEGV_PKERR when violating protection keys versus SEGV_ACCERR when
+the plain mprotect() permissions are violated.

arch/alpha/include/uapi/asm/mman.h

@@ -78,4 +78,9 @@
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
 #endif /* __ALPHA_MMAN_H__ */

arch/mips/include/uapi/asm/mman.h

@@ -105,4 +105,9 @@
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
 #endif /* _ASM_MMAN_H */

arch/parisc/include/uapi/asm/mman.h

@@ -75,4 +75,9 @@
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
 #endif /* __PARISC_MMAN_H__ */

arch/x86/entry/syscalls/syscall_32.tbl

@@ -386,3 +386,8 @@
 377	i386	copy_file_range		sys_copy_file_range
 378	i386	preadv2			sys_preadv2			compat_sys_preadv2
 379	i386	pwritev2		sys_pwritev2			compat_sys_pwritev2
+380	i386	pkey_mprotect		sys_pkey_mprotect
+381	i386	pkey_alloc		sys_pkey_alloc
+382	i386	pkey_free		sys_pkey_free
+#383	i386	pkey_get		sys_pkey_get
+#384	i386	pkey_set		sys_pkey_set

arch/x86/entry/syscalls/syscall_64.tbl

@@ -335,6 +335,11 @@
 326	common	copy_file_range		sys_copy_file_range
 327	64	preadv2			sys_preadv2
 328	64	pwritev2		sys_pwritev2
+329	common	pkey_mprotect		sys_pkey_mprotect
+330	common	pkey_alloc		sys_pkey_alloc
+331	common	pkey_free		sys_pkey_free
+#332	common	pkey_get		sys_pkey_get
+#333	common	pkey_set		sys_pkey_set
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

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

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 */

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 */

arch/x86/kernel/fpu/core.c

@@ -12,6 +12,7 @@
 #include <asm/traps.h>
 
 #include <linux/hardirq.h>
+#include <linux/pkeys.h>
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/fpu.h>
@@ -505,6 +506,9 @@ static inline void copy_init_fpstate_to_fpregs(void)
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
 	else
 		copy_kernel_to_fregs(&init_fpstate.fsave);
+
+	if (boot_cpu_has(X86_FEATURE_OSPKE))
+		copy_init_pkru_to_fpregs();
 }
 
 /*

arch/x86/kernel/fpu/xstate.c

@@ -5,6 +5,7 @@
  */
 #include <linux/compat.h>
 #include <linux/cpu.h>
+#include <linux/mman.h>
 #include <linux/pkeys.h>
 
 #include <asm/fpu/api.h>
@@ -866,9 +867,10 @@ const void *get_xsave_field_ptr(int xsave_state)
 	return get_xsave_addr(&fpu->state.xsave, xsave_state);
 }
 
+#ifdef CONFIG_ARCH_HAS_PKEYS
+
 #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
 #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
-
 /*
  * This will go out and modify PKRU register to set the access
  * rights for @pkey to @init_val.
@@ -914,6 +916,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 
 	return 0;
 }
+#endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
 /*
  * This is similar to user_regset_copyout(), but will not add offset to

arch/x86/kernel/process_64.c

@@ -109,12 +109,13 @@ void __show_regs(struct pt_regs *regs, int all)
 	get_debugreg(d7, 7);
 
 	/* Only print out debug registers if they are in their non-default state. */
-	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))
-		return;
-
-	printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
-	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
+	if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
+	    (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+		printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n",
+		       d0, d1, d2);
+		printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n",
+		       d3, d6, d7);
+	}
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru());

arch/x86/mm/fault.c

@@ -1144,6 +1144,15 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
 {
 	/* This is only called for the current mm, so: */
 	bool foreign = false;
+
+	/*
+	 * Read or write was blocked by protection keys.  This is
+	 * always an unconditional error and can never result in
+	 * a follow-up action to resolve the fault, like a COW.
+	 */
+	if (error_code & PF_PK)
+		return 1;
+
 	/*
 	 * Make sure to check the VMA so that we do not perform
 	 * faults just to hit a PF_PK as soon as we fill in a

arch/x86/mm/pkeys.c

@@ -11,6 +11,7 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  */
+#include <linux/debugfs.h>		/* debugfs_create_u32()		*/
 #include <linux/mm_types.h>             /* mm_struct, vma, etc...       */
 #include <linux/pkeys.h>                /* PKEY_*                       */
 #include <uapi/asm-generic/mman-common.h>
@@ -21,8 +22,19 @@
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
+	bool need_to_set_mm_pkey = false;
+	int execute_only_pkey = mm->context.execute_only_pkey;
 	int ret;
 
+	/* Do we need to assign a pkey for mm's execute-only maps? */
+	if (execute_only_pkey == -1) {
+		/* Go allocate one to use, which might fail */
+		execute_only_pkey = mm_pkey_alloc(mm);
+		if (execute_only_pkey < 0)
+			return -1;
+		need_to_set_mm_pkey = true;
+	}
+
 	/*
 	 * We do not want to go through the relatively costly
 	 * dance to set PKRU if we do not need to.  Check it
@@ -32,22 +44,33 @@ int __execute_only_pkey(struct mm_struct *mm)
 	 * can make fpregs inactive.
 	 */
 	preempt_disable();
-	if (fpregs_active() &&
-	    !__pkru_allows_read(read_pkru(), PKEY_DEDICATED_EXECUTE_ONLY)) {
+	if (!need_to_set_mm_pkey &&
+	    fpregs_active() &&
+	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
 		preempt_enable();
-		return PKEY_DEDICATED_EXECUTE_ONLY;
+		return execute_only_pkey;
 	}
 	preempt_enable();
-	ret = arch_set_user_pkey_access(current, PKEY_DEDICATED_EXECUTE_ONLY,
+
+	/*
+	 * Set up PKRU so that it denies access for everything
+	 * other than execution.
+	 */
+	ret = arch_set_user_pkey_access(current, execute_only_pkey,
 			PKEY_DISABLE_ACCESS);
 	/*
 	 * If the PKRU-set operation failed somehow, just return
 	 * 0 and effectively disable execute-only support.
 	 */
-	if (ret)
-		return 0;
+	if (ret) {
+		mm_set_pkey_free(mm, execute_only_pkey);
+		return -1;
+	}
 
-	return PKEY_DEDICATED_EXECUTE_ONLY;
+	/* We got one, store it and use it from here on out */
+	if (need_to_set_mm_pkey)
+		mm->context.execute_only_pkey = execute_only_pkey;
+	return execute_only_pkey;
 }
 
 static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
@@ -55,7 +78,7 @@ static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
 	/* Do this check first since the vm_flags should be hot */
 	if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC)
 		return false;
-	if (vma_pkey(vma) != PKEY_DEDICATED_EXECUTE_ONLY)
+	if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey)
 		return false;
 
 	return true;
@@ -99,3 +122,106 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
 	 */
 	return vma_pkey(vma);
 }
+
+#define PKRU_AD_KEY(pkey)	(PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY))
+
+/*
+ * Make the default PKRU value (at execve() time) as restrictive
+ * as possible.  This ensures that any threads clone()'d early
+ * in the process's lifetime will not accidentally get access
+ * to data which is pkey-protected later on.
+ */
+u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
+		      PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
+		      PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |
+		      PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) |
+		      PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15);
+
+/*
+ * Called from the FPU code when creating a fresh set of FPU
+ * registers.  This is called from a very specific context where
+ * we know the FPU regstiers are safe for use and we can use PKRU
+ * directly.  The fact that PKRU is only available when we are
+ * using eagerfpu mode makes this possible.
+ */
+void copy_init_pkru_to_fpregs(void)
+{
+	u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value);
+	/*
+	 * Any write to PKRU takes it out of the XSAVE 'init
+	 * state' which increases context switch cost.  Avoid
+	 * writing 0 when PKRU was already 0.
+	 */
+	if (!init_pkru_value_snapshot && !read_pkru())
+		return;
+	/*
+	 * Override the PKRU state that came from 'init_fpstate'
+	 * with the baseline from the process.
+	 */
+	write_pkru(init_pkru_value_snapshot);
+}
+
+static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	char buf[32];
+	unsigned int len;
+
+	len = sprintf(buf, "0x%x\n", init_pkru_value);
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t init_pkru_write_file(struct file *file,
+		 const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[32];
+	ssize_t len;
+	u32 new_init_pkru;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	/* Make the buffer a valid string that we can not overrun */
+	buf[len] = '\0';
+	if (kstrtouint(buf, 0, &new_init_pkru))
+		return -EINVAL;
+
+	/*
+	 * Don't allow insane settings that will blow the system
+	 * up immediately if someone attempts to disable access
+	 * or writes to pkey 0.
+	 */
+	if (new_init_pkru & (PKRU_AD_BIT|PKRU_WD_BIT))
+		return -EINVAL;
+
+	WRITE_ONCE(init_pkru_value, new_init_pkru);
+	return count;
+}
+
+static const struct file_operations fops_init_pkru = {
+	.read = init_pkru_read_file,
+	.write = init_pkru_write_file,
+	.llseek = default_llseek,
+};
+
+static int __init create_init_pkru_value(void)
+{
+	debugfs_create_file("init_pkru", S_IRUSR | S_IWUSR,
+			arch_debugfs_dir, NULL, &fops_init_pkru);
+	return 0;
+}
+late_initcall(create_init_pkru_value);
+
+static __init int setup_init_pkru(char *opt)
+{
+	u32 new_init_pkru;
+
+	if (kstrtouint(opt, 0, &new_init_pkru))
+		return 1;
+
+	WRITE_ONCE(init_pkru_value, new_init_pkru);
+
+	return 1;
+}
+__setup("init_pkru=", setup_init_pkru);

