x86: Replace assembly access_ok() with a C variant
It turns out that the assembly variant doesn't actually produce that
good code, presumably partly because it creates a long dependency
chain with no scheduling, and partly because we cannot get a flags
result out of gcc (which could be fixed with asm goto, but it turns
out not to be worth it.)
The C code allows gcc to schedule and generate multiple (easily
predictable) branches, and as a side benefit we can really optimize
the case where the size is constant.
Link: http://lkml.kernel.org/r/CA%2B55aFzPBdbfKovMT8Edr4SmE2_=%2BOKJFac9XW2awegogTkVTA@mail.gmail.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8ec57c0..84ecf1d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -40,22 +40,28 @@
/*
* Test whether a block of memory is a valid user space address.
* Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
- *
- * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
+static inline int __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
+{
+ /*
+ * If we have used "sizeof()" for the size,
+ * we know it won't overflow the limit (but
+ * it might overflow the 'addr', so it's
+ * important to subtract the size from the
+ * limit, not add it to the address).
+ */
+ if (__builtin_constant_p(size))
+ return addr > limit - size;
+
+ /* Arbitrary sizes? Be careful about overflow */
+ addr += size;
+ return (addr < size) || (addr > limit);
+}
#define __range_not_ok(addr, size, limit) \
({ \
- unsigned long flag, roksum; \
__chk_user_ptr(addr); \
- asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \
- : "=&r" (flag), "=r" (roksum) \
- : "1" (addr), "g" ((long)(size)), \
- "rm" (limit)); \
- flag; \
+ __chk_range_not_ok((unsigned long __force)(addr), size, limit); \
})
/**