From: Arnd Bergmann <arnd@xxxxxxxx>
arm64 has an inline asm implementation of access_ok() that is derived from
the 32-bit arm version and optimized for the case that both the limit and
the size are variable. With set_fs() gone, the limit is always constant,
and the size usually is as well, so just using the default implementation
reduces the check into a comparison against a constant that can be
scheduled by the compiler.
On a defconfig build, this saves over 28KB of .text.
Acked-by: Robin Murphy <robin.murphy@xxxxxxx>
Acked-by: Mark Rutland <mark.rutland@xxxxxxx>
Signed-off-by: Arnd Bergmann <arnd@xxxxxxxx>
---
arch/arm64/include/asm/uaccess.h | 34 ++++++++++----------------------
1 file changed, 10 insertions(+), 24 deletions(-)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 2e20879fe3cf..199c553b740a 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -26,6 +26,14 @@
#include <asm/memory.h>
#include <asm/extable.h>
+static inline int __access_ok(const void __user *ptr, unsigned long size)
+{
+ unsigned long limit = TASK_SIZE_MAX;
+ unsigned long addr = (unsigned long)ptr;
+
+ return (size <= limit) && (addr <= (limit - size));
+}
+
/*
* Test whether a block of memory is a valid user space address.
* Returns 1 if the range is valid, 0 otherwise.
@@ -33,10 +41,8 @@
* This is equivalent to the following test:
* (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX
*/
-static inline unsigned long __range_ok(const void __user *addr, unsigned long size)
+static inline int access_ok(const void __user *addr, unsigned long size)
{
- unsigned long ret, limit = TASK_SIZE_MAX - 1;
-
/*
* Asynchronous I/O running in a kernel thread does not have the
* TIF_TAGGED_ADDR flag of the process owning the mm, so always untag
@@ -46,29 +52,9 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
(current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR)))
addr = untagged_addr(addr);
- __chk_user_ptr(addr);
- asm volatile(
- // A + B <= C + 1 for all A,B,C, in four easy steps:
- // 1: X = A + B; X' = X % 2^64
- " adds %0, %3, %2\n"
- // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
- " csel %1, xzr, %1, hi\n"
- // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
- // to compensate for the carry flag being set in step 4. For
- // X > 2^64, X' merely has to remain nonzero, which it does.
- " csinv %0, %0, xzr, cc\n"
- // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1
- // comes from the carry in being clear. Otherwise, we are
- // testing X' - C == 0, subject to the previous adjustments.
- " sbcs xzr, %0, %1\n"
- " cset %0, ls\n"
- : "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc");
-
- return ret;
+ return likely(__access_ok(addr, size));
}
-#define access_ok(addr, size) __range_ok(addr, size)
-
/*
* User access enabling/disabling.
*/
--
2.29.2