arch/xtensa/include/uapi/asm/mman.h

@@ -117,4 +117,9 @@
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
 #endif /* _XTENSA_MMAN_H */

include/linux/pkeys.h

@@ -4,11 +4,6 @@
 #include <linux/mm_types.h>
 #include <asm/mmu_context.h>
 
-#define PKEY_DISABLE_ACCESS	0x1
-#define PKEY_DISABLE_WRITE	0x2
-#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
-				 PKEY_DISABLE_WRITE)
-
 #ifdef CONFIG_ARCH_HAS_PKEYS
 #include <asm/pkeys.h>
 #else /* ! CONFIG_ARCH_HAS_PKEYS */
@@ -16,18 +11,34 @@
 #define execute_only_pkey(mm) (0)
 #define arch_override_mprotect_pkey(vma, prot, pkey) (0)
 #define PKEY_DEDICATED_EXECUTE_ONLY 0
-#endif /* ! CONFIG_ARCH_HAS_PKEYS */
+#define ARCH_VM_PKEY_FLAGS 0
+
+static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
+{
+	return (pkey == 0);
+}
+
+static inline int mm_pkey_alloc(struct mm_struct *mm)
+{
+	return -1;
+}
 
-/*
- * This is called from mprotect_pkey().
- *
- * Returns true if the protection keys is valid.
- */
-static inline bool validate_pkey(int pkey)
+static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	if (pkey < 0)
-		return false;
-	return (pkey < arch_max_pkey());
+	WARN_ONCE(1, "free of protection key when disabled");
+	return -EINVAL;
 }
 
+static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+			unsigned long init_val)
+{
+	return 0;
+}
+
+static inline void copy_init_pkru_to_fpregs(void)
+{
+}
+
+#endif /* ! CONFIG_ARCH_HAS_PKEYS */
+
 #endif /* _LINUX_PKEYS_H */

include/linux/syscalls.h

@@ -898,4 +898,12 @@ asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 
+asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
+				  unsigned long prot, int pkey);
+asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
+asmlinkage long sys_pkey_free(int pkey);
+//asmlinkage long sys_pkey_get(int pkey, unsigned long flags);
+//asmlinkage long sys_pkey_set(int pkey, unsigned long access_rights,
+//			     unsigned long flags);
+
 #endif

include/uapi/asm-generic/mman-common.h

@@ -72,4 +72,9 @@
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
 #endif /* __ASM_GENERIC_MMAN_COMMON_H */

include/uapi/asm-generic/unistd.h

@@ -724,9 +724,19 @@ __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
 __SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
 #define __NR_pwritev2 287
 __SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_pkey_get 291
+//__SYSCALL(__NR_pkey_get,      sys_pkey_get)
+#define __NR_pkey_set 292
+//__SYSCALL(__NR_pkey_set,      sys_pkey_set)
 
 #undef __NR_syscalls
-#define __NR_syscalls 288
+#define __NR_syscalls 291
 
 /*
  * All syscalls below here should go away really,

kernel/sys_ni.c

@@ -250,3 +250,8 @@ cond_syscall(sys_execveat);
 
 /* membarrier */
 cond_syscall(sys_membarrier);
+
+/* memory protection keys */
+cond_syscall(sys_pkey_mprotect);
+cond_syscall(sys_pkey_alloc);
+cond_syscall(sys_pkey_free);

mm/mprotect.c

@@ -23,11 +23,13 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/perf_event.h>
+#include <linux/pkeys.h>
 #include <linux/ksm.h>
 #include <linux/pkeys.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
 #include "internal.h"
@@ -353,8 +355,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	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;
@@ -383,6 +388,14 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 	if (down_write_killable(&current->mm->mmap_sem))
 		return -EINTR;
 
+	/*
+	 * If userspace did not allocate the pkey, do not let
+	 * them use it here.
+	 */
+	error = -EINVAL;
+	if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
+		goto out;
+
 	vma = find_vma(current->mm, start);
 	error = -ENOMEM;
 	if (!vma)
@@ -409,8 +422,9 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		prev = vma;
 
 	for (nstart = start ; ; ) {
+		unsigned long mask_off_old_flags;
 		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. */
 
@@ -418,8 +432,17 @@ 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);
-		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+		/*
+		 * Each mprotect() call explicitly passes r/w/x permissions.
+		 * If a permission is not passed to mprotect(), it must be
+		 * cleared from the VMA.
+		 */
+		mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC |
+					ARCH_VM_PKEY_FLAGS;
+
+		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
+		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
+		newflags |= (vma->vm_flags & ~mask_off_old_flags);
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
@@ -455,3 +478,60 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 	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);
+}
+
+SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
+{
+	int pkey;
+	int ret;
+
+	/* No flags supported yet. */
+	if (flags)
+		return -EINVAL;
+	/* check for unsupported init values */
+	if (init_val & ~PKEY_ACCESS_MASK)
+		return -EINVAL;
+
+	down_write(&current->mm->mmap_sem);
+	pkey = mm_pkey_alloc(current->mm);
+
+	ret = -ENOSPC;
+	if (pkey == -1)
+		goto out;
+
+	ret = arch_set_user_pkey_access(current, pkey, init_val);
+	if (ret) {
+		mm_pkey_free(current->mm, pkey);
+		goto out;
+	}
+	ret = pkey;
+out:
+	up_write(&current->mm->mmap_sem);
+	return ret;
+}
+
+SYSCALL_DEFINE1(pkey_free, int, pkey)
+{
+	int ret;
+
+	down_write(&current->mm->mmap_sem);
+	ret = mm_pkey_free(current->mm, pkey);
+	up_write(&current->mm->mmap_sem);
+
+	/*
+	 * We could provie warnings or errors if any VMA still
+	 * has the pkey set here.
+	 */
+	return ret;
+}

tools/testing/selftests/x86/Makefile

@@ -5,7 +5,8 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test
+			check_initial_reg_state sigreturn ldt_gdt iopl \
+			protection_keys
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer

