Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more misc uaccess and vfs updates from Al Viro:
 "The rest of the stuff from -next (more uaccess work) + assorted fixes"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  score: traps: Add missing include file to fix build error
  fs/super.c: don't fool lockdep in freeze_super() and thaw_super() paths
  fs/super.c: fix race between freeze_super() and thaw_super()
  overlayfs: Fix setting IOP_XATTR flag
  iov_iter: kernel-doc import_iovec() and rw_copy_check_uvector()
  blackfin: no access_ok() for __copy_{to,from}_user()
  arm64: don't zero in __copy_from_user{,_inatomic}
  arm: don't zero in __copy_from_user_inatomic()/__copy_from_user()
  arc: don't leak bits of kernel stack into coredump
  alpha: get rid of tail-zeroing in __copy_user()

arch/alpha/include/asm/uaccess.h

@@ -396,11 +396,12 @@ copy_to_user(void __user *to, const void *from, long n)
 extern inline long
 copy_from_user(void *to, const void __user *from, long n)
 {
+	long res = n;
 	if (likely(__access_ok((unsigned long)from, n, get_fs())))
-		n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
-	else
-		memset(to, 0, n);
-	return n;
+		res = __copy_from_user_inatomic(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 extern void __do_clear_user(void);

arch/alpha/lib/copy_user.S

@@ -126,22 +126,8 @@ $65:
 	bis $31,$31,$0
 $41:
 $35:
-$exitout:
-	ret $31,($28),1
-
 $exitin:
-	/* A stupid byte-by-byte zeroing of the rest of the output
-	   buffer.  This cures security holes by never leaving 
-	   random kernel data around to be copied elsewhere.  */
-
-	mov $0,$1
-$101:
-	EXO ( ldq_u $2,0($6) )
-	subq $1,1,$1
-	mskbl $2,$6,$2
-	EXO ( stq_u $2,0($6) )
-	addq $6,1,$6
-	bgt $1,$101
+$exitout:
 	ret $31,($28),1
 
 	.end __copy_user

arch/alpha/lib/ev6-copy_user.S

@@ -228,33 +228,12 @@ $dirtyentry:
 	bgt $0,$onebyteloop	# U  .. .. ..	: U L U L
 
 $zerolength:
+$exitin:
 $exitout:			# Destination for exception recovery(?)
 	nop			# .. .. .. E
 	nop			# .. .. E  ..
 	nop			# .. E  .. ..
 	ret $31,($28),1		# L0 .. .. ..	: L U L U
 
-$exitin:
-
-	/* A stupid byte-by-byte zeroing of the rest of the output
-	   buffer.  This cures security holes by never leaving 
-	   random kernel data around to be copied elsewhere.  */
-
-	nop
-	nop
-	nop
-	mov	$0,$1
-
-$101:
-	EXO ( stb $31,0($6) )	# L
-	subq $1,1,$1		# E
-	addq $6,1,$6		# E
-	bgt $1,$101		# U
-
-	nop
-	nop
-	nop
-	ret $31,($28),1		# L0
-
 	.end __copy_user
 	EXPORT_SYMBOL(__copy_user)

arch/arc/kernel/signal.c

@@ -107,13 +107,13 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	struct user_regs_struct uregs;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
-	if (!err)
-		set_current_blocked(&set);
-
 	err |= __copy_from_user(&uregs.scratch,
 				&(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
+	if (err)
+		return err;
 
+	set_current_blocked(&set);
 	regs->bta	= uregs.scratch.bta;
 	regs->lp_start	= uregs.scratch.lp_start;
 	regs->lp_end	= uregs.scratch.lp_end;
@@ -138,7 +138,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	regs->r0	= uregs.scratch.r0;
 	regs->sp	= uregs.scratch.sp;
 
-	return err;
+	return 0;
 }
 
 static inline int is_do_ss_needed(unsigned int magic)

arch/arm/include/asm/uaccess.h

@@ -533,11 +533,12 @@ __clear_user(void __user *addr, unsigned long n)
 
