vfs: make word-at-a-time accesses handle a non-existing page

It turns out that there are more cases than CONFIG_DEBUG_PAGEALLOC that
can have holes in the kernel address space: it seems to happen easily
with Xen, and it looks like the AMD gart64 code will also punch holes
dynamically.

Actually hitting that case is still very unlikely, so just do the
access, and take an exception and fix it up for the very unlikely case
of it being a page-crosser with no next page.

And hey, this abstraction might even help other architectures that have
other issues with unaligned word accesses than the possible missing next
page.  IOW, this could do the byte order magic too.

Peter Anvin fixed a thinko in the shifting for the exception case.

Reported-and-tested-by: Jana Saout <jana@saout.de>
Cc:  Peter Anvin <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/dcache.c b/fs/dcache.c
index b60ddc4..b80531c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -141,18 +141,29 @@
  * Compare 2 name strings, return 0 if they match, otherwise non-zero.
  * The strings are both count bytes long, and count is non-zero.
  */
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#include <asm/word-at-a-time.h>
+/*
+ * NOTE! 'cs' and 'scount' come from a dentry, so it has a
+ * aligned allocation for this particular component. We don't
+ * strictly need the load_unaligned_zeropad() safety, but it
+ * doesn't hurt either.
+ *
+ * In contrast, 'ct' and 'tcount' can be from a pathname, and do
+ * need the careful unaligned handling.
+ */
 static inline int dentry_cmp(const unsigned char *cs, size_t scount,
 				const unsigned char *ct, size_t tcount)
 {
-#ifdef CONFIG_DCACHE_WORD_ACCESS
 	unsigned long a,b,mask;
 
 	if (unlikely(scount != tcount))
 		return 1;
 
 	for (;;) {
-		a = *(unsigned long *)cs;
-		b = *(unsigned long *)ct;
+		a = load_unaligned_zeropad(cs);
+		b = load_unaligned_zeropad(ct);
 		if (tcount < sizeof(unsigned long))
 			break;
 		if (unlikely(a != b))
@@ -165,7 +176,13 @@
 	}
 	mask = ~(~0ul << tcount*8);
 	return unlikely(!!((a ^ b) & mask));
+}
+
 #else
+
+static inline int dentry_cmp(const unsigned char *cs, size_t scount,
+				const unsigned char *ct, size_t tcount)
+{
 	if (scount != tcount)
 		return 1;
 
@@ -177,9 +194,10 @@
 		tcount--;
 	} while (tcount);
 	return 0;
-#endif
 }
 
+#endif
+
 static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);