s390/stackleak: provide fast __stackleak_poison() implementation

Provide an s390 specific __stackleak_poison() implementation which is
faster than the generic variant.

For the original implementation with an enforced 4kb stackframe for the
getpid() system call the system call overhead increases by a factor of 3 if
the stackleak feature is enabled. Using the s390 mvc based variant this is
reduced to an increase of 25% instead.

This is within the expected area, since the mvc based implementation is
more or less a memset64() variant which comes with similar results. See
commit 0b77d6701cf8 ("s390: implement memset16, memset32 & memset64").

Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/20230405130841.1350565-3-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index efffc28cbad8d1ac182a3c3f15275a4113b12eff..dc17896a001a9235d8cf21374f323917e46d1e97 100644 (file)
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -118,6 +118,41 @@ unsigned long vdso_size(void);
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
 
+#define __stackleak_poison __stackleak_poison
+static __always_inline void __stackleak_poison(unsigned long erase_low,
+                                              unsigned long erase_high,
+                                              unsigned long poison)
+{
+       unsigned long tmp, count;
+
+       count = erase_high - erase_low;
+       if (!count)
+               return;
+       asm volatile(
+               "       cghi    %[count],8\n"
+               "       je      2f\n"
+               "       aghi    %[count],-(8+1)\n"
+               "       srlg    %[tmp],%[count],8\n"
+               "       ltgr    %[tmp],%[tmp]\n"
+               "       jz      1f\n"
+               "0:     stg     %[poison],0(%[addr])\n"
+               "       mvc     8(256-8,%[addr]),0(%[addr])\n"
+               "       la      %[addr],256(%[addr])\n"
+               "       brctg   %[tmp],0b\n"
+               "1:     stg     %[poison],0(%[addr])\n"
+               "       larl    %[tmp],3f\n"
+               "       ex      %[count],0(%[tmp])\n"
+               "       j       4f\n"
+               "2:     stg     %[poison],0(%[addr])\n"
+               "       j       4f\n"
+               "3:     mvc     8(1,%[addr]),0(%[addr])\n"
+               "4:\n"
+               : [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp)
+               : [poison] "d" (poison)
+               : "memory", "cc"
+               );
+}
+
 /*
  * Thread structure
  */