tools/testing/selftests/x86/pkey-helpers.h

+#ifndef _PKEYS_HELPER_H
+#define _PKEYS_HELPER_H
+#define _GNU_SOURCE
+#include <string.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <ucontext.h>
+#include <sys/mman.h>
+
+#define NR_PKEYS 16
+#define PKRU_BITS_PER_PKEY 2
+
+#ifndef DEBUG_LEVEL
+#define DEBUG_LEVEL 0
+#endif
+#define DPRINT_IN_SIGNAL_BUF_SIZE 4096
+extern int dprint_in_signal;
+extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
+static inline void sigsafe_printf(const char *format, ...)
+{
+	va_list ap;
+
+	va_start(ap, format);
+	if (!dprint_in_signal) {
+		vprintf(format, ap);
+	} else {
+		int len = vsnprintf(dprint_in_signal_buffer,
+				    DPRINT_IN_SIGNAL_BUF_SIZE,
+				    format, ap);
+		/*
+		 * len is amount that would have been printed,
+		 * but actual write is truncated at BUF_SIZE.
+		 */
+		if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
+			len = DPRINT_IN_SIGNAL_BUF_SIZE;
+		write(1, dprint_in_signal_buffer, len);
+	}
+	va_end(ap);
+}
+#define dprintf_level(level, args...) do {	\
+	if (level <= DEBUG_LEVEL)		\
+		sigsafe_printf(args);		\
+	fflush(NULL);				\
+} while (0)
+#define dprintf0(args...) dprintf_level(0, args)
+#define dprintf1(args...) dprintf_level(1, args)
+#define dprintf2(args...) dprintf_level(2, args)
+#define dprintf3(args...) dprintf_level(3, args)
+#define dprintf4(args...) dprintf_level(4, args)
+
+extern unsigned int shadow_pkru;
+static inline unsigned int __rdpkru(void)
+{
+	unsigned int eax, edx;
+	unsigned int ecx = 0;
+	unsigned int pkru;
+
+	asm volatile(".byte 0x0f,0x01,0xee\n\t"
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (ecx));
+	pkru = eax;
+	return pkru;
+}
+
+static inline unsigned int _rdpkru(int line)
+{
+	unsigned int pkru = __rdpkru();
+
+	dprintf4("rdpkru(line=%d) pkru: %x shadow: %x\n",
+			line, pkru, shadow_pkru);
+	assert(pkru == shadow_pkru);
+
+	return pkru;
+}
+
+#define rdpkru() _rdpkru(__LINE__)
+
+static inline void __wrpkru(unsigned int pkru)
+{
+	unsigned int eax = pkru;
+	unsigned int ecx = 0;
+	unsigned int edx = 0;
+
+	dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
+	asm volatile(".byte 0x0f,0x01,0xef\n\t"
+		     : : "a" (eax), "c" (ecx), "d" (edx));
+	assert(pkru == __rdpkru());
+}
+
+static inline void wrpkru(unsigned int pkru)
+{
+	dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
+	/* will do the shadow check for us: */
+	rdpkru();
+	__wrpkru(pkru);
+	shadow_pkru = pkru;
+	dprintf4("%s(%08x) pkru: %08x\n", __func__, pkru, __rdpkru());
+}
+
+/*
+ * These are technically racy. since something could
+ * change PKRU between the read and the write.
+ */
+static inline void __pkey_access_allow(int pkey, int do_allow)
+{
+	unsigned int pkru = rdpkru();
+	int bit = pkey * 2;
+
+	if (do_allow)
+		pkru &= (1<<bit);
+	else
+		pkru |= (1<<bit);
+
+	dprintf4("pkru now: %08x\n", rdpkru());
+	wrpkru(pkru);
+}
+
+static inline void __pkey_write_allow(int pkey, int do_allow_write)
+{
+	long pkru = rdpkru();
+	int bit = pkey * 2 + 1;
+
+	if (do_allow_write)
+		pkru &= (1<<bit);
+	else
+		pkru |= (1<<bit);
+
+	wrpkru(pkru);
+	dprintf4("pkru now: %08x\n", rdpkru());
+}
+
+#define PROT_PKEY0     0x10            /* protection key value (bit 0) */
+#define PROT_PKEY1     0x20            /* protection key value (bit 1) */
+#define PROT_PKEY2     0x40            /* protection key value (bit 2) */
+#define PROT_PKEY3     0x80            /* protection key value (bit 3) */
+
+#define PAGE_SIZE 4096
+#define MB	(1<<20)
+
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+		unsigned int *ecx, unsigned int *edx)
+{
+	/* ecx is often an input as well as an output. */
+	asm volatile(
+		"cpuid;"
+		: "=a" (*eax),
+		  "=b" (*ebx),
+		  "=c" (*ecx),
+		  "=d" (*edx)
+		: "0" (*eax), "2" (*ecx));
+}
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */
+#define X86_FEATURE_PKU        (1<<3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE      (1<<4) /* OS Protection Keys Enable */
+
+static inline int cpu_has_pku(void)
+{
+	unsigned int eax;
+	unsigned int ebx;
+	unsigned int ecx;
+	unsigned int edx;
+
+	eax = 0x7;
+	ecx = 0x0;
+	__cpuid(&eax, &ebx, &ecx, &edx);
+
+	if (!(ecx & X86_FEATURE_PKU)) {
+		dprintf2("cpu does not have PKU\n");
+		return 0;
+	}
+	if (!(ecx & X86_FEATURE_OSPKE)) {
+		dprintf2("cpu does not have OSPKE\n");
+		return 0;
+	}
+	return 1;
+}
+
+#define XSTATE_PKRU_BIT	(9)
+#define XSTATE_PKRU	0x200
+
+int pkru_xstate_offset(void)
+{
+	unsigned int eax;
+	unsigned int ebx;
+	unsigned int ecx;
+	unsigned int edx;
+	int xstate_offset;
+	int xstate_size;
+	unsigned long XSTATE_CPUID = 0xd;
+	int leaf;
+
+	/* assume that XSTATE_PKRU is set in XCR0 */
+	leaf = XSTATE_PKRU_BIT;
+	{
+		eax = XSTATE_CPUID;
+		ecx = leaf;
+		__cpuid(&eax, &ebx, &ecx, &edx);
+
+		if (leaf == XSTATE_PKRU_BIT) {
+			xstate_offset = ebx;
+			xstate_size = eax;
+		}
+	}
+
+	if (xstate_size == 0) {
+		printf("could not find size/offset of PKRU in xsave state\n");
+		return 0;
+	}
+
+	return xstate_offset;
+}
+
+#endif /* _PKEYS_HELPER_H */