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
-		n = __copy_from_user(to, from, n);
-	else /* security hole - plug it */
-		memset(to, 0, n);
-	return n;
+	unsigned long res = n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)

arch/arm/lib/copy_from_user.S

@@ -100,12 +100,9 @@ EXPORT_SYMBOL(arm_copy_from_user)
 	.pushsection .fixup,"ax"
 	.align 0
 	copy_abort_preamble
-	ldmfd	sp!, {r1, r2}
-	sub	r3, r0, r1
-	rsb	r1, r3, r2
-	str	r1, [sp]
-	bl	__memzero
-	ldr	r0, [sp], #4
+	ldmfd	sp!, {r1, r2, r3}
+	sub	r0, r0, r1
+	rsb	r0, r0, r2
 	copy_abort_end
 	.popsection
 

arch/arm64/include/asm/uaccess.h

@@ -278,14 +278,16 @@ static inline unsigned long __must_check __copy_to_user(void __user *to, const v
 
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	unsigned long res = n;
 	kasan_check_write(to, n);
 
 	if (access_ok(VERIFY_READ, from, n)) {
 		check_object_size(to, n, false);
-		n = __arch_copy_from_user(to, from, n);
-	} else /* security hole - plug it */
-		memset(to, 0, n);
-	return n;
+		res = __arch_copy_from_user(to, from, n);
+	}
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)

arch/arm64/lib/copy_from_user.S

@@ -79,11 +79,6 @@ ENDPROC(__arch_copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
-9998:
-	sub	x0, end, dst
-9999:
-	strb	wzr, [dst], #1			// zero remaining buffer space
-	cmp	dst, end
-	b.lo	9999b
+9998:	sub	x0, end, dst			// bytes not copied
 	ret
 	.previous

arch/blackfin/include/asm/uaccess.h

@@ -163,18 +163,29 @@ static inline int bad_user_access_length(void)
 		: "a" (__ptr(ptr)));		\
 })
 
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
 static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
+__copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (likely(access_ok(VERIFY_READ, from, n))) {
 	memcpy(to, (const void __force *)from, n);
 	return 0;
-	}
+}
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	memcpy((void __force *)to, from, n);
+	SSYNC();
+	return 0;
+}
+
+static inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		return __copy_from_user(to, from, n);
 	memset(to, 0, n);
 	return n;
 }
@@ -182,12 +193,9 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (access_ok(VERIFY_WRITE, to, n))
-		memcpy((void __force *)to, from, n);
-	else
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		return __copy_to_user(to, from, n);
 	return n;
-	SSYNC();
-	return 0;
 }
 
 /*

arch/score/kernel/traps.c

@@ -29,6 +29,7 @@
 #include <asm/cacheflush.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
+#include <asm/uaccess.h>
 
 unsigned long exception_handlers[32];
 

fs/overlayfs/super.c

@@ -1303,6 +1303,12 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!oe)
 		goto out_put_cred;
 
+	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
+	sb->s_op = &ovl_super_operations;
+	sb->s_xattr = ovl_xattr_handlers;
+	sb->s_fs_info = ufs;
+	sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
+
 	root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR));
 	if (!root_dentry)
 		goto out_free_oe;
@@ -1326,12 +1332,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	ovl_inode_init(d_inode(root_dentry), realinode, !!upperpath.dentry);
 	ovl_copyattr(realinode, d_inode(root_dentry));
 
-	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
-	sb->s_op = &ovl_super_operations;
-	sb->s_xattr = ovl_xattr_handlers;
 	sb->s_root = root_dentry;
-	sb->s_fs_info = ufs;
-	sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
 
 	return 0;
 

fs/read_write.c

@@ -730,6 +730,35 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 /* A write operation does a read from user space and vice versa */
 #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
 
+/**
+ * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
+ *     into the kernel and check that it is valid.
+ *
+ * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @fast_pointer.
+ * @fast_pointer: Pointer to (usually small on-stack) kernel array.
+ * @ret_pointer: (output parameter) Pointer to a variable that will point to
+ *     either @fast_pointer, a newly allocated kernel array, or NULL,
+ *     depending on which array was used.
+ *
+ * This function copies an array of &struct iovec of @nr_segs from
+ * userspace into the kernel and checks that each element is valid (e.g.
+ * it does not point to a kernel address or cause overflow by being too
+ * large, etc.).
+ *
+ * As an optimization, the caller may provide a pointer to a small
+ * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
+ * (the size of this array, or 0 if unused, should be given in @fast_segs).
+ *
+ * @ret_pointer will always point to the array that was used, so the
+ * caller must take care not to call kfree() on it e.g. in case the
+ * @fast_pointer array was used and it was allocated on the stack.
+ *
+ * Return: The total number of bytes covered by the iovec array on success
+ *   or a negative error code on error.
+ */
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,

