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

2 files changed, 143 insertions, 8 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 1e52512..4dc1334 100644
--- a/arch/x86/mm/fault.c
+++ b/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
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index e8c4744..f88ce0e 100644
--- a/arch/x86/mm/pkeys.c
+++ b/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);