tools/testing/selftests/x86/protection_keys.c

+/*
+ * Tests x86 Memory Protection Keys (see Documentation/x86/protection-keys.txt)
+ *
+ * There are examples in here of:
+ *  * how to set protection keys on memory
+ *  * how to set/clear bits in PKRU (the rights register)
+ *  * how to handle SEGV_PKRU signals and extract pkey-relevant
+ *    information from the siginfo
+ *
+ * Things to add:
+ *	make sure KSM and KSM COW breaking works
+ *	prefault pages in at malloc, or not
+ *	protect MPX bounds tables with protection keys?
+ *	make sure VMA splitting/merging is working correctly
+ *	OOMs can destroy mm->mmap (see exit_mmap()), so make sure it is immune to pkeys
+ *	look for pkey "leaks" where it is still set on a VMA but "freed" back to the kernel
+ *	do a plain mprotect() to a mprotect_pkey() area and make sure the pkey sticks
+ *
+ * Compile like this:
+ *	gcc      -o protection_keys    -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ *	gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/futex.h>
+#include <sys/time.h>
+#include <sys/syscall.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <ucontext.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+#include <setjmp.h>
+
+#include "pkey-helpers.h"
+
+int iteration_nr = 1;
+int test_nr;
+
+unsigned int shadow_pkru;
+
+#define HPAGE_SIZE	(1UL<<21)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+#define ALIGN_UP(x, align_to)	(((x) + ((align_to)-1)) & ~((align_to)-1))
+#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
+#define ALIGN_PTR_UP(p, ptr_align_to)	((typeof(p))ALIGN_UP((unsigned long)(p),	ptr_align_to))
+#define ALIGN_PTR_DOWN(p, ptr_align_to)	((typeof(p))ALIGN_DOWN((unsigned long)(p),	ptr_align_to))
+#define __stringify_1(x...)     #x
+#define __stringify(x...)       __stringify_1(x)
+
+#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
+
+int dprint_in_signal;
+char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
+
+extern void abort_hooks(void);
+#define pkey_assert(condition) do {		\
+	if (!(condition)) {			\
+		dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \
+				__FILE__, __LINE__,	\
+				test_nr, iteration_nr);	\
+		dprintf0("errno at assert: %d", errno);	\
+		abort_hooks();			\
+		assert(condition);		\
+	}					\
+} while (0)
+#define raw_assert(cond) assert(cond)
+
+void cat_into_file(char *str, char *file)
+{
+	int fd = open(file, O_RDWR);
+	int ret;
+
+	dprintf2("%s(): writing '%s' to '%s'\n", __func__, str, file);
+	/*
+	 * these need to be raw because they are called under
+	 * pkey_assert()
+	 */
+	raw_assert(fd >= 0);
+	ret = write(fd, str, strlen(str));
+	if (ret != strlen(str)) {
+		perror("write to file failed");
+		fprintf(stderr, "filename: '%s' str: '%s'\n", file, str);
+		raw_assert(0);
+	}
+	close(fd);
+}
+
+#if CONTROL_TRACING > 0
+static int warned_tracing;
+int tracing_root_ok(void)
+{
+	if (geteuid() != 0) {
+		if (!warned_tracing)
+			fprintf(stderr, "WARNING: not run as root, "
+					"can not do tracing control\n");
+		warned_tracing = 1;
+		return 0;
+	}
+	return 1;
+}
+#endif
+
+void tracing_on(void)
+{
+#if CONTROL_TRACING > 0
+#define TRACEDIR "/sys/kernel/debug/tracing"
+	char pidstr[32];
+
+	if (!tracing_root_ok())
+		return;
+
+	sprintf(pidstr, "%d", getpid());
+	cat_into_file("0", TRACEDIR "/tracing_on");
+	cat_into_file("\n", TRACEDIR "/trace");
+	if (1) {
+		cat_into_file("function_graph", TRACEDIR "/current_tracer");
+		cat_into_file("1", TRACEDIR "/options/funcgraph-proc");
+	} else {
+		cat_into_file("nop", TRACEDIR "/current_tracer");
+	}
+	cat_into_file(pidstr, TRACEDIR "/set_ftrace_pid");
+	cat_into_file("1", TRACEDIR "/tracing_on");
+	dprintf1("enabled tracing\n");
+#endif
+}
+
+void tracing_off(void)
+{
+#if CONTROL_TRACING > 0
+	if (!tracing_root_ok())
+		return;
+	cat_into_file("0", "/sys/kernel/debug/tracing/tracing_on");
+#endif
+}
+
+void abort_hooks(void)
+{
+	fprintf(stderr, "running %s()...\n", __func__);
+	tracing_off();
+#ifdef SLEEP_ON_ABORT
+	sleep(SLEEP_ON_ABORT);
+#endif
+}
+
+static inline void __page_o_noops(void)
+{
+	/* 8-bytes of instruction * 512 bytes = 1 page */
+	asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr");
+}
+
+/*
+ * This attempts to have roughly a page of instructions followed by a few
+ * instructions that do a write, and another page of instructions.  That
+ * way, we are pretty sure that the write is in the second page of
+ * instructions and has at least a page of padding behind it.
+ *
+ * *That* lets us be sure to madvise() away the write instruction, which
+ * will then fault, which makes sure that the fault code handles
+ * execute-only memory properly.
+ */
+__attribute__((__aligned__(PAGE_SIZE)))
+void lots_o_noops_around_write(int *write_to_me)
+{
+	dprintf3("running %s()\n", __func__);
+	__page_o_noops();
+	/* Assume this happens in the second page of instructions: */
+	*write_to_me = __LINE__;
+	/* pad out by another page: */
+	__page_o_noops();
+	dprintf3("%s() done\n", __func__);
+}
+
+/* Define some kernel-like types */
+#define  u8 uint8_t
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+#ifdef __i386__
+#define SYS_mprotect_key 380
+#define SYS_pkey_alloc	 381
+#define SYS_pkey_free	 382
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x18
+#else
+#define SYS_mprotect_key 329
+#define SYS_pkey_alloc	 330
+#define SYS_pkey_free	 331
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
+#endif
+
+void dump_mem(void *dumpme, int len_bytes)
+{
+	char *c = (void *)dumpme;
+	int i;
+
+	for (i = 0; i < len_bytes; i += sizeof(u64)) {
+		u64 *ptr = (u64 *)(c + i);
+		dprintf1("dump[%03d][@%p]: %016jx\n", i, ptr, *ptr);
+	}
+}
+
+#define __SI_FAULT      (3 << 16)
+#define SEGV_BNDERR     (__SI_FAULT|3)  /* failed address bound checks */
+#define SEGV_PKUERR     (__SI_FAULT|4)
+
+static char *si_code_str(int si_code)
+{
+	if (si_code & SEGV_MAPERR)
+		return "SEGV_MAPERR";
+	if (si_code & SEGV_ACCERR)
+		return "SEGV_ACCERR";
+	if (si_code & SEGV_BNDERR)
+		return "SEGV_BNDERR";
+	if (si_code & SEGV_PKUERR)
+		return "SEGV_PKUERR";
+	return "UNKNOWN";
+}
+
+int pkru_faults;
+int last_si_pkey = -1;
+void signal_handler(int signum, siginfo_t *si, void *vucontext)
+{
+	ucontext_t *uctxt = vucontext;
+	int trapno;
+	unsigned long ip;
+	char *fpregs;
+	u32 *pkru_ptr;
+	u64 si_pkey;
+	u32 *si_pkey_ptr;
+	int pkru_offset;
+	fpregset_t fpregset;
+
+	dprint_in_signal = 1;
+	dprintf1(">>>>===============SIGSEGV============================\n");
+	dprintf1("%s()::%d, pkru: 0x%x shadow: %x\n", __func__, __LINE__,
+			__rdpkru(), shadow_pkru);
+
+	trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO];
+	ip = uctxt->uc_mcontext.gregs[REG_IP_IDX];
+	fpregset = uctxt->uc_mcontext.fpregs;
+	fpregs = (void *)fpregset;
+
+	dprintf2("%s() trapno: %d ip: 0x%lx info->si_code: %s/%d\n", __func__,
+			trapno, ip, si_code_str(si->si_code), si->si_code);
+#ifdef __i386__
+	/*
+	 * 32-bit has some extra padding so that userspace can tell whether
+	 * the XSTATE header is present in addition to the "legacy" FPU
+	 * state.  We just assume that it is here.
+	 */
+	fpregs += 0x70;
+#endif
+	pkru_offset = pkru_xstate_offset();
+	pkru_ptr = (void *)(&fpregs[pkru_offset]);
+
+	dprintf1("siginfo: %p\n", si);
+	dprintf1(" fpregs: %p\n", fpregs);
+	/*
+	 * If we got a PKRU fault, we *HAVE* to have at least one bit set in
+	 * here.
+	 */
+	dprintf1("pkru_xstate_offset: %d\n", pkru_xstate_offset());