fs/super.c

@@ -1269,25 +1269,34 @@ EXPORT_SYMBOL(__sb_start_write);
 static void sb_wait_write(struct super_block *sb, int level)
 {
 	percpu_down_write(sb->s_writers.rw_sem + level-1);
-	/*
-	 * We are going to return to userspace and forget about this lock, the
-	 * ownership goes to the caller of thaw_super() which does unlock.
-	 *
-	 * FIXME: we should do this before return from freeze_super() after we
-	 * called sync_filesystem(sb) and s_op->freeze_fs(sb), and thaw_super()
-	 * should re-acquire these locks before s_op->unfreeze_fs(sb). However
-	 * this leads to lockdep false-positives, so currently we do the early
-	 * release right after acquire.
+}
+
+/*
+ * We are going to return to userspace and forget about these locks, the
+ * ownership goes to the caller of thaw_super() which does unlock().
  */
-	percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_);
+static void lockdep_sb_freeze_release(struct super_block *sb)
+{
+	int level;
+
+	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+		percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
 }
 
-static void sb_freeze_unlock(struct super_block *sb)
+/*
+ * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb).
+ */
+static void lockdep_sb_freeze_acquire(struct super_block *sb)
 {
 	int level;
 
 	for (level = 0; level < SB_FREEZE_LEVELS; ++level)
 		percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
+}
+
+static void sb_freeze_unlock(struct super_block *sb)
+{
+	int level;
 
 	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
 		percpu_up_write(sb->s_writers.rw_sem + level);
@@ -1379,10 +1388,11 @@ int freeze_super(struct super_block *sb)
 		}
 	}
 	/*
-	 * This is just for debugging purposes so that fs can warn if it
-	 * sees write activity when frozen is set to SB_FREEZE_COMPLETE.
+	 * For debugging purposes so that fs can warn if it sees write activity
+	 * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
 	 */
 	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
+	lockdep_sb_freeze_release(sb);
 	up_write(&sb->s_umount);
 	return 0;
 }
@@ -1399,7 +1409,7 @@ int thaw_super(struct super_block *sb)
 	int error;
 
 	down_write(&sb->s_umount);
-	if (sb->s_writers.frozen == SB_UNFROZEN) {
+	if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) {
 		up_write(&sb->s_umount);
 		return -EINVAL;
 	}
@@ -1409,11 +1419,14 @@ int thaw_super(struct super_block *sb)
 		goto out;
 	}
 
+	lockdep_sb_freeze_acquire(sb);
+
 	if (sb->s_op->unfreeze_fs) {
 		error = sb->s_op->unfreeze_fs(sb);
 		if (error) {
 			printk(KERN_ERR
 				"VFS:Filesystem thaw failed\n");
+			lockdep_sb_freeze_release(sb);
 			up_write(&sb->s_umount);
 			return error;
 		}

lib/iov_iter.c

@@ -1139,6 +1139,28 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 }
 EXPORT_SYMBOL(dup_iter);
 
+/**
+ * import_iovec() - Copy an array of &struct iovec from userspace
+ *     into the kernel, check that it is valid, and initialize a new
+ *     &struct iov_iter iterator to access it.
+ *
+ * @type: One of %READ or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @iov.
+ * @iov: (input and output parameter) Pointer to pointer to (usually small
+ *     on-stack) kernel array.
+ * @i: Pointer to iterator that will be initialized on success.
+ *
+ * If the array pointed to by *@iov is large enough to hold all @nr_segs,
+ * then this function places %NULL in *@iov on return. Otherwise, a new
+ * array will be allocated and the result placed in *@iov. This means that
+ * the caller may call kfree() on *@iov regardless of whether the small
+ * on-stack array was used or not (and regardless of whether this function
+ * returns an error or not).
+ *
+ * Return: 0 on success or negative error code on error.
+ */
 int import_iovec(int type, const struct iovec __user * uvector,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iov, struct iov_iter *i)