+	if (DEBUG_LEVEL > 4)
+		dump_mem(pkru_ptr - 128, 256);
+	pkey_assert(*pkru_ptr);
+
+	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
+	dump_mem(si_pkey_ptr - 8, 24);
+	si_pkey = *si_pkey_ptr;
+	pkey_assert(si_pkey < NR_PKEYS);
+	last_si_pkey = si_pkey;
+
+	if ((si->si_code == SEGV_MAPERR) ||
+	    (si->si_code == SEGV_ACCERR) ||
+	    (si->si_code == SEGV_BNDERR)) {
+		printf("non-PK si_code, exiting...\n");
+		exit(4);
+	}
+
+	dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
+	/* need __rdpkru() version so we do not do shadow_pkru checking */
+	dprintf1("signal pkru from  pkru: %08x\n", __rdpkru());
+	dprintf1("si_pkey from siginfo: %jx\n", si_pkey);
+	*(u64 *)pkru_ptr = 0x00000000;
+	dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
+	pkru_faults++;
+	dprintf1("<<<<==================================================\n");
+	return;
+	if (trapno == 14) {
+		fprintf(stderr,
+			"ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
+			trapno, ip);
+		fprintf(stderr, "si_addr %p\n", si->si_addr);
+		fprintf(stderr, "REG_ERR: %lx\n",
+				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
+		exit(1);
+	} else {
+		fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
+		fprintf(stderr, "si_addr %p\n", si->si_addr);
+		fprintf(stderr, "REG_ERR: %lx\n",
+				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
+		exit(2);
+	}
+	dprint_in_signal = 0;
+}
+
+int wait_all_children(void)
+{
+	int status;
+	return waitpid(-1, &status, 0);
+}
+
+void sig_chld(int x)
+{
+	dprint_in_signal = 1;
+	dprintf2("[%d] SIGCHLD: %d\n", getpid(), x);
+	dprint_in_signal = 0;
+}
+
+void setup_sigsegv_handler(void)
+{
+	int r, rs;
+	struct sigaction newact;
+	struct sigaction oldact;
+
+	/* #PF is mapped to sigsegv */
+	int signum  = SIGSEGV;
+
+	newact.sa_handler = 0;
+	newact.sa_sigaction = signal_handler;
+
+	/*sigset_t - signals to block while in the handler */
+	/* get the old signal mask. */
+	rs = sigprocmask(SIG_SETMASK, 0, &newact.sa_mask);
+	pkey_assert(rs == 0);
+
+	/* call sa_sigaction, not sa_handler*/
+	newact.sa_flags = SA_SIGINFO;
+
+	newact.sa_restorer = 0;  /* void(*)(), obsolete */
+	r = sigaction(signum, &newact, &oldact);
+	r = sigaction(SIGALRM, &newact, &oldact);
+	pkey_assert(r == 0);
+}
+
+void setup_handlers(void)
+{
+	signal(SIGCHLD, &sig_chld);
+	setup_sigsegv_handler();
+}
+
+pid_t fork_lazy_child(void)
+{
+	pid_t forkret;
+
+	forkret = fork();
+	pkey_assert(forkret >= 0);
+	dprintf3("[%d] fork() ret: %d\n", getpid(), forkret);
+
+	if (!forkret) {
+		/* in the child */
+		while (1) {
+			dprintf1("child sleeping...\n");
+			sleep(30);
+		}
+	}
+	return forkret;
+}
+
+void davecmp(void *_a, void *_b, int len)
+{
+	int i;
+	unsigned long *a = _a;
+	unsigned long *b = _b;
+
+	for (i = 0; i < len / sizeof(*a); i++) {
+		if (a[i] == b[i])
+			continue;
+
+		dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]);
+	}
+}
+
+void dumpit(char *f)
+{
+	int fd = open(f, O_RDONLY);
+	char buf[100];
+	int nr_read;
+
+	dprintf2("maps fd: %d\n", fd);
+	do {
+		nr_read = read(fd, &buf[0], sizeof(buf));
+		write(1, buf, nr_read);
+	} while (nr_read > 0);
+	close(fd);
+}
+
+#define PKEY_DISABLE_ACCESS    0x1
+#define PKEY_DISABLE_WRITE     0x2
+
+u32 pkey_get(int pkey, unsigned long flags)
+{
+	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
+	u32 pkru = __rdpkru();
+	u32 shifted_pkru;
+	u32 masked_pkru;
+
+	dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n",
+			__func__, pkey, flags, 0, 0);
+	dprintf2("%s() raw pkru: %x\n", __func__, pkru);
+
+	shifted_pkru = (pkru >> (pkey * PKRU_BITS_PER_PKEY));
+	dprintf2("%s() shifted_pkru: %x\n", __func__, shifted_pkru);
+	masked_pkru = shifted_pkru & mask;
+	dprintf2("%s() masked  pkru: %x\n", __func__, masked_pkru);
+	/*
+	 * shift down the relevant bits to the lowest two, then
+	 * mask off all the other high bits.
+	 */
+	return masked_pkru;
+}
+
+int pkey_set(int pkey, unsigned long rights, unsigned long flags)
+{
+	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
+	u32 old_pkru = __rdpkru();
+	u32 new_pkru;
+
+	/* make sure that 'rights' only contains the bits we expect: */
+	assert(!(rights & ~mask));
+
+	/* copy old pkru */
+	new_pkru = old_pkru;
+	/* mask out bits from pkey in old value: */
+	new_pkru &= ~(mask << (pkey * PKRU_BITS_PER_PKEY));
+	/* OR in new bits for pkey: */
+	new_pkru |= (rights << (pkey * PKRU_BITS_PER_PKEY));
+
+	__wrpkru(new_pkru);
+
+	dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x pkru now: %x old_pkru: %x\n",
+			__func__, pkey, rights, flags, 0, __rdpkru(), old_pkru);
+	return 0;
+}
+
+void pkey_disable_set(int pkey, int flags)
+{
+	unsigned long syscall_flags = 0;
+	int ret;
+	int pkey_rights;
+	u32 orig_pkru;
+
+	dprintf1("START->%s(%d, 0x%x)\n", __func__,
+		pkey, flags);
+	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+	pkey_rights = pkey_get(pkey, syscall_flags);
+
+	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+	pkey_assert(pkey_rights >= 0);
+
+	pkey_rights |= flags;
+
+	ret = pkey_set(pkey, pkey_rights, syscall_flags);
+	assert(!ret);
+	/*pkru and flags have the same format */
+	shadow_pkru |= flags << (pkey * 2);
+	dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkru);
+
+	pkey_assert(ret >= 0);
+
+	pkey_rights = pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+
+	dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
+	if (flags)
+		pkey_assert(rdpkru() > orig_pkru);
+	dprintf1("END<---%s(%d, 0x%x)\n", __func__,
+		pkey, flags);
+}
+
+void pkey_disable_clear(int pkey, int flags)
+{
+	unsigned long syscall_flags = 0;
+	int ret;
+	int pkey_rights = pkey_get(pkey, syscall_flags);
+	u32 orig_pkru = rdpkru();
+
+	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+	pkey_assert(pkey_rights >= 0);
+
+	pkey_rights |= flags;
+
+	ret = pkey_set(pkey, pkey_rights, 0);
+	/* pkru and flags have the same format */
+	shadow_pkru &= ~(flags << (pkey * 2));
+	pkey_assert(ret >= 0);
+
+	pkey_rights = pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+
+	dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
+	if (flags)
+		assert(rdpkru() > orig_pkru);
+}
+
+void pkey_write_allow(int pkey)
+{
+	pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_write_deny(int pkey)
+{
+	pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_access_allow(int pkey)
+{
+	pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
+}
+void pkey_access_deny(int pkey)
+{
+	pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
+}
+
+int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+		unsigned long pkey)
+{
+	int sret;
+
+	dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__,
+			ptr, size, orig_prot, pkey);
+
+	errno = 0;
+	sret = syscall(SYS_mprotect_key, ptr, size, orig_prot, pkey);
+	if (errno) {
+		dprintf2("SYS_mprotect_key sret: %d\n", sret);
+		dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot);
+		dprintf2("SYS_mprotect_key failed, errno: %d\n", errno);
+		if (DEBUG_LEVEL >= 2)
+			perror("SYS_mprotect_pkey");
+	}
+	return sret;
+}
+
+int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
+{
+	int ret = syscall(SYS_pkey_alloc, flags, init_val);
+	dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n",
+			__func__, flags, init_val, ret, errno);
+	return ret;
+}
+
+int alloc_pkey(void)
+{
+	int ret;
+	unsigned long init_val = 0x0;
+
+	dprintf1("alloc_pkey()::%d, pkru: 0x%x shadow: %x\n",
+			__LINE__, __rdpkru(), shadow_pkru);
+	ret = sys_pkey_alloc(0, init_val);
+	/*
+	 * pkey_alloc() sets PKRU, so we need to reflect it in
+	 * shadow_pkru:
+	 */
+	dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	if (ret) {
+		/* clear both the bits: */
+		shadow_pkru &= ~(0x3      << (ret * 2));
+		dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
+				__LINE__, ret, __rdpkru(), shadow_pkru);
+		/*
+		 * move the new state in from init_val
+		 * (remember, we cheated and init_val == pkru format)
+		 */
+		shadow_pkru |=  (init_val << (ret * 2));
+	}
+	dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	dprintf1("alloc_pkey()::%d errno: %d\n", __LINE__, errno);
+	/* for shadow checking: */
+	rdpkru();
+	dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n",
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	return ret;
+}
+
+int sys_pkey_free(unsigned long pkey)
+{
+	int ret = syscall(SYS_pkey_free, pkey);
+	dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret);
+	return ret;
+}
+
+/*
+ * I had a bug where pkey bits could be set by mprotect() but
+ * not cleared.  This ensures we get lots of random bit sets
+ * and clears on the vma and pte pkey bits.
+ */
+int alloc_random_pkey(void)
+{
+	int max_nr_pkey_allocs;
+	int ret;
+	int i;
+	int alloced_pkeys[NR_PKEYS];
+	int nr_alloced = 0;
+	int random_index;
+	memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
+
+	/* allocate every possible key and make a note of which ones we got */
+	max_nr_pkey_allocs = NR_PKEYS;
+	max_nr_pkey_allocs = 1;
+	for (i = 0; i < max_nr_pkey_allocs; i++) {
+		int new_pkey = alloc_pkey();
+		if (new_pkey < 0)
+			break;
+		alloced_pkeys[nr_alloced++] = new_pkey;
+	}
+
+	pkey_assert(nr_alloced > 0);
+	/* select a random one out of the allocated ones */
+	random_index = rand() % nr_alloced;
+	ret = alloced_pkeys[random_index];
+	/* now zero it out so we don't free it next */
+	alloced_pkeys[random_index] = 0;
+
+	/* go through the allocated ones that we did not want and free them */
+	for (i = 0; i < nr_alloced; i++) {
+		int free_ret;
+		if (!alloced_pkeys[i])
+			continue;
+		free_ret = sys_pkey_free(alloced_pkeys[i]);
+		pkey_assert(!free_ret);
+	}
+	dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	return ret;
+}
+
+int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+		unsigned long pkey)
+{
+	int nr_iterations = random() % 100;
+	int ret;
+
+	while (0) {
+		int rpkey = alloc_random_pkey();
+		ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey);
+		dprintf1("sys_mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n",
+				ptr, size, orig_prot, pkey, ret);
+		if (nr_iterations-- < 0)
+			break;
+
+		dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+		sys_pkey_free(rpkey);
+		dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	}
+	pkey_assert(pkey < NR_PKEYS);
+
+	ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey);
+	dprintf1("mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n",
+			ptr, size, orig_prot, pkey, ret);
+	pkey_assert(!ret);
+	dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__,
+			__LINE__, ret, __rdpkru(), shadow_pkru);
+	return ret;
+}
+
+struct pkey_malloc_record {
+	void *ptr;
+	long size;
+};
+struct pkey_malloc_record *pkey_malloc_records;
+long nr_pkey_malloc_records;
+void record_pkey_malloc(void *ptr, long size)
+{
+	long i;
+	struct pkey_malloc_record *rec = NULL;
+
+	for (i = 0; i < nr_pkey_malloc_records; i++) {
+		rec = &pkey_malloc_records[i];
+		/* find a free record */
+		if (rec)
+			break;
+	}
+	if (!rec) {
+		/* every record is full */
+		size_t old_nr_records = nr_pkey_malloc_records;
+		size_t new_nr_records = (nr_pkey_malloc_records * 2 + 1);
+		size_t new_size = new_nr_records * sizeof(struct pkey_malloc_record);
+		dprintf2("new_nr_records: %zd\n", new_nr_records);
+		dprintf2("new_size: %zd\n", new_size);
+		pkey_malloc_records = realloc(pkey_malloc_records, new_size);
+		pkey_assert(pkey_malloc_records != NULL);
+		rec = &pkey_malloc_records[nr_pkey_malloc_records];
+		/*
+		 * realloc() does not initialize memory, so zero it from
+		 * the first new record all the way to the end.
+		 */
+		for (i = 0; i < new_nr_records - old_nr_records; i++)
+			memset(rec + i, 0, sizeof(*rec));
+	}
+	dprintf3("filling malloc record[%d/%p]: {%p, %ld}\n",
+		(int)(rec - pkey_malloc_records), rec, ptr, size);
+	rec->ptr = ptr;
+	rec->size = size;
+	nr_pkey_malloc_records++;
+}
+
+void free_pkey_malloc(void *ptr)
+{
+	long i;
+	int ret;
+	dprintf3("%s(%p)\n", __func__, ptr);
+	for (i = 0; i < nr_pkey_malloc_records; i++) {
+		struct pkey_malloc_record *rec = &pkey_malloc_records[i];
+		dprintf4("looking for ptr %p at record[%ld/%p]: {%p, %ld}\n",
+				ptr, i, rec, rec->ptr, rec->size);
+		if ((ptr <  rec->ptr) ||
+		    (ptr >= rec->ptr + rec->size))
+			continue;
+
+		dprintf3("found ptr %p at record[%ld/%p]: {%p, %ld}\n",
+				ptr, i, rec, rec->ptr, rec->size);
+		nr_pkey_malloc_records--;
+		ret = munmap(rec->ptr, rec->size);
+		dprintf3("munmap ret: %d\n", ret);
+		pkey_assert(!ret);
+		dprintf3("clearing rec->ptr, rec: %p\n", rec);
+		rec->ptr = NULL;
+		dprintf3("done clearing rec->ptr, rec: %p\n", rec);
+		return;
+	}
+	pkey_assert(false);
+}
+
+
+void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
+{
+	void *ptr;
+	int ret;
+
+	rdpkru();
+	dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
+			size, prot, pkey);
+	pkey_assert(pkey < NR_PKEYS);
+	ptr = mmap(NULL, size, prot, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	pkey_assert(ptr != (void *)-1);
+	ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
+	pkey_assert(!ret);
+	record_pkey_malloc(ptr, size);
+	rdpkru();
+
+	dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
+	return ptr;
+}
+
+void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
+{
+	int ret;
+	void *ptr;
+
+	dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
+			size, prot, pkey);
+	/*
+	 * Guarantee we can fit at least one huge page in the resulting
+	 * allocation by allocating space for 2:
+	 */
+	size = ALIGN_UP(size, HPAGE_SIZE * 2);
+	ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	pkey_assert(ptr != (void *)-1);
+	record_pkey_malloc(ptr, size);
+	mprotect_pkey(ptr, size, prot, pkey);
+
+	dprintf1("unaligned ptr: %p\n", ptr);
+	ptr = ALIGN_PTR_UP(ptr, HPAGE_SIZE);
+	dprintf1("  aligned ptr: %p\n", ptr);
+	ret = madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE);
+	dprintf1("MADV_HUGEPAGE ret: %d\n", ret);
+	ret = madvise(ptr, HPAGE_SIZE, MADV_WILLNEED);
+	dprintf1("MADV_WILLNEED ret: %d\n", ret);
+	memset(ptr, 0, HPAGE_SIZE);
+
+	dprintf1("mmap()'d thp for pkey %d @ %p\n", pkey, ptr);
+	return ptr;
+}
+
+int hugetlb_setup_ok;
+#define GET_NR_HUGE_PAGES 10
+void setup_hugetlbfs(void)
+{
+	int err;
+	int fd;
+	int validated_nr_pages;
+	int i;
+	char buf[] = "123";
+
+	if (geteuid() != 0) {
+		fprintf(stderr, "WARNING: not run as root, can not do hugetlb test\n");
+		return;
+	}
+
+	cat_into_file(__stringify(GET_NR_HUGE_PAGES), "/proc/sys/vm/nr_hugepages");
+
+	/*
+	 * Now go make sure that we got the pages and that they
+	 * are 2M pages.  Someone might have made 1G the default.
+	 */
+	fd = open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages", O_RDONLY);
+	if (fd < 0) {
+		perror("opening sysfs 2M hugetlb config");
+		return;
+	}
+
+	/* -1 to guarantee leaving the trailing \0 */
+	err = read(fd, buf, sizeof(buf)-1);
+	close(fd);
+	if (err <= 0) {
+		perror("reading sysfs 2M hugetlb config");
+		return;
+	}
+
+	if (atoi(buf) != GET_NR_HUGE_PAGES) {
+		fprintf(stderr, "could not confirm 2M pages, got: '%s' expected %d\n",
+			buf, GET_NR_HUGE_PAGES);
+		return;
+	}
+
+	hugetlb_setup_ok = 1;
+}
+
+void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
+{
+	void *ptr;
+	int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB;
+
+	if (!hugetlb_setup_ok)
+		return PTR_ERR_ENOTSUP;
+
+	dprintf1("doing %s(%ld, %x, %x)\n", __func__, size, prot, pkey);
+	size = ALIGN_UP(size, HPAGE_SIZE * 2);
+	pkey_assert(pkey < NR_PKEYS);
+	ptr = mmap(NULL, size, PROT_NONE, flags, -1, 0);
+	pkey_assert(ptr != (void *)-1);
+	mprotect_pkey(ptr, size, prot, pkey);
+
+	record_pkey_malloc(ptr, size);
+
+	dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr);
+	return ptr;
+}
+
+void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
+{
+	void *ptr;
+	int fd;
+
+	dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
+			size, prot, pkey);
+	pkey_assert(pkey < NR_PKEYS);
+	fd = open("/dax/foo", O_RDWR);
+	pkey_assert(fd >= 0);
+
+	ptr = mmap(0, size, prot, MAP_SHARED, fd, 0);
+	pkey_assert(ptr != (void *)-1);
+
+	mprotect_pkey(ptr, size, prot, pkey);
+
+	record_pkey_malloc(ptr, size);
+
+	dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
+	close(fd);
+	return ptr;
+}
+
+void *(*pkey_malloc[])(long size, int prot, u16 pkey) = {
+
+	malloc_pkey_with_mprotect,
+	malloc_pkey_anon_huge,
+	malloc_pkey_hugetlb
+/* can not do direct with the pkey_mprotect() API:
+	malloc_pkey_mmap_direct,
+	malloc_pkey_mmap_dax,
+*/
+};
+
+void *malloc_pkey(long size, int prot, u16 pkey)
+{
+	void *ret;
+	static int malloc_type;
+	int nr_malloc_types = ARRAY_SIZE(pkey_malloc);
+
+	pkey_assert(pkey < NR_PKEYS);
+
+	while (1) {
+		pkey_assert(malloc_type < nr_malloc_types);
+
+		ret = pkey_malloc[malloc_type](size, prot, pkey);
+		pkey_assert(ret != (void *)-1);
+
+		malloc_type++;
+		if (malloc_type >= nr_malloc_types)
+			malloc_type = (random()%nr_malloc_types);
+
+		/* try again if the malloc_type we tried is unsupported */
+		if (ret == PTR_ERR_ENOTSUP)
+			continue;
+
+		break;
+	}
+
+	dprintf3("%s(%ld, prot=%x, pkey=%x) returning: %p\n", __func__,
+			size, prot, pkey, ret);
+	return ret;
+}
+
+int last_pkru_faults;
+void expected_pk_fault(int pkey)
+{
+	dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
+			__func__, last_pkru_faults, pkru_faults);
+	dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
+	pkey_assert(last_pkru_faults + 1 == pkru_faults);
+	pkey_assert(last_si_pkey == pkey);
+	/*
+	 * The signal handler shold have cleared out PKRU to let the
+	 * test program continue.  We now have to restore it.
+	 */
+	if (__rdpkru() != 0)
+		pkey_assert(0);
+
+	__wrpkru(shadow_pkru);
+	dprintf1("%s() set PKRU=%x to restore state after signal nuked it\n",
+			__func__, shadow_pkru);
+	last_pkru_faults = pkru_faults;
+	last_si_pkey = -1;
+}
+
+void do_not_expect_pk_fault(void)
+{
+	pkey_assert(last_pkru_faults == pkru_faults);
+}
+
+int test_fds[10] = { -1 };
+int nr_test_fds;
+void __save_test_fd(int fd)
+{
+	pkey_assert(fd >= 0);
+	pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds));
+	test_fds[nr_test_fds] = fd;
+	nr_test_fds++;
+}
+
+int get_test_read_fd(void)
+{
+	int test_fd = open("/etc/passwd", O_RDONLY);
+	__save_test_fd(test_fd);
+	return test_fd;
+}
+
+void close_test_fds(void)
+{
+	int i;
+
+	for (i = 0; i < nr_test_fds; i++) {
+		if (test_fds[i] < 0)
+			continue;
+		close(test_fds[i]);
+		test_fds[i] = -1;
+	}
+	nr_test_fds = 0;
+}
+
+#define barrier() __asm__ __volatile__("": : :"memory")
+__attribute__((noinline)) int read_ptr(int *ptr)
+{
+	/*
+	 * Keep GCC from optimizing this away somehow
+	 */
+	barrier();
+	return *ptr;
+}
+
+void test_read_of_write_disabled_region(int *ptr, u16 pkey)
+{
+	int ptr_contents;
+
+	dprintf1("disabling write access to PKEY[1], doing read\n");
+	pkey_write_deny(pkey);
+	ptr_contents = read_ptr(ptr);
+	dprintf1("*ptr: %d\n", ptr_contents);
+	dprintf1("\n");
+}
+void test_read_of_access_disabled_region(int *ptr, u16 pkey)
+{
+	int ptr_contents;
+
+	dprintf1("disabling access to PKEY[%02d], doing read @ %p\n", pkey, ptr);
+	rdpkru();
+	pkey_access_deny(pkey);
+	ptr_contents = read_ptr(ptr);
+	dprintf1("*ptr: %d\n", ptr_contents);
+	expected_pk_fault(pkey);
+}
+void test_write_of_write_disabled_region(int *ptr, u16 pkey)
+{
+	dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey);
+	pkey_write_deny(pkey);
+	*ptr = __LINE__;
+	expected_pk_fault(pkey);
+}
+void test_write_of_access_disabled_region(int *ptr, u16 pkey)
+{
+	dprintf1("disabling access to PKEY[%02d], doing write\n", pkey);
+	pkey_access_deny(pkey);
+	*ptr = __LINE__;
+	expected_pk_fault(pkey);
+}
+void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
+{
+	int ret;
+	int test_fd = get_test_read_fd();
+
+	dprintf1("disabling access to PKEY[%02d], "
+		 "having kernel read() to buffer\n", pkey);
+	pkey_access_deny(pkey);
+	ret = read(test_fd, ptr, 1);
+	dprintf1("read ret: %d\n", ret);
+	pkey_assert(ret);
+}
+void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
+{
+	int ret;
+	int test_fd = get_test_read_fd();
+
+	pkey_write_deny(pkey);
+	ret = read(test_fd, ptr, 100);
+	dprintf1("read ret: %d\n", ret);
+	if (ret < 0 && (DEBUG_LEVEL > 0))
+		perror("verbose read result (OK for this to be bad)");
+	pkey_assert(ret);
+}
+
+void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)
+{
+	int pipe_ret, vmsplice_ret;
+	struct iovec iov;
+	int pipe_fds[2];
+
+	pipe_ret = pipe(pipe_fds);
+
+	pkey_assert(pipe_ret == 0);
+	dprintf1("disabling access to PKEY[%02d], "
+		 "having kernel vmsplice from buffer\n", pkey);
+	pkey_access_deny(pkey);
+	iov.iov_base = ptr;
+	iov.iov_len = PAGE_SIZE;
+	vmsplice_ret = vmsplice(pipe_fds[1], &iov, 1, SPLICE_F_GIFT);
+	dprintf1("vmsplice() ret: %d\n", vmsplice_ret);
+	pkey_assert(vmsplice_ret == -1);
+
+	close(pipe_fds[0]);
+	close(pipe_fds[1]);
+}
+
+void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
+{
+	int ignored = 0xdada;
+	int futex_ret;
+	int some_int = __LINE__;
+
+	dprintf1("disabling write to PKEY[%02d], "
+		 "doing futex gunk in buffer\n", pkey);
+	*ptr = some_int;
+	pkey_write_deny(pkey);
+	futex_ret = syscall(SYS_futex, ptr, FUTEX_WAIT, some_int-1, NULL,
+			&ignored, ignored);
+	if (DEBUG_LEVEL > 0)
+		perror("futex");
+	dprintf1("futex() ret: %d\n", futex_ret);
+}
+
+/* Assumes that all pkeys other than 'pkey' are unallocated */
+void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
+{
+	int err;
+	int i;
+
+	/* Note: 0 is the default pkey, so don't mess with it */
+	for (i = 1; i < NR_PKEYS; i++) {
+		if (pkey == i)
+			continue;
+
+		dprintf1("trying get/set/free to non-allocated pkey: %2d\n", i);
+		err = sys_pkey_free(i);
+		pkey_assert(err);
+
+		/* not enforced when pkey_get() is not a syscall
+		err = pkey_get(i, 0);
+		pkey_assert(err < 0);
+		*/
+
+		err = sys_pkey_free(i);
+		pkey_assert(err);
+
+		err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, i);
+		pkey_assert(err);
+	}
+}
+
+/* Assumes that all pkeys other than 'pkey' are unallocated */
+void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
+{
+	int err;
+	int bad_flag = (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) + 1;
+	int bad_pkey = NR_PKEYS+99;
+
+	/* not enforced when pkey_get() is not a syscall
+	err = pkey_get(bad_pkey, bad_flag);
+	pkey_assert(err < 0);
+	*/
+
+	/* pass a known-invalid pkey in: */
+	err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, bad_pkey);
+	pkey_assert(err);
+}
+
+/* Assumes that all pkeys other than 'pkey' are unallocated */
+void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
+{
+	unsigned long flags;
+	unsigned long init_val;
+	int err;
+	int allocated_pkeys[NR_PKEYS] = {0};
+	int nr_allocated_pkeys = 0;
+	int i;
+
+	for (i = 0; i < NR_PKEYS*2; i++) {
+		int new_pkey;
+		dprintf1("%s() alloc loop: %d\n", __func__, i);
+		new_pkey = alloc_pkey();
+		dprintf4("%s()::%d, err: %d pkru: 0x%x shadow: 0x%x\n", __func__,
+				__LINE__, err, __rdpkru(), shadow_pkru);
+		rdpkru(); /* for shadow checking */
+		dprintf2("%s() errno: %d ENOSPC: %d\n", __func__, errno, ENOSPC);
+		if ((new_pkey == -1) && (errno == ENOSPC)) {
+			dprintf2("%s() failed to allocate pkey after %d tries\n",
+				__func__, nr_allocated_pkeys);
+			break;
+		}
+		pkey_assert(nr_allocated_pkeys < NR_PKEYS);
+		allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+	}
+
+	dprintf3("%s()::%d\n", __func__, __LINE__);
+
+	/*
+	 * ensure it did not reach the end of the loop without
+	 * failure:
+	 */
+	pkey_assert(i < NR_PKEYS*2);
+
+	/*
+	 * There are 16 pkeys supported in hardware.  One is taken
+	 * up for the default (0) and another can be taken up by
+	 * an execute-only mapping.  Ensure that we can allocate
+	 * at least 14 (16-2).
+	 */
+	pkey_assert(i >= NR_PKEYS-2);
+
+	for (i = 0; i < nr_allocated_pkeys; i++) {
+		err = sys_pkey_free(allocated_pkeys[i]);
+		pkey_assert(!err);
+		rdpkru(); /* for shadow checking */
+	}
+}
+
+void test_ptrace_of_child(int *ptr, u16 pkey)
+{
+	__attribute__((__unused__)) int peek_result;
+	pid_t child_pid;
+	void *ignored = 0;
+	long ret;
+	int status;
+	/*
+	 * This is the "control" for our little expermient.  Make sure
+	 * we can always access it when ptracing.
+	 */
+	int *plain_ptr_unaligned = malloc(HPAGE_SIZE);
+	int *plain_ptr = ALIGN_PTR_UP(plain_ptr_unaligned, PAGE_SIZE);
+
+	/*
+	 * Fork a child which is an exact copy of this process, of course.
+	 * That means we can do all of our tests via ptrace() and then plain
+	 * memory access and ensure they work differently.
+	 */
+	child_pid = fork_lazy_child();
+	dprintf1("[%d] child pid: %d\n", getpid(), child_pid);
+
+	ret = ptrace(PTRACE_ATTACH, child_pid, ignored, ignored);
+	if (ret)
+		perror("attach");
+	dprintf1("[%d] attach ret: %ld %d\n", getpid(), ret, __LINE__);
+	pkey_assert(ret != -1);
+	ret = waitpid(child_pid, &status, WUNTRACED);
+	if ((ret != child_pid) || !(WIFSTOPPED(status))) {
+		fprintf(stderr, "weird waitpid result %ld stat %x\n",
+				ret, status);
+		pkey_assert(0);
+	}
+	dprintf2("waitpid ret: %ld\n", ret);
+	dprintf2("waitpid status: %d\n", status);
+
+	pkey_access_deny(pkey);
+	pkey_write_deny(pkey);
+
+	/* Write access, untested for now:
+	ret = ptrace(PTRACE_POKEDATA, child_pid, peek_at, data);
+	pkey_assert(ret != -1);
+	dprintf1("poke at %p: %ld\n", peek_at, ret);
+	*/
+
+	/*
+	 * Try to access the pkey-protected "ptr" via ptrace:
+	 */
+	ret = ptrace(PTRACE_PEEKDATA, child_pid, ptr, ignored);
+	/* expect it to work, without an error: */
+	pkey_assert(ret != -1);
+	/* Now access from the current task, and expect an exception: */
+	peek_result = read_ptr(ptr);
+	expected_pk_fault(pkey);
+
+	/*
+	 * Try to access the NON-pkey-protected "plain_ptr" via ptrace:
+	 */
+	ret = ptrace(PTRACE_PEEKDATA, child_pid, plain_ptr, ignored);
+	/* expect it to work, without an error: */
+	pkey_assert(ret != -1);
+	/* Now access from the current task, and expect NO exception: */
+	peek_result = read_ptr(plain_ptr);
+	do_not_expect_pk_fault();
+
+	ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
+	pkey_assert(ret != -1);
+
+	ret = kill(child_pid, SIGKILL);
+	pkey_assert(ret != -1);
+
+	wait(&status);
+
+	free(plain_ptr_unaligned);
+}
+
+void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+{
+	void *p1;
+	int scratch;
+	int ptr_contents;
+	int ret;
+
+	p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE);
+	dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write);
+	/* lots_o_noops_around_write should be page-aligned already */
+	assert(p1 == &lots_o_noops_around_write);
+
+	/* Point 'p1' at the *second* page of the function: */
+	p1 += PAGE_SIZE;
+
+	madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+	lots_o_noops_around_write(&scratch);
+	ptr_contents = read_ptr(p1);
+	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+
+	ret = mprotect_pkey(p1, PAGE_SIZE, PROT_EXEC, (u64)pkey);
+	pkey_assert(!ret);
+	pkey_access_deny(pkey);
+
+	dprintf2("pkru: %x\n", rdpkru());
+
+	/*
+	 * Make sure this is an *instruction* fault
+	 */
+	madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+	lots_o_noops_around_write(&scratch);
+	do_not_expect_pk_fault();
+	ptr_contents = read_ptr(p1);
+	dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+	expected_pk_fault(pkey);
+}
+
+void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
+{
+	int size = PAGE_SIZE;
+	int sret;
+
+	if (cpu_has_pku()) {
+		dprintf1("SKIP: %s: no CPU support\n", __func__);
+		return;
+	}
+
+	sret = syscall(SYS_mprotect_key, ptr, size, PROT_READ, pkey);
+	pkey_assert(sret < 0);
+}
+
+void (*pkey_tests[])(int *ptr, u16 pkey) = {
+	test_read_of_write_disabled_region,
+	test_read_of_access_disabled_region,
+	test_write_of_write_disabled_region,
+	test_write_of_access_disabled_region,
+	test_kernel_write_of_access_disabled_region,
+	test_kernel_write_of_write_disabled_region,
+	test_kernel_gup_of_access_disabled_region,
+	test_kernel_gup_write_to_write_disabled_region,
+	test_executing_on_unreadable_memory,
+	test_ptrace_of_child,
+	test_pkey_syscalls_on_non_allocated_pkey,
+	test_pkey_syscalls_bad_args,
+	test_pkey_alloc_exhaust,
+};
+
+void run_tests_once(void)
+{
+	int *ptr;
+	int prot = PROT_READ|PROT_WRITE;
+
+	for (test_nr = 0; test_nr < ARRAY_SIZE(pkey_tests); test_nr++) {
+		int pkey;
+		int orig_pkru_faults = pkru_faults;
+
+		dprintf1("======================\n");
+		dprintf1("test %d preparing...\n", test_nr);
+
+		tracing_on();
+		pkey = alloc_random_pkey();
+		dprintf1("test %d starting with pkey: %d\n", test_nr, pkey);
+		ptr = malloc_pkey(PAGE_SIZE, prot, pkey);
+		dprintf1("test %d starting...\n", test_nr);
+		pkey_tests[test_nr](ptr, pkey);
+		dprintf1("freeing test memory: %p\n", ptr);
+		free_pkey_malloc(ptr);
+		sys_pkey_free(pkey);
+
+		dprintf1("pkru_faults: %d\n", pkru_faults);
+		dprintf1("orig_pkru_faults: %d\n", orig_pkru_faults);
+
+		tracing_off();
+		close_test_fds();
+
+		printf("test %2d PASSED (itertation %d)\n", test_nr, iteration_nr);
+		dprintf1("======================\n\n");
+	}
+	iteration_nr++;
+}
+
+void pkey_setup_shadow(void)
+{
+	shadow_pkru = __rdpkru();
+}
+
+int main(void)
+{
+	int nr_iterations = 22;
+
+	setup_handlers();
+
+	printf("has pku: %d\n", cpu_has_pku());
+
+	if (!cpu_has_pku()) {
+		int size = PAGE_SIZE;
+		int *ptr;
+
+		printf("running PKEY tests for unsupported CPU/OS\n");
+
+		ptr  = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+		assert(ptr != (void *)-1);
+		test_mprotect_pkey_on_unsupported_cpu(ptr, 1);
+		exit(0);
+	}
+
+	pkey_setup_shadow();
+	printf("startup pkru: %x\n", rdpkru());
+	setup_hugetlbfs();
+
+	while (nr_iterations-- > 0)
+		run_tests_once();
+
+	printf("done (all tests OK)\n");
+	return 0;
+}